def model_fn(features, mode, params):
# ***********************************************************************************************
# * Backbone Net *
# ***********************************************************************************************
net_config = params["net_config"]
IS_TRAINING = False
image_window = features["image_window"]
origin_image_batch = features["image"]
image_batch = origin_image_batch - tf.convert_to_tensor(
net_config.PIXEL_MEANS, dtype=tf.float32)
# there is is_training means that bn is training, so it is important!
_, share_net = get_network_byname(inputs=image_batch,
config=net_config,
is_training=IS_TRAINING,
reuse=tf.AUTO_REUSE)
# ***********************************************************************************************
# * FPN *
# ***********************************************************************************************
feature_pyramid = build_fpn.build_feature_pyramid(share_net, net_config)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(feature_pyramid=feature_pyramid,
image_window=image_window,
config=net_config)
# rpn_proposals_scores==(2000,)
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(IS_TRAINING)
# ***********************************************************************************************
# * Fast RCNN Head *
# ***********************************************************************************************
fast_rcnn = build_head.FPNHead(feature_pyramid=feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
origin_image=origin_image_batch,
gtboxes_and_label=None,
config=net_config,
is_training=IS_TRAINING,
image_window=image_window)
detections = fast_rcnn.head_detection()
# ***********************************************************************************************
# * Summary *
# ***********************************************************************************************
if mode == tf.estimator.ModeKeys.PREDICT:
predicts = {
"image": origin_image_batch,
"predict_bbox": detections[:, :, :4],
"predict_class_id": detections[:, :, 4],
"predict_scores": detections[:, :, 5],
"rpn_proposal_boxes": rpn_proposals_boxes,
"rpn_proposals_scores": rpn_proposals_scores,
"gt_box_labels": features["gt_box_labels"]
}
return tf.estimator.EstimatorSpec(mode, predictions=predicts)
def eval_dict_convert(img_num):
with tf.Graph().as_default():
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=False)
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=True,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
gtboxes_and_label=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.
FINAL_SCORE_THRESHOLD, # show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
use_dropout=False,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
# train
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
gtbox_dict = {}
predict_dict = {}
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label_batch, _fast_rcnn_decode_boxes, \
_fast_rcnn_score, _detection_category \
= sess.run([img_name_batch, img_batch, gtboxes_and_label_batch, fast_rcnn_decode_boxes,
fast_rcnn_score, detection_category])
end = time.time()
# gtboxes convert dict
gtbox_dict[str(_img_name_batch[0])] = []
predict_dict[str(_img_name_batch[0])] = []
for j, box in enumerate(_gtboxes_and_label_batch[0]):
bbox_dict = {}
bbox_dict['bbox'] = np.array(
_gtboxes_and_label_batch[0][j, :-1], np.float64)
bbox_dict['name'] = LABEl_NAME_MAP[int(
_gtboxes_and_label_batch[0][j, -1])]
gtbox_dict[str(_img_name_batch[0])].append(bbox_dict)
for label in NAME_LABEL_MAP.keys():
if label == 'back_ground':
continue
else:
temp_dict = {}
temp_dict['name'] = label
ind = np.where(
_detection_category == NAME_LABEL_MAP[label])[0]
temp_boxes = _fast_rcnn_decode_boxes[ind]
temp_score = np.reshape(_fast_rcnn_score[ind], [-1, 1])
temp_dict['bbox'] = np.array(
np.concatenate([temp_boxes, temp_score], axis=1),
np.float64)
predict_dict[str(_img_name_batch[0])].append(temp_dict)
view_bar(
'{} image cost {}s'.format(str(_img_name_batch[0]),
(end - start)), i + 1, img_num)
fw1 = open('gtboxes_dict.pkl', 'w')
fw2 = open('predict_dict.pkl', 'w')
pickle.dump(gtbox_dict, fw1)
pickle.dump(predict_dict, fw2)
fw1.close()
fw2.close()
coord.request_stop()
coord.join(threads)
def detect_img(file_paths,
des_folder,
det_th,
h_len,
w_len,
h_overlap,
w_overlap,
show_res=False):
with tf.Graph().as_default():
img_plac = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8)
img_tensor = tf.cast(img_plac, tf.float32) - tf.constant(
[103.939, 116.779, 123.68])
img_batch = image_preprocess.short_side_resize_for_inference_data(
img_tensor,
target_shortside_len=cfgs.SHORT_SIDE_LEN,
is_resize=False)
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
gtboxes_and_label=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=det_th,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
use_dropout=False,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
for img_path in file_paths:
start = timer()
img = cv2.imread(img_path)
box_res = []
label_res = []
score_res = []
imgH = img.shape[0]
imgW = img.shape[1]
for hh in range(0, imgH, h_len - h_overlap):
if imgH - hh - 1 < h_len:
hh_ = imgH - h_len
else:
hh_ = hh
for ww in range(0, imgW, w_len - w_overlap):
if imgW - ww - 1 < w_len:
ww_ = imgW - w_len
else:
ww_ = ww
src_img = img[hh_:(hh_ + h_len), ww_:(ww_ + w_len), :]
boxes, labels, scores = sess.run(
[
fast_rcnn_decode_boxes, detection_category,
fast_rcnn_score
],
feed_dict={img_plac: src_img})
if show_res:
visualize_detection(src_img, boxes, scores)
if len(boxes) > 0:
for ii in range(len(boxes)):
box = boxes[ii]
box[0] = box[0] + hh_
box[1] = box[1] + ww_
box[2] = box[2] + hh_
box[3] = box[3] + ww_
box_res.append(box)
label_res.append(labels[ii])
score_res.append(scores[ii])
box_res = np.array(box_res)
label_res = np.array(label_res)
score_res = np.array(score_res)
box_res_, label_res_, score_res_ = [], [], []
for sub_class in range(1, cfgs.CLASS_NUM + 1):
index = np.where(label_res == sub_class)[0]
if len(index) == 0:
continue
tmp_boxes_h = box_res[index]
tmp_label_h = label_res[index]
tmp_score_h = score_res[index]
tmp_boxes_h = np.array(tmp_boxes_h)
tmp = np.zeros(
[tmp_boxes_h.shape[0], tmp_boxes_h.shape[1] + 1])
tmp[:, 0:-1] = tmp_boxes_h
tmp[:, -1] = np.array(tmp_score_h)
inx = nms.py_cpu_nms(dets=np.array(tmp, np.float32),
thresh=0.7,
max_output_size=500)
box_res_.extend(np.array(tmp_boxes_h)[inx])
score_res_.extend(np.array(tmp_score_h)[inx])
label_res_.extend(np.array(tmp_label_h)[inx])
time_elapsed = timer() - start
print("{} detection time : {:.4f} sec".format(
img_path.split('/')[-1].split('.')[0], time_elapsed))
mkdir(des_folder)
img_np = draw_box_cv(np.array(img, np.float32) -
np.array([103.939, 116.779, 123.68]),
boxes=np.array(box_res_),
labels=np.array(label_res_),
scores=np.array(score_res_))
cv2.imwrite(
des_folder + '/{}_fpn.jpg'.format(
img_path.split('/')[-1].split('.')[0]), img_np)
coord.request_stop()
coord.join(threads)
def model_fn(features,
mode,
params,
config):
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
net_config = params["net_config"]
IS_TRAINING = False
origin_image_batch = features["image"]
image_window = features["image_window"]
image_batch = origin_image_batch - net_config.PIXEL_MEANS
# there is is_training means that bn is training, so it is important!
_, share_net = get_network_byname(inputs=image_batch,
config=net_config,
is_training=IS_TRAINING,
reuse=tf.AUTO_REUSE)
# ***********************************************************************************************
# * fpn *
# ***********************************************************************************************
feature_pyramid = build_fpn.build_feature_pyramid(share_net, net_config)
# ***********************************************************************************************
# * rpn *
# ***********************************************************************************************
rpn = build_rpn.RPN(feature_pyramid=feature_pyramid,
image_window=image_window,
config=net_config)
# rpn_proposals_scores==(2000,)
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(IS_TRAINING)
# ***********************************************************************************************
# * Rerference image *
# ***********************************************************************************************
reference_image = load_reference_image()
reference_image = tf.cast(reference_image, tf.float32)
reference_image = reference_image - net_config.PIXEL_MEANS
_, reference_share_net = get_network_byname(inputs=reference_image,
config=net_config,
is_training=False,
reuse=tf.AUTO_REUSE)
reference_feature_pyramid = build_fpn.build_feature_pyramid(reference_share_net, net_config)
# average the features of support images
# reference_feature_pyramid[key](C*S, H, W, 256)---->(C, 7, 7, 256)
with tf.variable_scope('reference_feature_origision'):
for key, value in reference_feature_pyramid.items():
reference_feature_pyramid[key] = tf.image.resize_bilinear(reference_feature_pyramid[key],
(net_config.ROI_SIZE, net_config.ROI_SIZE))
reference_feature_pyramid[key] = tf.reduce_mean(tf.reshape(reference_feature_pyramid[key],
(net_config.NUM_CLASS-1, net_config.NUM_SUPPROTS,
net_config.ROI_SIZE, net_config.ROI_SIZE,
256)), axis=1)
# average the features of fpn features
average_fpn_feature = []
for key, value in reference_feature_pyramid.items():
average_fpn_feature.append(value)
reference_fpn_features = tf.reduce_mean(tf.stack(average_fpn_feature, axis=0), axis=0)
# compute the negative features
with tf.variable_scope("reference_negative"):
with slim.arg_scope([slim.conv2d],
padding="SAME",
weights_initializer=tf.glorot_uniform_initializer(),
weights_regularizer=slim.l2_regularizer(net_config.WEIGHT_DECAY)):
# the shape of positive features is (1, H, W, C*channels)
positive_features = tf.reshape(tf.transpose(reference_fpn_features, (1, 2, 0, 3)),
(1, net_config.ROI_SIZE, net_config.ROI_SIZE, (net_config.NUM_CLASS-1)*256))
# (1, H, W, channels)
negative_feature = slim.conv2d(positive_features, num_outputs=256, kernel_size=[3,3], stride=1)
total_refernece_feature = tf.concat([negative_feature, reference_fpn_features], axis=0)
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(feature_pyramid=feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
origin_image=origin_image_batch,
gtboxes_and_label=None,
reference_feature=total_refernece_feature,
config=net_config,
is_training=IS_TRAINING,
image_window=image_window)
detections = fast_rcnn.fast_rcnn_detection()
# ***********************************************************************************************
# * Summary *
# ***********************************************************************************************
if mode == tf.estimator.ModeKeys.PREDICT:
predicts = {"image": origin_image_batch,
"predict_bbox": detections[:, :, :4],
"predict_class_id": detections[:, :, 4], "predict_scores": detections[:, :, 5],
"rpn_proposal_boxes": rpn_proposals_boxes,
"rpn_proposals_scores":rpn_proposals_scores,
"gt_box_labels": features["gt_box_labels"]}
return tf.estimator.EstimatorSpec(mode, predictions=predicts)
def test(img_num):
with tf.Graph().as_default():
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=False)
gtboxes_and_label, head = get_head(
tf.squeeze(gtboxes_and_label_batch, 0))
gtboxes_and_label = tf.py_func(back_forward_convert,
inp=[gtboxes_and_label],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
head_quadrant = tf.py_func(get_head_quadrant,
inp=[head, gtboxes_and_label],
Tout=tf.float32)
head_quadrant = tf.reshape(head_quadrant, [-1, 1])
gtboxes_and_label_minAreaRectangle = get_horizen_minAreaRectangle(
gtboxes_and_label)
gtboxes_and_label_minAreaRectangle = tf.reshape(
gtboxes_and_label_minAreaRectangle, [-1, 5])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
img_batch=img_batch,
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
gtboxes_and_label_minAreaRectangle=
gtboxes_and_label_minAreaRectangle,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
# iou>0.5 is positive, iou<0.5 is negative
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL,
head_quadrant=head_quadrant)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category, \
fast_rcnn_decode_boxes_rotate, fast_rcnn_score_rotate, fast_rcnn_head_quadrant, \
num_of_objects_rotate, detection_category_rotate = fast_rcnn.fast_rcnn_predict()
# train
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label, _gtboxes_and_label_minAreaRectangle, _head_quadrant, \
_fast_rcnn_decode_boxes, _fast_rcnn_score, _detection_category, _fast_rcnn_decode_boxes_rotate, \
_fast_rcnn_score_rotate, _fast_rcnn_head_quadrant, _detection_category_rotate \
= sess.run([img_name_batch, img_batch, gtboxes_and_label, gtboxes_and_label_minAreaRectangle, head_quadrant,
fast_rcnn_decode_boxes, fast_rcnn_score, detection_category, fast_rcnn_decode_boxes_rotate,
fast_rcnn_score_rotate, fast_rcnn_head_quadrant, detection_category_rotate])
end = time.time()
_img_batch = np.squeeze(_img_batch, axis=0)
_img_batch_fpn_horizonal = help_utils.draw_box_cv(
_img_batch,
boxes=_fast_rcnn_decode_boxes,
labels=_detection_category,
scores=_fast_rcnn_score)
_img_batch_fpn_rotate = help_utils.draw_rotate_box_cv(
_img_batch,
boxes=_fast_rcnn_decode_boxes_rotate,
labels=_detection_category_rotate,
scores=_fast_rcnn_score_rotate,
head=np.argmax(_fast_rcnn_head_quadrant, axis=1))
mkdir(cfgs.TEST_SAVE_PATH)
cv2.imwrite(
cfgs.TEST_SAVE_PATH +
'/{}_horizontal_fpn.jpg'.format(str(_img_name_batch[0])),
_img_batch_fpn_horizonal)
cv2.imwrite(
cfgs.TEST_SAVE_PATH +
'/{}_rotate_fpn.jpg'.format(str(_img_name_batch[0])),
_img_batch_fpn_rotate)
temp_label_horizontal = np.reshape(_gtboxes_and_label[:, -1:],
[
-1,
]).astype(np.int64)
temp_label_rotate = np.reshape(_gtboxes_and_label[:, -1:], [
-1,
]).astype(np.int64)
_img_batch_gt_horizontal = help_utils.draw_box_cv(
_img_batch,
boxes=_gtboxes_and_label_minAreaRectangle[:, :-1],
labels=temp_label_horizontal,
scores=None)
_img_batch_gt_rotate = help_utils.draw_rotate_box_cv(
_img_batch,
boxes=_gtboxes_and_label[:, :-1],
labels=temp_label_rotate,
scores=None,
head=np.reshape(_head_quadrant, [
-1,
]))
cv2.imwrite(
cfgs.TEST_SAVE_PATH +
'/{}_horizontal_gt.jpg'.format(str(_img_name_batch[0])),
_img_batch_gt_horizontal)
cv2.imwrite(
cfgs.TEST_SAVE_PATH +
'/{}_rotate_gt.jpg'.format(str(_img_name_batch[0])),
_img_batch_gt_rotate)
view_bar(
'{} image cost {}s'.format(str(_img_name_batch[0]),
(end - start)), i + 1, img_num)
coord.request_stop()
coord.join(threads)
def test(args):
with tf.Graph().as_default():
img_batch = tf.placeholder(shape=[1, None, None, 3], dtype=tf.float32)
# img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
# next_batch(dataset_name=cfgs.DATASET_NAME,
# batch_size=cfgs.BATCH_SIZE,
# shortside_len=cfgs.SHORT_SIDE_LEN,
# is_training=False)
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
gtboxes_and_label=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.
FINAL_SCORE_THRESHOLD, # show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
use_dropout=False,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
# train
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer(
checkpoint_path=args.weights)
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
# coord = tf.train.Coordinator()
# threads = tf.train.start_queue_runners(sess, coord)
test_filenames = [file for file in os.listdir(args.test_dir)]
for i in tqdm(range(args.img_num)):
# _img_name_batch, _img_batch, _gtboxes_and_label_batch, _fast_rcnn_decode_boxes, \
# _fast_rcnn_score, _detection_category \
# = sess.run([img_name_batch, img_batch, gtboxes_and_label_batch, fast_rcnn_decode_boxes,
# fast_rcnn_score, detection_category])
img_test = cv2.imread(args.test_dir + '/' + test_filenames[i])
img_test, img_test_4dim = no_tensor_pic_prepross(
img_test, cfgs.SHORT_SIDE_LEN)
_fast_rcnn_decode_boxes, \
_fast_rcnn_score, _detection_category \
= sess.run([fast_rcnn_decode_boxes,
fast_rcnn_score, detection_category], feed_dict={img_batch: img_test_4dim})
# _img_batch = np.squeeze(_img_batch, axis=0)
# print(_detection_category)
_img_batch_fpn = help_utils.draw_box_cv(
img_test,
boxes=_fast_rcnn_decode_boxes,
labels=_detection_category,
scores=_fast_rcnn_score)
mkdir(cfgs.TEST_SAVE_PATH)
cv2.imwrite(
cfgs.TEST_SAVE_PATH +
'/{}_fpn.jpg'.format(str(test_filenames[i])),
_img_batch_fpn)
def train():
with tf.Graph().as_default():
with tf.name_scope('get_batch'):
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=True)
gtboxes_and_label = tf.py_func(
back_forward_convert,
inp=[tf.squeeze(gtboxes_and_label_batch, 0)],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
gtboxes_and_label_minAreaRectangle = get_horizen_minAreaRectangle(
gtboxes_and_label)
gtboxes_and_label_minAreaRectangle = tf.reshape(
gtboxes_and_label_minAreaRectangle, [-1, 5])
with tf.name_scope('draw_gtboxes'):
gtboxes_in_img = draw_box_with_color(
img_batch,
tf.reshape(gtboxes_and_label_minAreaRectangle,
[-1, 5])[:, :-1],
text=tf.shape(gtboxes_and_label_minAreaRectangle)[0])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * rpn *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=gtboxes_and_label_minAreaRectangle,
is_training=True,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.
RPN_IOU_NEGATIVE_THRESHOLD, # iou>=0.7 is positive box, iou< 0.3 is negative
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
rpn_location_loss, rpn_classification_loss = rpn.rpn_losses()
rpn_total_loss = rpn_classification_loss + rpn_location_loss
with tf.name_scope('draw_proposals'):
# score > 0.5 is object
rpn_object_boxes_indices = tf.reshape(
tf.where(tf.greater(rpn_proposals_scores, 0.5)), [-1])
rpn_object_boxes = tf.gather(rpn_proposals_boxes,
rpn_object_boxes_indices)
rpn_proposals_objcet_boxes_in_img = draw_box_with_color(
img_batch,
rpn_object_boxes,
text=tf.shape(rpn_object_boxes)[0])
rpn_proposals_boxes_in_img = draw_box_with_color(
img_batch,
rpn_proposals_boxes,
text=tf.shape(rpn_proposals_boxes)[0])
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=gtboxes_and_label,
gtboxes_and_label_minAreaRectangle=
gtboxes_and_label_minAreaRectangle,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.
FINAL_SCORE_THRESHOLD, # show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD, # iou>0.5 is positive, iou<0.5 is negative
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=True,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
fast_rcnn_location_loss, fast_rcnn_classification_loss = fast_rcnn.fast_rcnn_loss(
)
fast_rcnn_total_loss = fast_rcnn_location_loss + fast_rcnn_classification_loss
with tf.name_scope('draw_boxes_with_categories'):
fast_rcnn_predict_boxes_in_imgs = draw_boxes_with_categories(
img_batch=img_batch,
boxes=fast_rcnn_decode_boxes,
labels=detection_category,
scores=fast_rcnn_score)
# train
total_loss = slim.losses.get_total_loss()
global_step = slim.get_or_create_global_step()
lr = tf.train.piecewise_constant(
global_step,
boundaries=[np.int64(20000), np.int64(40000)],
values=[cfgs.LR, cfgs.LR / 10, cfgs.LR / 100])
tf.summary.scalar('lr', lr)
optimizer = tf.train.MomentumOptimizer(lr, momentum=cfgs.MOMENTUM)
train_op = slim.learning.create_train_op(
total_loss, optimizer, global_step) # rpn_total_loss,
# train_op = optimizer.minimize(second_classification_loss, global_step)
# ***********************************************************************************************
# * Summary *
# ***********************************************************************************************
# ground truth and predict
tf.summary.image('img/gtboxes', gtboxes_in_img)
tf.summary.image('img/faster_rcnn_predict',
fast_rcnn_predict_boxes_in_imgs)
# rpn loss and image
tf.summary.scalar('rpn/rpn_location_loss', rpn_location_loss)
tf.summary.scalar('rpn/rpn_classification_loss',
rpn_classification_loss)
tf.summary.scalar('rpn/rpn_total_loss', rpn_total_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_location_loss',
fast_rcnn_location_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_classification_loss',
fast_rcnn_classification_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_total_loss',
fast_rcnn_total_loss)
tf.summary.scalar('loss/total_loss', total_loss)
tf.summary.image('rpn/rpn_all_boxes', rpn_proposals_boxes_in_img)
tf.summary.image('rpn/rpn_object_boxes',
rpn_proposals_objcet_boxes_in_img)
# learning_rate
tf.summary.scalar('learning_rate', lr)
summary_op = tf.summary.merge_all()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
saver = tf.train.Saver(max_to_keep=10)
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
summary_path = os.path.join(FLAGS.summary_path, cfgs.VERSION)
mkdir(summary_path)
summary_writer = tf.summary.FileWriter(summary_path,
graph=sess.graph)
for step in range(cfgs.MAX_ITERATION):
training_time = time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time()))
start = time.time()
_global_step, _img_name_batch, _rpn_location_loss, _rpn_classification_loss, \
_rpn_total_loss, _fast_rcnn_location_loss, _fast_rcnn_classification_loss, \
_fast_rcnn_total_loss, _total_loss, _ = \
sess.run([global_step, img_name_batch, rpn_location_loss, rpn_classification_loss,
rpn_total_loss, fast_rcnn_location_loss, fast_rcnn_classification_loss,
fast_rcnn_total_loss, total_loss, train_op])
end = time.time()
if step % 10 == 0:
print(""" {}: step{} image_name:{} |\t
rpn_loc_loss:{} |\t rpn_cla_loss:{} |\t rpn_total_loss:{} |
fast_rcnn_loc_loss:{} |\t fast_rcnn_cla_loss:{} |\t fast_rcnn_total_loss:{} |
total_loss:{} |\t pre_cost_time:{}s""" \
.format(training_time, _global_step, str(_img_name_batch[0]), _rpn_location_loss,
_rpn_classification_loss, _rpn_total_loss, _fast_rcnn_location_loss,
_fast_rcnn_classification_loss, _fast_rcnn_total_loss, _total_loss,
(end - start)))
if step % 50 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, _global_step)
summary_writer.flush()
if (step > 0
and step % 1000 == 0) or (step
== cfgs.MAX_ITERATION - 1):
save_dir = os.path.join(FLAGS.trained_checkpoint,
cfgs.VERSION)
mkdir(save_dir)
save_ckpt = os.path.join(
save_dir, 'voc_' + str(_global_step) + 'model.ckpt')
saver.save(sess, save_ckpt)
print(' weights had been saved')
coord.request_stop()
coord.join(threads)
def train():
with tf.Graph().as_default():
with tf.name_scope('get_batch'):
img_name_batch, img_batch, gtboxes_and_label_batch = \
next_batch(data_tfrecord_location=cfgs.DATASET_DIR,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
longside_len=cfgs.LONG_SIDE_LEN,
is_training=True)
image_height, image_width = tf.shape(img_batch)[1], tf.shape(
img_batch)[2]
# with tf.name_scope('draw_gtboxes'):
# gtboxes_in_img = draw_box_with_color(img_batch, tf.reshape(gtboxes_and_label_batch, [-1, 5])[:, :-1],
# text=tf.shape(gtboxes_and_label_batch)[1])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# fpn
feature_pyramid = build_fpn.build_feature_pyramid(
share_net) # [P2,P3,P4,P5,P6]
# ***********************************************************************************************
# * rpn *
# ***********************************************************************************************
rpn = build_rpn.RPN(feature_pyramid=feature_pyramid,
image_height=image_height,
image_width=image_width,
gtboxes_and_label=gtboxes_and_label_batch,
is_training=True)
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
is_training=True)
rpn_location_loss, rpn_classification_loss = rpn.rpn_losses()
rpn_total_loss = rpn_classification_loss + rpn_location_loss
# ***********************************************************************************************
# * Fast RCNN Head *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FAST_RCNN(
feature_pyramid=feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
gtboxes_and_label=gtboxes_and_label_batch,
origin_image=img_batch,
is_training=True,
image_height=image_height,
image_width=image_width)
detections = fast_rcnn.head_detection()
if cfgs.DEBUG:
print_tensors(rpn_proposals_scores[0, :50], "scores") # 前50
print_tensors(rpn_proposals_boxes[0, :50, :], "bbox")
rpn_proposals_vision = draw_boxes_with_scores(
img_batch[0, :, :, :], rpn_proposals_boxes[0, :50, :],
rpn_proposals_scores[0, :50])
fast_rcnn_vision = draw_boxes_with_categories_and_scores(
img_batch[0, :, :, :], detections[0, :, :4],
detections[0, :, 4], detections[0, :, 5], cfgs.LABEL_TO_NAME)
tf.summary.image("rpn_proposals_vision", rpn_proposals_vision)
tf.summary.image("fast_rcnn_vision", fast_rcnn_vision)
fast_rcnn_location_loss, fast_rcnn_classification_loss = fast_rcnn.head_loss(
)
fast_rcnn_total_loss = fast_rcnn_location_loss + fast_rcnn_classification_loss
# train
with tf.name_scope("regularization_losses"):
regularization_list = [
tf.nn.l2_loss(w.read_value()) *
cfgs.WEIGHT_DECAY[cfgs.NET_NAME] /
tf.cast(tf.size(w.read_value()), tf.float32)
for w in tf.trainable_variables()
if 'gamma' not in w.name and 'beta' not in w.name
]
regularization_loss = tf.add_n(regularization_list)
total_loss = regularization_loss + fast_rcnn_total_loss + rpn_total_loss
total_loss = tf.cond(tf.is_nan(total_loss), lambda: 0.0,
lambda: total_loss)
global_step = tf.train.get_or_create_global_step()
lr = tf.train.piecewise_constant(
global_step,
boundaries=[np.int64(10000), np.int64(20000)],
values=[cfgs.LR, cfgs.LR / 10, cfgs.LR / 100])
# * Summary *
# ***********************************************************************************************
# rpn loss and image
tf.summary.scalar('rpn_location_loss',
rpn_location_loss,
family="rpn_loss")
tf.summary.scalar('rpn_classification_loss',
rpn_classification_loss,
family="rpn_loss")
tf.summary.scalar('rpn_total_loss', rpn_total_loss, family="rpn_loss")
tf.summary.scalar('fast_rcnn_location_loss',
fast_rcnn_location_loss,
family="head_loss")
tf.summary.scalar('fast_rcnn_classification_loss',
fast_rcnn_classification_loss,
family="head_loss")
tf.summary.scalar('fast_rcnn_total_loss',
fast_rcnn_total_loss,
family="head_loss")
tf.summary.scalar("regularization_loss", regularization_loss)
tf.summary.scalar('total_loss', total_loss)
tf.summary.scalar('learning_rate', lr)
# optimizer = tf.train.MomentumOptimizer(lr, momentum=cfgs.MOMENTUM)
#
# train_op = slim.learning.create_train_op(total_loss, optimizer, global_step)
with tf.name_scope("optimizer"):
optimizer = tf.train.MomentumOptimizer(lr, momentum=cfgs.MOMENTUM)
optimizer = tf.contrib.estimator.TowerOptimizer(optimizer)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies([tf.group(*update_ops)]):
grads = optimizer.compute_gradients(total_loss)
# clip gradients
grads = tf.contrib.training.clip_gradient_norms(
grads, cfgs.CLIP_GRADIENT_NORM)
train_op = optimizer.apply_gradients(grads, global_step)
summary_op = tf.summary.merge_all()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
# restorer, restore_ckpt = restore_model.get_restorer(test=False,checkpoint_path=cfgs.TRAINED_MODEL_DIR)
saver = tf.train.Saver(max_to_keep=3)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
# if not restorer is None:
# restorer.restore(sess, restore_ckpt)
# print('restore model successfully')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
summary_path = cfgs.SUMMARY_PATH
summary_writer = tf.summary.FileWriter(summary_path,
graph=sess.graph)
for step in range(cfgs.MAX_ITERATION):
training_time = time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time()))
start = time.time()
_global_step,_rpn_location_loss, _rpn_classification_loss, \
_rpn_total_loss, _fast_rcnn_location_loss, _fast_rcnn_classification_loss, \
_fast_rcnn_total_loss, _total_loss, _ = \
sess.run([global_step,rpn_location_loss, rpn_classification_loss,
rpn_total_loss, fast_rcnn_location_loss, fast_rcnn_classification_loss,
fast_rcnn_total_loss,total_loss, train_op])
end = time.time()
if step % 50 == 0:
print("""{}: step{}
rpn_loc_loss:{:.4f} | rpn_cla_loss:{:.4f} | rpn_total_loss:{:.4f}
fast_rcnn_loc_loss:{:.4f} | fast_rcnn_cla_loss:{:.4f} | fast_rcnn_total_loss:{:.4f}
| total_loss:{:.4f} | pre_cost_time:{:.4f}s""".
format(training_time, _global_step,
_rpn_location_loss, _rpn_classification_loss,
_rpn_total_loss, _fast_rcnn_location_loss,
_fast_rcnn_classification_loss,
_fast_rcnn_total_loss, _total_loss,
(end - start)))
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, _global_step)
summary_writer.flush()
if (step > 0
and step % 5000 == 0) or (step
== cfgs.MAX_ITERATION - 1):
save_dir = cfgs.TRAINED_MODEL_DIR
save_ckpt = os.path.join(
save_dir, 'sarship' + '{}_'.format(cfgs.NET_NAME) +
str(_global_step) + 'model.ckpt')
saver.save(sess, save_ckpt)
print('Weights have been saved to {}.'.format(save_ckpt))
print('Training done')
coord.request_stop()
coord.join(threads)
def eval_dict_convert(img_num, mode):
with tf.Graph().as_default():
# img = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8)
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=False)
gtboxes_and_label = tf.py_func(
back_forward_convert,
inp=[tf.squeeze(gtboxes_and_label_batch, 0)],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
gtboxes_and_label_minAreaRectangle = get_horizon_minAreaRectangle(
gtboxes_and_label)
gtboxes_and_label_minAreaRectangle = tf.reshape(
gtboxes_and_label_minAreaRectangle, [-1, 5])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=gtboxes_and_label,
is_training=False,
share_head=False,
share_net=share_net,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
anchor_angles=cfgs.ANCHOR_ANGLES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
anchor_stride=cfgs.ANCHOR_STRIDE,
top_k_nms=cfgs.RPN_TOP_K_NMS,
kernel_size=cfgs.KERNEL_SIZE,
use_angles_condition=False,
anchor_angle_threshold=cfgs.RPN_ANCHOR_ANGLES_THRESHOLD,
nms_angle_threshold=cfgs.RPN_NMS_ANGLES_THRESHOLD,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
# iou>=0.7 is positive box, iou< 0.3 is negative
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=cfgs.
IS_FILTER_OUTSIDE_BOXES, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
scope='')
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
_, _, rpn_predict_boxes, rpn_predict_scores = rpn.rpn_losses()
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
stop_gradient_for_proposals=False,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
top_k_nms=cfgs.FAST_RCNN_TOP_K_NMS,
nms_angle_threshold=cfgs.FAST_RCNN_NMS_ANGLES_THRESHOLD,
use_angle_condition=False,
level=cfgs.LEVEL,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
boxes_angle_threshold=cfgs.FAST_RCNN_BOXES_ANGLES_THRESHOLD,
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
##############################################################################################
if cfgs.NEED_AUXILIARY:
predict_boxes = tf.concat(
[fast_rcnn_decode_boxes, rpn_predict_boxes], axis=0)
predict_scores = tf.concat(
[fast_rcnn_score, rpn_predict_scores - 0.2], axis=0)
rpn_predict_label = tf.ones([
tf.shape(rpn_predict_scores)[0],
], tf.int64)
labels = tf.concat([detection_category, rpn_predict_label], axis=0)
# valid_indices = nms_rotate.nms_rotate(decode_boxes=predict_boxes,
# scores=predict_scores,
# iou_threshold=0.15,
# max_output_size=30,
# use_angle_condition=False,
# angle_threshold=15,
# use_gpu=True)
valid_indices = tf.py_func(nms_rotate.nms_rotate_cpu,
inp=[
predict_boxes, predict_scores,
tf.constant(0.15, tf.float32),
tf.constant(30, tf.float32)
],
Tout=tf.int64)
fast_rcnn_decode_boxes = tf.gather(predict_boxes, valid_indices)
fast_rcnn_score = tf.gather(predict_scores, valid_indices)
detection_category = tf.gather(labels, valid_indices)
##############################################################################################
if mode == 0:
fast_rcnn_decode_boxes = get_horizon_minAreaRectangle(
fast_rcnn_decode_boxes, False)
# train
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
gtboxes_dict = {}
predict_dict = {}
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label, _fast_rcnn_decode_boxes, \
_gtboxes_and_label_minAreaRectangle, _fast_rcnn_score, _detection_category \
= sess.run([img_name_batch, img_batch, gtboxes_and_label, fast_rcnn_decode_boxes,
gtboxes_and_label_minAreaRectangle, fast_rcnn_score, detection_category])
end = time.time()
# gtboxes convert dict
gtboxes_dict[str(_img_name_batch[0])] = []
predict_dict[str(_img_name_batch[0])] = []
# for j, box in enumerate(_gtboxes_and_label):
# bbox_dict = {}
# bbox_dict['bbox'] = np.array(_gtboxes_and_label[j, :-1], np.float64)
# bbox_dict['name'] = LABEl_NAME_MAP[int(_gtboxes_and_label[j, -1])]
# gtbox_dict[str(_img_name_batch[0])].append(bbox_dict)
#
# for label in NAME_LABEL_MAP.keys():
# if label == 'back_ground':
# continue
# else:
# temp_dict = {}
# temp_dict['name'] = label
#
# ind = np.where(_detection_category == NAME_LABEL_MAP[label])[0]
# temp_boxes = _fast_rcnn_decode_boxes[ind]
# temp_score = np.reshape(_fast_rcnn_score[ind], [-1, 1])
# temp_dict['bbox'] = np.array(np.concatenate([temp_boxes, temp_score], axis=1), np.float64)
# predict_dict[str(_img_name_batch[0])].append(temp_dict)
if mode == 0:
gtboxes_list, predict_list = \
make_dict_packle(_gtboxes_and_label_minAreaRectangle, _fast_rcnn_decode_boxes,
_fast_rcnn_score, _detection_category)
else:
gtboxes_list, predict_list = \
make_dict_packle(_gtboxes_and_label, _fast_rcnn_decode_boxes,
_fast_rcnn_score, _detection_category)
gtboxes_dict[str(_img_name_batch[0])].extend(gtboxes_list)
predict_dict[str(_img_name_batch[0])].extend(predict_list)
view_bar(
'{} image cost {}s'.format(str(_img_name_batch[0]),
(end - start)), i + 1, img_num)
fw1 = open('gtboxes_dict.pkl', 'w')
fw2 = open('predict_dict.pkl', 'w')
pickle.dump(gtboxes_dict, fw1)
pickle.dump(predict_dict, fw2)
fw1.close()
fw2.close()
coord.request_stop()
coord.join(threads)
def train():
with tf.Graph().as_default():
tf.set_random_seed(1234)
with tf.name_scope('get_batch'):
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=True,
is_val=False)
with tf.name_scope('draw_gtboxes'):
gtboxes_in_img = draw_box_with_color(
img_batch,
tf.reshape(gtboxes_and_label_batch, [-1, 5])[:, :-1],
text=tf.shape(gtboxes_and_label_batch)[1])
# *********************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * rpn *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=tf.squeeze(gtboxes_and_label_batch, 0),
is_training=True,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.
RPN_IOU_NEGATIVE_THRESHOLD, # iou>=0.7 is positive box, iou< 0.3 is negative
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
rpn_location_loss, rpn_classification_loss = rpn.rpn_losses()
rpn_total_loss = rpn_classification_loss + rpn_location_loss
with tf.name_scope('draw_proposals'):
# score > 0.5 is object
rpn_object_boxes_indices = tf.reshape(
tf.where(tf.greater(rpn_proposals_scores, 0.5)), [-1])
rpn_object_boxes = tf.gather(rpn_proposals_boxes,
rpn_object_boxes_indices)
rpn_proposals_objcet_boxes_in_img = draw_box_with_color(
img_batch,
rpn_object_boxes,
text=tf.shape(rpn_object_boxes)[0])
rpn_proposals_boxes_in_img = draw_box_with_color(
img_batch,
rpn_proposals_boxes,
text=tf.shape(rpn_proposals_boxes)[0])
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=tf.squeeze(gtboxes_and_label_batch, 0),
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.
FINAL_SCORE_THRESHOLD, # show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD, # iou>0.5 is positive, iou<0.5 is negative
use_dropout=False,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=True,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
fast_rcnn_location_loss, fast_rcnn_classification_loss = fast_rcnn.fast_rcnn_loss(
)
fast_rcnn_total_loss = fast_rcnn_location_loss + fast_rcnn_classification_loss
with tf.name_scope('draw_boxes_with_categories'):
fast_rcnn_predict_boxes_in_imgs = draw_boxes_with_categories(
img_batch=img_batch,
boxes=fast_rcnn_decode_boxes,
labels=detection_category,
scores=fast_rcnn_score)
# train
total_loss = slim.losses.get_total_loss()
global_step = slim.get_or_create_global_step() #返回并创建全局步长张量
#
# lr = tf.train.piecewise_constant(global_step,
# boundaries=[np.int64(10000), np.int64(20000)],
# values=[cfgs.LR, cfgs.LR / 10, cfgs.LR / 100])
lr = tf.train.exponential_decay(cfgs.LR,
global_step,
decay_steps=5000,
decay_rate=1 / 2.,
staircase=True)
# lr = tf.train.piecewise_constant(global_step,
# boundaries=[np.int64(30000), np.int64(40000)],
# values=[lr, cfgs.LR/100, cfgs.LR/1000])
tf.summary.scalar('learning_rate', lr)
# optimizer = tf.train.MomentumOptimizer(lr, momentum=cfgs.MOMENTUM)
optimizer = tf.train.AdamOptimizer(lr,
beta1=cfgs.MOMENTUM,
beta2=0.999,
epsilon=1e-8,
use_locking=False,
name='Adam')
# optimizer = tf.train.RMSPropOptimizer(lr, decay=0.9, epsilon=1e-6, name='RMSProp')
#创建一个计算梯度并返回损失的Operation
train_op = slim.learning.create_train_op(
total_loss, optimizer, global_step) # rpn_total_loss,
# train_op = optimizer.minimize(second_classification_loss, global_step)
# ***********************************************************************************************
# * Summary *
# ***********************************************************************************************
# ground truth and predict
tf.summary.image('img/gtboxes', gtboxes_in_img)
tf.summary.image('img/faster_rcnn_predict',
fast_rcnn_predict_boxes_in_imgs)
# rpn loss and image
tf.summary.scalar('rpn/rpn_location_loss', rpn_location_loss)
tf.summary.scalar('rpn/rpn_classification_loss',
rpn_classification_loss)
tf.summary.scalar('rpn/rpn_total_loss', rpn_total_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_location_loss',
fast_rcnn_location_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_classification_loss',
fast_rcnn_classification_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_total_loss',
fast_rcnn_total_loss)
tf.summary.scalar('loss/total_loss', total_loss)
# #
# tf.summary.image('C2', _concact_features(share_net['resnet_v1_50/block1/unit_2/bottleneck_v1'][:, :, :, 0:16]), 1)
# tf.summary.image('C3', _concact_features(share_net['resnet_v1_50/block2/unit_3/bottleneck_v1'][:, :, :, 0:16]), 1)
# tf.summary.image('C4', _concact_features(share_net['resnet_v1_50/block3/unit_5/bottleneck_v1'][:, :, :, 0:16]), 1)
# tf.summary.image('C5', _concact_features(share_net['resnet_v1_50/block4'][:, :, :, 0:16]), 1)
# tf.summary.image('P2', _concact_features(rpn.feature_pyramid['P2'][:, :, :, 0:16]),1)
# tf.summary.image('P3', _concact_features(rpn.feature_pyramid['P3'][:, :, :, 0:16]),1)
# tf.summary.image('P4', _concact_features(rpn.feature_pyramid['P4'][:, :, :, 0:16]),1)
# tf.summary.image('P5', _concact_features(rpn.feature_pyramid['P5'][:, :, :, 0:16]), 1)
# tf.summary.image('rpn/rpn_all_boxes', rpn_proposals_boxes_in_img)
# tf.summary.image('rpn/rpn_object_boxes', rpn_proposals_objcet_boxes_in_img)
# learning_rate
# tf.summary.scalar('learning_rate', lr)
summary_op = tf.summary.merge_all()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
saver = tf.train.Saver(max_to_keep=16)
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
if cfgs.NET_NAME == 'pvanet':
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
start = 0
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
start = int("".join(
list(restore_ckpt.split('/')[-1])[4:8])) + 1
else:
# read_npy.load_initial_weights(sess)
read_npy.load_ckpt_weights(sess)
else:
sess.run(init_op)
# print(sess.run('resnet_v1_50/block4/unit_3/bottleneck_v1/conv3/BatchNorm/moving_variance'))
# print(sess.run('vgg_16/block4/unit_3/bottleneck_v1/conv3/BatchNorm/moving_variance'))
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
start = 0
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
# start = int("".join(list(restore_ckpt.split('/')[-1])[4:8]))+1
summary_path = os.path.join(FLAGS.summary_path, cfgs.VERSION)
mkdir(summary_path)
summary_writer = tf.summary.FileWriter(summary_path,
graph=sess.graph)
df = pd.DataFrame(
[],
columns=['Recall', 'Precision', 'mAP', 'F1_score'],
index=[])
for step in range(0, cfgs.MAX_ITERATION):
# print(img_name_batch.eval())
training_time = time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time()))
start = time.time()
_global_step, _img_name_batch, _rpn_location_loss, _rpn_classification_loss, \
_rpn_total_loss, _fast_rcnn_location_loss, _fast_rcnn_classification_loss, \
_fast_rcnn_total_loss, _total_loss, _ = \
sess.run([global_step, img_name_batch, rpn_location_loss, rpn_classification_loss,
rpn_total_loss, fast_rcnn_location_loss, fast_rcnn_classification_loss,
fast_rcnn_total_loss, total_loss, train_op])
end = time.time()
# if step == 100:
# save_dir = os.path.join(FLAGS.trained_checkpoint, cfgs.VERSION)
# mkdir(save_dir)
#
# save_ckpt = os.path.join(save_dir, 'voc_' + str(_global_step) + 'model.ckpt')
# saver.save(sess, save_ckpt)
# print(' weights had been saved')
# if step == 500:
# save_dir = os.path.join(FLAGS.trained_checkpoint, cfgs.VERSION)
# mkdir(save_dir)
#
# save_ckpt = os.path.join(save_dir, 'voc_' + str(_global_step) + 'model.ckpt')
# saver.save(sess, save_ckpt)
# print(' weights had been saved')
if step % 50 == 0:
print(""" {}: step{} image_name:{} |\t
rpn_loc_loss:{} |\t rpn_cla_loss:{} |\t rpn_total_loss:{} |
fast_rcnn_loc_loss:{} |\t fast_rcnn_cla_loss:{} |\t fast_rcnn_total_loss:{} |
total_loss:{} |\t pre_cost_time:{}s""" \
.format(training_time, _global_step, str(_img_name_batch[0]), _rpn_location_loss,
_rpn_classification_loss, _rpn_total_loss, _fast_rcnn_location_loss,
_fast_rcnn_classification_loss, _fast_rcnn_total_loss, _total_loss,
(end - start)))
# print(""" {}: step{} image_name:{} |\t
# rpn_loc_loss:{} |\t
# fast_rcnn_loc_loss:{} |\t fast_rcnn_cla_loss:{} |\t fast_rcnn_total_loss:{} |
# total_loss:{} |\t pre_cost_time:{}s""" \
# .format(training_time, _global_step, str(_img_name_batch[0]), _rpn_location_loss,
# _fast_rcnn_location_loss,
# _fast_rcnn_classification_loss, _fast_rcnn_total_loss, _total_loss,
# (end - start)))
if step % 250 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, _global_step)
summary_writer.flush()
if (step > 0 and step % 2000 == 0) or (
step > 0 and
(step == 1000)) or (step == cfgs.MAX_ITERATION - 1):
save_dir = os.path.join(FLAGS.trained_checkpoint,
cfgs.VERSION)
mkdir(save_dir)
save_ckpt = os.path.join(
save_dir, 'voc_' + str(_global_step) + 'model.ckpt')
saver.save(sess, save_ckpt)
print(' weights had been saved')
#保存验证集信息
if (step > 0
and step % 2000 == 0) or (step
== cfgs.MAX_ITERATION - 1):
save_excel = os.path.abspath(
'../'
) + r'/Loss/' + cfgs.NET_NAME + r'_' + cfgs.VERSION
mkdir(save_excel)
new_index = np.append(df.index, [str(step)])
df2 = pd.DataFrame(
[valval.val(is_val=True)],
columns=['Recall', 'Precision', 'mAP', 'F1_score'])
df = df.append(df2)
df.index = new_index
df.to_excel(save_excel + r'/validation.xls')
print('validation result had been saved')
coord.request_stop()
coord.join(threads)
def eval_dict_convert(img_num, mode):
with tf.Graph().as_default():
# img = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8)
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=False)
gtboxes_and_label = tf.py_func(back_forward_convert,
inp=[tf.squeeze(gtboxes_and_label_batch, 0)],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
gtboxes_and_label_minAreaRectangle = get_horizon_minAreaRectangle(gtboxes_and_label)
gtboxes_and_label_minAreaRectangle = tf.reshape(gtboxes_and_label_minAreaRectangle, [-1, 5])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=gtboxes_and_label,
is_training=False,
share_head=False,
share_net=share_net,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
anchor_angles=cfgs.ANCHOR_ANGLES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
anchor_stride=cfgs.ANCHOR_STRIDE,
top_k_nms=cfgs.RPN_TOP_K_NMS,
kernel_size=cfgs.KERNEL_SIZE,
use_angles_condition=False,
anchor_angle_threshold=cfgs.RPN_ANCHOR_ANGLES_THRESHOLD,
nms_angle_threshold=cfgs.RPN_NMS_ANGLES_THRESHOLD,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
# iou>=0.7 is positive box, iou< 0.3 is negative
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=cfgs.IS_FILTER_OUTSIDE_BOXES, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
scope='')
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals() # rpn_score shape: [300, ]
_, _, rpn_predict_boxes, rpn_predict_scores = rpn.rpn_losses()
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
stop_gradient_for_proposals=False,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
top_k_nms=cfgs.FAST_RCNN_TOP_K_NMS,
nms_angle_threshold=cfgs.FAST_RCNN_NMS_ANGLES_THRESHOLD,
use_angle_condition=False,
level=cfgs.LEVEL,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.FAST_RCNN_IOU_POSITIVE_THRESHOLD,
boxes_angle_threshold=cfgs.FAST_RCNN_BOXES_ANGLES_THRESHOLD,
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
##############################################################################################
if cfgs.NEED_AUXILIARY:
predict_boxes = tf.concat([fast_rcnn_decode_boxes, rpn_predict_boxes], axis=0)
predict_scores = tf.concat([fast_rcnn_score, rpn_predict_scores - 0.2], axis=0)
rpn_predict_label = tf.ones([tf.shape(rpn_predict_scores)[0], ], tf.int64)
labels = tf.concat([detection_category, rpn_predict_label], axis=0)
# valid_indices = nms_rotate.nms_rotate(decode_boxes=predict_boxes,
# scores=predict_scores,
# iou_threshold=0.15,
# max_output_size=30,
# use_angle_condition=False,
# angle_threshold=15,
# use_gpu=True)
valid_indices = tf.py_func(nms_rotate.nms_rotate_cpu,
inp=[predict_boxes, predict_scores,
tf.constant(0.15, tf.float32), tf.constant(30, tf.float32)],
Tout=tf.int64)
fast_rcnn_decode_boxes = tf.gather(predict_boxes, valid_indices)
fast_rcnn_score = tf.gather(predict_scores, valid_indices)
detection_category = tf.gather(labels, valid_indices)
##############################################################################################
if mode == 0:
fast_rcnn_decode_boxes = get_horizon_minAreaRectangle(fast_rcnn_decode_boxes, False)
# train
init_op = tf.group(
tf.global_variables_initializer(),
tf.local_variables_initializer()
)
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
gtboxes_dict = {}
predict_dict = {}
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label, _fast_rcnn_decode_boxes, \
_gtboxes_and_label_minAreaRectangle, _fast_rcnn_score, _detection_category \
= sess.run([img_name_batch, img_batch, gtboxes_and_label, fast_rcnn_decode_boxes,
gtboxes_and_label_minAreaRectangle, fast_rcnn_score, detection_category])
end = time.time()
# gtboxes convert dict
gtboxes_dict[str(_img_name_batch[0])] = []
predict_dict[str(_img_name_batch[0])] = []
# for j, box in enumerate(_gtboxes_and_label):
# bbox_dict = {}
# bbox_dict['bbox'] = np.array(_gtboxes_and_label[j, :-1], np.float64)
# bbox_dict['name'] = LABEl_NAME_MAP[int(_gtboxes_and_label[j, -1])]
# gtbox_dict[str(_img_name_batch[0])].append(bbox_dict)
#
# for label in NAME_LABEL_MAP.keys():
# if label == 'back_ground':
# continue
# else:
# temp_dict = {}
# temp_dict['name'] = label
#
# ind = np.where(_detection_category == NAME_LABEL_MAP[label])[0]
# temp_boxes = _fast_rcnn_decode_boxes[ind]
# temp_score = np.reshape(_fast_rcnn_score[ind], [-1, 1])
# temp_dict['bbox'] = np.array(np.concatenate([temp_boxes, temp_score], axis=1), np.float64)
# predict_dict[str(_img_name_batch[0])].append(temp_dict)
if mode == 0:
gtboxes_list, predict_list = \
make_dict_packle(_gtboxes_and_label_minAreaRectangle, _fast_rcnn_decode_boxes,
_fast_rcnn_score, _detection_category)
else:
gtboxes_list, predict_list = \
make_dict_packle(_gtboxes_and_label, _fast_rcnn_decode_boxes,
_fast_rcnn_score, _detection_category)
gtboxes_dict[str(_img_name_batch[0])].extend(gtboxes_list)
predict_dict[str(_img_name_batch[0])].extend(predict_list)
view_bar('{} image cost {}s'.format(str(_img_name_batch[0]), (end - start)), i + 1, img_num)
fw1 = open('gtboxes_dict.pkl', 'w')
fw2 = open('predict_dict.pkl', 'w')
pickle.dump(gtboxes_dict, fw1)
pickle.dump(predict_dict, fw2)
fw1.close()
fw2.close()
coord.request_stop()
coord.join(threads)
def train():
with tf.Graph().as_default():
with tf.name_scope('get_batch'):
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=True)
with tf.name_scope('draw_gtboxes'):
gtboxes_in_img = draw_box_with_color(img_batch, tf.reshape(gtboxes_and_label_batch, [-1, 5])[:, :-1],
text=tf.shape(gtboxes_and_label_batch)[1])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * rpn *
# ***********************************************************************************************
rpn = build_rpn.RPN(net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=tf.squeeze(gtboxes_and_label_batch, 0),
is_training=True,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
# iou>=0.7 is positive box, iou< 0.3 is negative
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals() # rpn_score shape: [300, ]
rpn_location_loss, rpn_classification_loss = rpn.rpn_losses()
rpn_total_loss = 10*rpn_classification_loss + rpn_location_loss
with tf.name_scope('draw_proposals'):
# score > 0.5 is object
rpn_object_boxes_indices = tf.reshape(tf.where(tf.greater(rpn_proposals_scores, 0.5)), [-1])
rpn_object_boxes = tf.gather(rpn_proposals_boxes, rpn_object_boxes_indices)
rpn_proposals_objcet_boxes_in_img = draw_box_with_color(img_batch, rpn_object_boxes,
text=tf.shape(rpn_object_boxes)[0])
rpn_proposals_boxes_in_img = draw_box_with_color(img_batch, rpn_proposals_boxes,
text=tf.shape(rpn_proposals_boxes)[0])
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=tf.squeeze(gtboxes_and_label_batch, 0),
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD, # show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
# iou>0.5 is positive, iou<0.5 is negative
fast_rcnn_positives_iou_threshold=cfgs.FAST_RCNN_IOU_POSITIVE_THRESHOLD,
use_dropout=False,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=True,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
fast_rcnn_location_l, fast_rcnn_classification_loss = fast_rcnn.fast_rcnn_loss()
fast_rcnn_total_loss = fast_rcnn_location_l + 10*fast_rcnn_classification_loss
with tf.name_scope('draw_boxes_with_categories'):
fast_rcnn_predict_boxes_in_imgs = draw_boxes_with_categories(img_batch=img_batch,
boxes=fast_rcnn_decode_boxes,
labels=detection_category,
scores=fast_rcnn_score)
# train
added_loss = rpn_total_loss + fast_rcnn_total_loss
total_loss = tf.losses.get_total_loss()
global_step = tf.train.get_or_create_global_step()
lr = tf.train.piecewise_constant(global_step,
boundaries=[np.int64(20000), np.int64(40000)],
values=[cfgs.LR, cfgs.LR / 10, cfgs.LR / 100])
tf.summary.scalar('lr', lr)
optimizer = tf.train.MomentumOptimizer(lr, momentum=cfgs.MOMENTUM)
# optimizer = tf.train.AdamOptimizer(lr)
# train_op = slim.learning.create_train_op(total_loss, optimizer, global_step) # rpn_total_loss,
train_op = slim.learning.create_train_op(added_loss, optimizer, global_step) # rpn_total_loss,
# train_op = optimizer.minimize(second_classification_loss, global_step)
# **********************************-*************************************************************
# * Summary *
# ***********************************************************************************************
# ground truth and predict
tf.summary.image('img/gtboxes', gtboxes_in_img)
tf.summary.image('img/faster_rcnn_predict', fast_rcnn_predict_boxes_in_imgs)
# rpn loss and image
tf.summary.scalar('rpn/rpn_location_loss', rpn_location_loss)
tf.summary.scalar('rpn/rpn_classification_loss', rpn_classification_loss)
tf.summary.scalar('rpn/rpn_total_loss', rpn_total_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_location_lossum', fast_rcnn_location_l)
tf.summary.scalar('fast_rcnn/fast_rcnn_classification_loss', fast_rcnn_classification_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_total_loss', fast_rcnn_total_loss)
tf.summary.scalar('loss/added_loss', added_loss)
tf.summary.scalar('loss/total_loss', total_loss)
tf.summary.image('rpn/rpn_all_boxes', rpn_proposals_boxes_in_img)
tf.summary.image('rpn/rpn_object_boxes', rpn_proposals_objcet_boxes_in_img)
# learning_rate
tf.summary.scalar('learning_rate', lr)
summary_op = tf.compat.v1.summary.merge_all()
init_op = tf.group(
tf.global_variables_initializer(),
tf.local_variables_initializer()
)
restorer, restore_ckpt = restore_model.get_restorer(test=False)
saver = tf.train.Saver(max_to_keep=5)
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model', restore_ckpt)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
summary_path = os.path.join('output/{}'.format(cfgs.DATASET_NAME),
FLAGS.summary_path, cfgs.VERSION)
mkdir(summary_path)
summary_writer = tf.summary.FileWriter(summary_path, graph=sess.graph)
for step in range(cfgs.MAX_ITERATION):
training_time = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
start = time.time()
# gtboxes = tf.cast(
# tf.reshape(fast_rcnn.gtboxes_and_label[:, :-1], [-1, 4]), tf.float32)
# ious = iou.iou_calculate(fast_rcnn.fast_rcnn_all_level_proposals, gtboxes)
# _global_step, _img_name_batch, _rpn_location_loss, _rpn_classification_loss, \
# _rpn_total_loss, _fast_rcnn_location_l, _fast_rcnn_classification_loss, \
# _fast_rcnn_total_loss, _added_loss, _total_loss, rcnn_minibatch, find_samples,\
# gtbox1, iou1, _ = \
# sess.run([global_step, img_name_batch, rpn_location_loss, rpn_classification_loss,
# rpn_total_loss, fast_rcnn_location_l, fast_rcnn_classification_loss,
# fast_rcnn_total_loss, added_loss, total_loss,
# fast_rcnn.fast_rcnn_minibatch(fast_rcnn.fast_rcnn_all_level_proposals),
# fast_rcnn.fast_rcnn_find_positive_negative_samples(fast_rcnn.fast_rcnn_all_level_proposals),
# gtboxes, ious,
# train_op])
_global_step, _img_name_batch, _rpn_location_loss, _rpn_classification_loss, \
_rpn_total_loss, _fast_rcnn_location_l, _fast_rcnn_classification_loss, \
_fast_rcnn_total_loss, _added_loss, _total_loss, \
_ = \
sess.run([global_step, img_name_batch, rpn_location_loss, rpn_classification_loss,
rpn_total_loss, fast_rcnn_location_l, fast_rcnn_classification_loss,
fast_rcnn_total_loss, added_loss, total_loss,
train_op])
# _global_step, _img_name_batch, _added_loss, _total_loss, \
# _ = \
# sess.run([global_step, img_name_batch, added_loss, total_loss,
# train_op])
end = time.time()
# a, b, c ,d = rcnn_minibatch
# aa, bb, cc = find_samples
# q = []
# for i in cc:
# if i not in q:
# q.append(i)
# qq = []
# for i in c:
# if i not in qq:
# qq.append(i)
# minibatch_encode_boxes = tf.gather(fast_rcnn.fast_rcnn_encode_boxes,a)
# minibatch_reference_boxes = tf.gather(fast_rcnn.fast_rcnn_all_level_proposals, a)
# minibatch_encode_gtboxes = \
# encode_and_decode.encode_boxes(
# unencode_boxes=b,
# reference_boxes=minibatch_reference_boxes,
# scale_factors=fast_rcnn.scale_factors
# )
# # [minibatch_size, num_classes*4]
# minibatch_encode_gtboxes = tf.tile(minibatch_encode_gtboxes, [1, fast_rcnn.num_classes])
#
# class_weights_list = []
# category_list = tf.unstack(d, axis=1)
# for i in range(1, fast_rcnn.num_classes + 1):
# tmp_class_weights = tf.ones(
# shape=[tf.shape(minibatch_encode_boxes)[0], 4], dtype=tf.float32)
# tmp_class_weights = tmp_class_weights * tf.expand_dims(category_list[i], axis=1)
# class_weights_list.append(tmp_class_weights)
# class_weights = tf.concat(class_weights_list, axis=1) # [minibatch_size, num_classes*4]
#
# loc_loss1 = losses.l1_smooth_losses(predict_boxes=minibatch_encode_boxes,
# gtboxes=minibatch_encode_gtboxes,
# object_weights=c,
# classes_weights=class_weights)
# print('loction-loss:', sess.run(loc_loss1))
if step % 50 == 0:
print("""{}: step{} image_name:{}
rpn_loc_loss:{:.4f} | rpn_cla_loss:{:.4f} | rpn_total_loss:{:.4f}
fast_rcnn_loc_loss:{:.10f} | fast_rcnn_cla_loss:{:.10f} | fast_rcnn_total_loss:{:.4f}
added_loss:{:.4f} | total_loss:{:.4f} | pre_cost_time:{:.4f}s"""
.format(training_time, _global_step, str(_img_name_batch[0]), _rpn_location_loss,
_rpn_classification_loss, _rpn_total_loss, _fast_rcnn_location_l,
_fast_rcnn_classification_loss, _fast_rcnn_total_loss, _added_loss, _total_loss,
(end - start)))
# if step % 100 == 0:
# print("""{}: step{} image_name:{}
# added_loss:{:.4f} | total_loss:{:.4f} | pre_cost_time:{:.4f}s"""
# .format(training_time, _global_step, str(_img_name_batch[0]), _added_loss, _total_loss, (end - start)
# ))
# print(q, '\n', qq)
# print(gtbox1)
# print(iou1)
if step % 500000 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, _global_step)
summary_writer.flush()
if (step > 0 and step % 10000 == 0) or (step == cfgs.MAX_ITERATION - 1):
save_dir = os.path.join('output/{}'.format(cfgs.DATASET_NAME),
FLAGS.trained_checkpoint, cfgs.VERSION)
mkdir(save_dir)
save_ckpt = os.path.join(save_dir, '{}_'.format(
cfgs.DATASET_NAME)+str(_global_step)+'model.ckpt')
saver.save(sess, save_ckpt)
print('Weights have been saved to {}.'.format(save_ckpt))
print('Training done.')
coord.request_stop()
coord.join(threads)
def test(img_num):
with tf.Graph().as_default():
# img = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8)
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=False)
gtboxes_and_label = tf.py_func(
back_forward_convert,
inp=[tf.squeeze(gtboxes_and_label_batch, 0)],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=gtboxes_and_label,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
anchor_angles=cfgs.ANCHOR_ANGLES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
anchor_stride=cfgs.ANCHOR_STRIDE,
pool_stride=cfgs.POOL_STRIDE,
top_k_nms=cfgs.RPN_TOP_K_NMS,
kernel_size=cfgs.KERNEL_SIZE,
use_angles_condition=True,
anchor_angle_threshold=cfgs.RPN_ANCHOR_ANGLES_THRESHOLD,
nms_angle_threshold=cfgs.RPN_NMS_ANGLES_THRESHOLD,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
scope='')
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
_, _, rpn_top_k_boxes, rpn_top_k_scores = rpn.rpn_losses()
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
stop_gradient_for_proposals=False,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
top_k_nms=cfgs.FAST_RCNN_TOP_K_NMS,
nms_angle_threshold=cfgs.FAST_RCNN_NMS_ANGLES_THRESHOLD,
use_angle_condition=False,
level=cfgs.LEVEL,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
boxes_angle_threshold=cfgs.FAST_RCNN_BOXES_ANGLES_THRESHOLD,
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
##############################################################################################
if cfgs.NEED_AUXILIARY:
predict_boxes = tf.concat(
[fast_rcnn_decode_boxes, rpn_top_k_boxes], axis=0)
predict_scores = tf.concat(
[fast_rcnn_score, rpn_top_k_scores - 0.2], axis=0)
rpn_top_k_label = tf.ones([
tf.shape(rpn_top_k_scores)[0],
], tf.int64)
labels = tf.concat([detection_category, rpn_top_k_label], axis=0)
# valid_indices = nms_rotate.nms_rotate(decode_boxes=predict_boxes,
# scores=predict_scores,
# iou_threshold=0.15,
# max_output_size=30,
# use_angle_condition=False,
# angle_threshold=15,
# use_gpu=True)
valid_indices = tf.py_func(nms_rotate.nms_rotate_cpu,
inp=[
predict_boxes, predict_scores,
tf.constant(0.15, tf.float32),
tf.constant(30, tf.float32)
],
Tout=tf.int64)
fast_rcnn_decode_boxes = tf.gather(predict_boxes, valid_indices)
fast_rcnn_score = tf.gather(predict_scores, valid_indices)
detection_category = tf.gather(labels, valid_indices)
##############################################################################################
# train
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label, _fast_rcnn_decode_boxes, \
_fast_rcnn_score, _detection_category \
= sess.run([img_name_batch, img_batch, gtboxes_and_label, fast_rcnn_decode_boxes,
fast_rcnn_score, detection_category])
end = time.time()
_img_batch = np.squeeze(_img_batch, axis=0)
_img_batch_fpn = help_utils.draw_box_cv(
_img_batch,
boxes=_fast_rcnn_decode_boxes,
labels=_detection_category,
scores=_fast_rcnn_score)
mkdir(cfgs.TEST_SAVE_PATH)
cv2.imwrite(
cfgs.TEST_SAVE_PATH + '/{}_fpn.jpg'.format(
str(_img_name_batch[0]).split('.tif')[0]),
_img_batch_fpn)
# _gtboxes_and_label_batch = np.squeeze(_gtboxes_and_label_batch, axis=0)
temp_label = np.reshape(_gtboxes_and_label[:, -1:], [
-1,
]).astype(np.int64)
_img_batch_gt = help_utils.draw_box_cv(
_img_batch,
boxes=_gtboxes_and_label[:, :-1],
labels=temp_label,
scores=None)
cv2.imwrite(
cfgs.TEST_SAVE_PATH + '/{}_gt.jpg'.format(
str(_img_name_batch[0]).split('.tif')[0]),
_img_batch_gt)
#view_bar('{} image cost {}s'.format(str(_img_name_batch[0]), (end - start)), i+1, img_num)
print('{} image cost {}s'.format(str(_img_name_batch[0]),
(end - start)) + str(i + 1) +
'/' + str(img_num))
coord.request_stop()
coord.join(threads)
def eval_with_plac(num_imgs, eval_dir, img_root, showbox, annotation_dir):
# with open('/home/yjr/DataSet/VOC/VOC_test/VOC2007/ImageSets/Main/aeroplane_test.txt') as f:
# all_lines = f.readlines()
# test_imgname_list = [a_line.split()[0].strip() for a_line in all_lines]
test_imgname_list = [
item for item in os.listdir(eval_dir)
if item.endswith(('.jpg', 'jpeg', '.png', '.tif', '.tiff'))
]
if num_imgs == np.inf:
real_test_imgname_list = test_imgname_list
else:
real_test_imgname_list = test_imgname_list[:num_imgs]
img_plac = tf.placeholder(dtype=tf.float32, shape=[None, None, 3])
img = img_plac - tf.constant([103.939, 116.779, 123.68])
img_batch = short_side_resize_for_inference_data(img, cfgs.SHORT_SIDE_LEN)
h, w = img.shape[0], img.shape[1]
gt_boxes_label = tf.placeholder(dtype=tf.float32, shape=[None, 5])
gt_boxes_label_batch = tf.expand_dims(gt_boxes_label, axis=0)
image_height, image_width = tf.shape(img_batch)[1], tf.shape(img_batch)[2]
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=False,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
feature_pyramid = build_fpn.build_feature_pyramid(share_net)
rpn = build_rpn.RPN(feature_pyramid=feature_pyramid,
image_height=image_height,
image_width=image_width,
gtboxes_and_label=gt_boxes_label_batch,
is_training=False)
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
is_training=False)
fast_rcnn = build_fast_rcnn.FAST_RCNN(
feature_pyramid=feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
gtboxes_and_label=gt_boxes_label_batch,
origin_image=img_batch,
is_training=True,
image_height=image_height,
image_width=image_width)
detections = fast_rcnn.head_detection()
detection_boxes, detection_category,detection_scores = tf.squeeze(detections[:,:,:4],axis=0),\
tf.squeeze(detections[:,:,4],axis=0),\
tf.squeeze(detections[:,:,5],axis=0)
indices = tf.reshape(
tf.where(tf.greater_equal(detection_scores,
cfgs.FINAL_SCORE_THRESHOLD)), [-1])
detection_boxes = tf.gather(detection_boxes, indices)
detection_scores = tf.gather(detection_scores, indices)
detection_category = tf.gather(detection_category, indices)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer(
test=True, checkpoint_path=cfgs.chekpoint_path)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
all_boxes = []
for i, a_img_name in enumerate(real_test_imgname_list):
raw_img = cv2.imread(os.path.join(img_root, a_img_name))
raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
start = time.time()
resized_img, detected_boxes, detected_scores, detected_categories = \
sess.run(
[img, detection_boxes, detection_scores, detection_category],
feed_dict={img_plac: raw_img} # cv is BGR. But need RGB
)
print(a_img_name, detected_boxes, detected_scores,
detected_categories)
end = time.time()
ymin, xmin, ymax, xmax = detected_boxes[:, 0], detected_boxes[:, 1], \
detected_boxes[:, 2], detected_boxes[:, 3]
resized_h, resized_w = resized_img.shape[1], resized_img.shape[2]
xmin = xmin * raw_w / resized_w
xmax = xmax * raw_w / resized_w
ymin = ymin * raw_h / resized_h
ymax = ymax * raw_h / resized_h
boxes = np.transpose(np.stack([xmin, ymin, xmax, ymax]))
dets = np.hstack((detected_categories.reshape(-1, 1),
detected_scores.reshape(-1, 1), boxes))
all_boxes.append(dets)
view_bar('{} image cost {}s'.format(a_img_name, (end - start)),
i + 1, len(real_test_imgname_list))
voc_evaluate_detections(all_boxes=all_boxes,
test_annotation_path=annotation_dir,
test_imgid_list=real_test_imgname_list)
def model_fn(features, labels, mode, params):
# ***********************************************************************************************
# * Backbone Net *
# ***********************************************************************************************
net_config = params["net_config"]
if mode == tf.estimator.ModeKeys.TRAIN:
IS_TRAINING = True
else:
IS_TRAINING = False
origin_image_batch = features["image"]
image_batch = origin_image_batch - tf.convert_to_tensor(
net_config.PIXEL_MEANS, dtype=tf.float32)
image_window = features["image_window"]
# there is is_training means that bn is training, so it is important!
_, share_net = get_network_byname(inputs=image_batch,
config=net_config,
is_training=False,
reuse=tf.AUTO_REUSE)
# ***********************************************************************************************
# * FPN *
# ***********************************************************************************************
feature_pyramid = build_fpn.build_feature_pyramid(share_net, net_config)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
gtboxes_and_label_batch = labels.get("gt_box_labels")
rpn = build_rpn.RPN(feature_pyramid=feature_pyramid,
image_window=image_window,
config=net_config)
# rpn_proposals_scores==(2000,)
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(IS_TRAINING)
rpn_location_loss, rpn_classification_loss = rpn.rpn_losses(
labels["minibatch_indices"], labels["minibatch_encode_gtboxes"],
labels["minibatch_objects_one_hot"])
rpn_total_loss = rpn_classification_loss + rpn_location_loss
# ***********************************************************************************************
# * Fast RCNN Head *
# ***********************************************************************************************
fpn_fast_rcnn_head = build_head.FPNHead(
feature_pyramid=feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
origin_image=origin_image_batch,
gtboxes_and_label=gtboxes_and_label_batch,
config=net_config,
is_training=False,
image_window=image_window)
detections = fpn_fast_rcnn_head.head_detection()
if net_config.DEBUG:
print_tensors(rpn_proposals_scores[0, :50], "scores")
print_tensors(rpn_proposals_boxes[0, :50, :], "bbox")
rpn_proposals_vision = draw_boxes_with_scores(
origin_image_batch[0, :, :, :], rpn_proposals_boxes[0, :50, :],
rpn_proposals_scores[0, :50])
head_vision = draw_boxes_with_categories_and_scores(
origin_image_batch[0, :, :, :], detections[0, :, :4],
detections[0, :, 4], detections[0, :, 5], net_config.LABEL_TO_NAME)
tf.summary.image("rpn_proposals_vision", rpn_proposals_vision)
tf.summary.image("head_vision", head_vision)
head_location_loss, head_classification_loss = fpn_fast_rcnn_head.head_loss(
)
head_total_loss = head_location_loss + head_classification_loss
# train
with tf.name_scope("regularization_losses"):
regularization_list = [
tf.nn.l2_loss(w.read_value()) * net_config.WEIGHT_DECAY /
tf.cast(tf.size(w.read_value()), tf.float32)
for w in tf.trainable_variables()
if 'gamma' not in w.name and 'beta' not in w.name
]
regularization_loss = tf.add_n(regularization_list)
total_loss = regularization_loss + head_total_loss + rpn_total_loss
total_loss = tf.cond(tf.is_nan(total_loss), lambda: 0.0,
lambda: total_loss)
print_tensors(head_total_loss, "head_loss")
print_tensors(rpn_total_loss, "rpn_loss")
global_step = tf.train.get_or_create_global_step()
tf.train.init_from_checkpoint(
net_config.CHECKPOINT_DIR,
{net_config.BACKBONE_NET + "/": net_config.BACKBONE_NET + "/"})
with tf.name_scope("optimizer"):
lr = tf.train.piecewise_constant(
global_step,
boundaries=[np.int64(net_config.BOUNDARY[0])],
values=[net_config.LEARNING_RATE, net_config.LEARNING_RATE / 10])
optimizer = tf.train.MomentumOptimizer(lr,
momentum=net_config.MOMENTUM)
optimizer = tf.contrib.estimator.TowerOptimizer(optimizer)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies([tf.group(*update_ops)]):
grads = optimizer.compute_gradients(total_loss)
# clip gradients
grads = tf.contrib.training.clip_gradient_norms(
grads, net_config.CLIP_GRADIENT_NORM)
train_op = optimizer.apply_gradients(grads, global_step)
# ***********************************************************************************************
# * Summary *
# ***********************************************************************************************
# rpn loss and image
tf.summary.scalar('rpn_location_loss',
rpn_location_loss,
family="rpn_loss")
tf.summary.scalar('rpn_classification_loss',
rpn_classification_loss,
family="rpn_loss")
tf.summary.scalar('rpn_total_loss', rpn_total_loss, family="rpn_loss")
tf.summary.scalar('head_location_loss',
head_location_loss,
family="head_loss")
tf.summary.scalar('head_classification_loss',
head_classification_loss,
family="head_loss")
tf.summary.scalar('head_total_loss', head_total_loss, family="head_loss")
tf.summary.scalar("regularization_loss", regularization_loss)
tf.summary.scalar('total_loss', total_loss)
tf.summary.scalar('learning_rate', lr)
meta_hook = MetadataHook(save_steps=net_config.SAVE_EVERY_N_STEP *
net_config.EPOCH / 2,
output_dir=net_config.MODLE_DIR)
summary_hook = tf.train.SummarySaverHook(
save_steps=net_config.SAVE_EVERY_N_STEP,
output_dir=net_config.MODLE_DIR,
summary_op=tf.summary.merge_all())
hooks = [summary_hook]
if net_config.COMPUTE_TIME:
hooks.append(meta_hook)
if mode == tf.estimator.ModeKeys.TRAIN:
return tf.estimator.EstimatorSpec(mode,
loss=total_loss,
train_op=train_op,
training_hooks=hooks)
# ***********************************************************************************************
# * EVAL *
# ***********************************************************************************************
metric_ap_dict = batch_slice([
features["gt_box_labels"][:, :, :4], features["gt_box_labels"][:, :,
4],
detections[:, :, :4], detections[:, :, 4], detections[:, :, 5]
], lambda x, y, z, u, v: compute_metric_ap(x, y, z, u, v, net_config),
net_config.PER_GPU_IMAGE)
if mode == tf.estimator.ModeKeys.EVAL:
return tf.estimator.EstimatorSpec(mode,
loss=total_loss,
eval_metric_ops=metric_ap_dict)
def eval_ship(img_num):
with tf.Graph().as_default():
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=True)
gtboxes_and_label, head = get_head(
tf.squeeze(gtboxes_and_label_batch, 0))
gtboxes_and_label = tf.py_func(back_forward_convert,
inp=[gtboxes_and_label],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
head_quadrant = tf.py_func(get_head_quadrant,
inp=[head, gtboxes_and_label],
Tout=tf.float32)
head_quadrant = tf.reshape(head_quadrant, [-1, 1])
gtboxes_and_label_minAreaRectangle = get_horizen_minAreaRectangle(
gtboxes_and_label)
gtboxes_and_label_minAreaRectangle = tf.reshape(
gtboxes_and_label_minAreaRectangle, [-1, 5])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
img_batch=img_batch,
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
gtboxes_and_label_minAreaRectangle=
gtboxes_and_label_minAreaRectangle,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
# iou>0.5 is positive, iou<0.5 is negative
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL,
head_quadrant=head_quadrant)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category, \
fast_rcnn_decode_boxes_rotate, fast_rcnn_score_rotate, fast_rcnn_head_quadrant, \
num_of_objects_rotate, detection_category_rotate = fast_rcnn.fast_rcnn_predict()
# train
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
gtboxes_horizontal_dict = {}
gtboxes_rotate_dict = {}
all_boxes_h = []
all_boxes_r = []
all_img_names = []
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label, _gtboxes_and_label_minAreaRectangle, \
_fast_rcnn_decode_boxes, _fast_rcnn_score, _detection_category, _fast_rcnn_decode_boxes_rotate, \
_fast_rcnn_score_rotate, _detection_category_rotate \
= sess.run([img_name_batch, img_batch, gtboxes_and_label, gtboxes_and_label_minAreaRectangle,
fast_rcnn_decode_boxes, fast_rcnn_score, detection_category, fast_rcnn_decode_boxes_rotate,
fast_rcnn_score_rotate, detection_category_rotate])
end = time.time()
# gtboxes convert dict
gtboxes_horizontal_dict[str(_img_name_batch[0])] = []
gtboxes_rotate_dict[str(_img_name_batch[0])] = []
gtbox_horizontal_list, gtbox_rotate_list = make_dict_packle(
_gtboxes_and_label, _gtboxes_and_label_minAreaRectangle)
xmin, ymin, xmax, ymax = _fast_rcnn_decode_boxes[:,
1], _fast_rcnn_decode_boxes[:,
0], _fast_rcnn_decode_boxes[:,
3], _fast_rcnn_decode_boxes[:,
2]
x_c, y_c, w, h, theta = _fast_rcnn_decode_boxes_rotate[:, 1], _fast_rcnn_decode_boxes_rotate[:, 0], _fast_rcnn_decode_boxes_rotate[:, 3], \
_fast_rcnn_decode_boxes_rotate[:, 2], _fast_rcnn_decode_boxes_rotate[:, 4]
boxes_h = np.transpose(np.stack([xmin, ymin, xmax, ymax]))
boxes_r = np.transpose(np.stack([x_c, y_c, w, h, theta]))
dets_h = np.hstack((_detection_category.reshape(-1, 1),
_fast_rcnn_score.reshape(-1, 1), boxes_h))
dets_r = np.hstack(
(_detection_category_rotate.reshape(-1, 1),
_fast_rcnn_score_rotate.reshape(-1, 1), boxes_r))
all_boxes_h.append(dets_h)
all_boxes_r.append(dets_r)
all_img_names.append(str(_img_name_batch[0]))
gtboxes_horizontal_dict[str(
_img_name_batch[0])].extend(gtbox_horizontal_list)
gtboxes_rotate_dict[str(
_img_name_batch[0])].extend(gtbox_rotate_list)
print(str(_img_name_batch[0]))
view_bar(
'{} image cost {}s'.format(str(_img_name_batch[0]),
(end - start)), i + 1, img_num)
write_voc_results_file(all_boxes_h, all_img_names,
cfgs.EVALUATE_R_DIR, 0)
write_voc_results_file(all_boxes_r, all_img_names,
cfgs.EVALUATE_R_DIR, 1)
fw1 = open('gtboxes_horizontal_dict.pkl', 'wb')
fw2 = open('gtboxes_rotate_dict.pkl', 'wb')
pickle.dump(gtboxes_horizontal_dict, fw1)
pickle.dump(gtboxes_rotate_dict, fw2)
fw1.close()
fw2.close()
coord.request_stop()
coord.join(threads)
def detect_img(file_paths,
des_folder,
paramPath,
bakpath,
det_th,
h_len,
w_len,
h_overlap,
w_overlap,
file_ext,
show_res=False):
with tf.Graph().as_default():
img_plac = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8)
img_tensor = tf.cast(img_plac, tf.float32) - tf.constant(
[103.939, 116.779, 123.68])
img_batch = image_preprocess.short_side_resize_for_inference_data(
img_tensor,
target_shortside_len=cfgs.SHORT_SIDE_LEN,
is_resize=False)
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
gtboxes_and_label_minAreaRectangle=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=det_th,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
# iou>0.5 is positive, iou<0.5 is negative
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL,
head_quadrant=None)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category, \
fast_rcnn_decode_boxes_rotate, fast_rcnn_score_rotate, fast_rcnn_head_quadrant, \
num_of_objects_rotate, detection_category_rotate = fast_rcnn.fast_rcnn_predict()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
obstacle_points, obstacle_labels = read_vif('./sp_whole_reg.vif')
while True:
alldemo = os.listdir(file_paths)
file_names = []
for singledemo in alldemo:
singlepath = os.path.join(file_paths, singledemo)
file_names.append(singlepath)
for img_path in file_names:
if img_path.endswith(('.jpg')): # and f not in fs_found:
l_f = img_path + '.lock'
if os.path.exists(l_f):
time.sleep(0.01)
continue
# try:
start = timer()
img = cv2.imread(img_path)
box_res = []
label_res = []
score_res = []
box_res_rotate = []
label_res_rotate = []
score_res_rotate = []
head_rotate = []
imgH = img.shape[0]
imgW = img.shape[1]
for hh in range(0, imgH, h_len - h_overlap):
h_size = min(h_len, imgH - hh)
if h_size < 10:
break
for ww in range(0, imgW, w_len - w_overlap):
w_size = min(w_len, imgW - ww)
if w_size < 10:
break
src_img = img[hh:(hh + h_size),
ww:(ww + w_size), :]
# boxes, labels, scores = sess.run([fast_rcnn_decode_boxes, detection_category, fast_rcnn_score],
# feed_dict={img_plac: src_img})
boxes_rotate, labels_rotate, scores_rotate, _fast_rcnn_head_quadrant = \
sess.run([fast_rcnn_decode_boxes_rotate, detection_category_rotate,
fast_rcnn_score_rotate,
fast_rcnn_head_quadrant],
feed_dict={img_plac: src_img})
# if len(boxes) > 0:
# for ii in range(len(boxes)):
# box = boxes[ii]
# box[0] = box[0] + hh
# box[1] = box[1] + ww
# box[2] = box[2] + hh
# box[3] = box[3] + ww
# box_res.append(box)
# label_res.append(labels[ii])
# score_res.append(scores[ii])
if len(boxes_rotate) > 0:
for ii in range(len(boxes_rotate)):
box_rotate = boxes_rotate[ii]
box_rotate[0] = box_rotate[0] + hh
box_rotate[1] = box_rotate[1] + ww
box_res_rotate.append(box_rotate)
label_res_rotate.append(labels_rotate[ii])
score_res_rotate.append(scores_rotate[ii])
head_rotate.append(
_fast_rcnn_head_quadrant[ii])
time_elapsed = timer() - start
print("{} detection time : {:.4f} sec".format(
img_path.split('/')[-1].split('.')[0], time_elapsed))
mkdir(des_folder)
if len(head_rotate) != 0:
# img_np = draw_box_cv(np.array(img, np.float32) - np.array([103.939, 116.779, 123.68]),
# boxes=np.array(box_res),
# labels=np.array(label_res),
# scores=np.array(score_res))
img_np_rotate = draw_rotate_box_cv(
np.array(img, np.float32) -
np.array([103.939, 116.779, 123.68]),
boxes=np.array(box_res_rotate),
labels=np.array(label_res_rotate),
scores=np.array(score_res_rotate),
head=np.argmax(head_rotate, axis=1))
geo_points = get_points(box_res_rotate,
np.argmax(head_rotate, axis=1))
image_name = img_path.split('/')[-1]
xml_path_1 = os.path.join(des_folder,
'1_' + image_name).replace(
file_ext, ".xml")
param_path = os.path.join(paramPath,
'UAV_' + image_name).replace(
file_ext, ".param")
x_tr, y_tr = get_param(param_path)
obstacle_left, obstacle_labels = filter_obstacle(
obstacle_points, imgH, imgW, x_tr, y_tr)
######################################################
# obstacle_left = []
# temp = np.array([[2233, 1013], [2196, 980], [2215, 959], [2252, 993]])
# for coord in temp:
# coord_convet = convert_coordinate(coord, imgH, imgW, x_tr, y_tr)
# obstacle_left.extend(coord_convet)
# geo_points, obstacle_labels = filter_obstacle(np.array(geo_points)[:, :8], imgH, imgW, x_tr, y_tr)
######################################################
detect_res, label_res = get_detect_res(
obstacle_left, obstacle_labels, geo_points,
label_res_rotate, imgH, imgW, x_tr, y_tr)
# writer_XML(xml_name, geo_points, label_res, imgW, imgH)
writer_XML2(xml_path_1, detect_res, label_res)
shutil.move(img_path,
os.path.join(bakpath, image_name))
# cv2.imwrite(des_folder + '/{}_horizontal_fpn.jpg'.format(img_path.split('/')[-1].split('.')[0]), img_np)
cv2.imwrite(
des_folder + '/{}_rotate_fpn.jpg'.format(
img_path.split('/')[-1].split('.')[0]),
img_np_rotate)
final_points = []
final_labels = []
for type in range(3):
indx = np.where(np.equal(label_res_rotate,
type))[0]
if len(indx) != 0:
box_res_rotate_ = np.array(
box_res_rotate)[indx]
label_res_rotate_ = np.array(
label_res_rotate)[indx]
head_rotate_ = np.array(
np.argmax(head_rotate, axis=1))[indx]
angles_ = get_angles(box_res_rotate_[:, 4],
head_rotate_)
convex_points_, center_point_, angle_ = get_convex_points(
box_res_rotate_[:, :2], angles_)
head_ = get_head(center_point_, angle_)
all_points = []
for ii in box_res_rotate_:
all_points.extend(
convert_coordinate(
ii, imgH, imgW, x_tr, y_tr))
all_points.extend(
convert_coordinate(center_point_, imgH,
imgW, x_tr, y_tr))
all_points.extend(
convert_coordinate(head_, imgH, imgW, x_tr,
y_tr))
final_points.append(all_points)
final_labels.append(type)
xml_path_2 = os.path.join(des_folder,
'2_' + image_name).replace(
file_ext, ".xml")
writer_XML2(xml_path_2, final_points, final_labels)
# except:
# print("Get an error, filename: {}".format(img_path))
coord.request_stop()
coord.join(threads)
def test(img_num):
with tf.Graph().as_default():
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=False)
gtboxes_and_label = tf.py_func(
back_forward_convert,
inp=[tf.squeeze(gtboxes_and_label_batch, 0)],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
gtboxes_and_label_minAreaRectangle = get_horizen_minAreaRectangle(
gtboxes_and_label)
gtboxes_and_label_minAreaRectangle = tf.reshape(
gtboxes_and_label_minAreaRectangle, [-1, 5])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn1.FastRCNN(
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
gtboxes_and_label_minAreaRectangle=
gtboxes_and_label_minAreaRectangle,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
# iou>0.5 is positive, iou<0.5 is negative
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category, \
fast_rcnn_decode_boxes_rotate, fast_rcnn_score_rotate, num_of_objects_rotate, detection_category_rotate,_, _, _, _ = \
fast_rcnn.fast_rcnn_predict()
# train
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
TrueDetection = 0
FalseAlarm = 0
TotalObjects = 0
TotalDetections = 0
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label, _gtboxes_and_label_minAreaRectangle, \
_fast_rcnn_decode_boxes, _fast_rcnn_score, _detection_category, _fast_rcnn_decode_boxes_rotate, \
_fast_rcnn_score_rotate, _detection_category_rotate \
= sess.run([img_name_batch, img_batch, gtboxes_and_label, gtboxes_and_label_minAreaRectangle,
fast_rcnn_decode_boxes, fast_rcnn_score, detection_category, fast_rcnn_decode_boxes_rotate,
fast_rcnn_score_rotate, detection_category_rotate])
end = time.time()
_img_batch = np.squeeze(_img_batch, axis=0)
_img_batch_fpn_horizonal = help_utils.draw_box_cv(
_img_batch,
boxes=_fast_rcnn_decode_boxes,
labels=_detection_category,
scores=_fast_rcnn_score)
_img_batch_fpn_rotate = help_utils.draw_rotate_box_cv(
_img_batch,
boxes=_fast_rcnn_decode_boxes_rotate,
labels=_detection_category_rotate,
scores=_fast_rcnn_score_rotate)
mkdir(cfgs.TEST_SAVE_PATH)
cv2.imwrite(
cfgs.TEST_SAVE_PATH + str(_img_name_batch[0]) +
'_horizontal_fpn.jpg', _img_batch_fpn_horizonal)
cv2.imwrite(
cfgs.TEST_SAVE_PATH + str(_img_name_batch[0]) +
'_rotate_fpn.jpg', _img_batch_fpn_rotate)
temp_label_horizontal = np.reshape(_gtboxes_and_label[:, -1:],
[
-1,
]).astype(np.int64)
temp_label_rotate = np.reshape(_gtboxes_and_label[:, -1:], [
-1,
]).astype(np.int64)
_img_batch_gt_horizontal = help_utils.draw_box_cv(
_img_batch,
boxes=_gtboxes_and_label_minAreaRectangle[:, :-1],
labels=temp_label_horizontal,
scores=None)
_img_batch_gt_rotate = help_utils.draw_rotate_box_cv(
_img_batch,
boxes=_gtboxes_and_label[:, :-1],
labels=temp_label_rotate,
scores=None)
cv2.imwrite(
cfgs.TEST_SAVE_PATH + str(_img_name_batch[0]) +
'_horizontal_gt.jpg', _img_batch_gt_horizontal)
cv2.imwrite(
cfgs.TEST_SAVE_PATH + str(_img_name_batch[0]) +
'_rotate_gt.jpg', _img_batch_gt_rotate)
Current_TrueDetection = 0
lock_list = []
for m in range(len(_gtboxes_and_label)):
for n, box in enumerate(_fast_rcnn_decode_boxes_rotate):
if n in lock_list:
continue
y_c, x_c, h, w, theta = box[0], box[1], box[2], box[
3], box[4]
r1 = ((x_c, y_c), (w, h), theta)
gt_box = _gtboxes_and_label[m]
gt_yc, gt_xc, gt_h, gt_w, gt_theta = gt_box[0], gt_box[
1], gt_box[2], gt_box[3], gt_box[4]
r2 = ((gt_xc, gt_yc), (gt_w, gt_h), gt_theta)
int_pts = cv2.rotatedRectangleIntersection(r1, r2)[0]
if int_pts > 0.5:
Current_TrueDetection += 1
lock_list.append(n)
TrueDetection += Current_TrueDetection
if (len(_fast_rcnn_decode_boxes_rotate) > 0):
FalseAlarm += len(
_fast_rcnn_score_rotate) - Current_TrueDetection
TotalDetections += len(_fast_rcnn_score_rotate)
TotalObjects += len(_gtboxes_and_label)
view_bar(
'{} image cost {}s'.format(str(_img_name_batch[0]),
(end - start)), i + 1, img_num)
Pd = float(TrueDetection) / float(TotalDetections)
Pf = float(FalseAlarm) / float(TotalDetections)
F1 = 2 * float(Pd * (1 - Pf)) / float(Pd + (1 - Pf))
Op = float(TrueDetection) / float(TotalObjects)
print("\nACC: " + str(Pd))
print("FalseAlarm: " + str(Pf))
print("F1: " + str(F1))
print("Op: " + str(TrueDetection) + "/" + str(TotalObjects) +
"=" + str(Op))
coord.request_stop()
coord.join(threads)
def test(img_num):
with tf.Graph().as_default():
# img = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8)
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=False)
gtboxes_and_label = tf.py_func(back_forward_convert,
inp=[tf.squeeze(gtboxes_and_label_batch, 0)],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=gtboxes_and_label,
is_training=False,
share_head=False,
share_net=share_net,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
anchor_angles=cfgs.ANCHOR_ANGLES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
anchor_stride=cfgs.ANCHOR_STRIDE,
top_k_nms=cfgs.RPN_TOP_K_NMS,
kernel_size=cfgs.KERNEL_SIZE,
use_angles_condition=True,
anchor_angle_threshold=cfgs.RPN_ANCHOR_ANGLES_THRESHOLD,
nms_angle_threshold=cfgs.RPN_NMS_ANGLES_THRESHOLD,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
scope='')
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals() # rpn_score shape: [300, ]
# _, _, rpn_top_k_boxes, rpn_top_k_scores = rpn.rpn_losses()
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
stop_gradient_for_proposals=False,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
top_k_nms=cfgs.FAST_RCNN_TOP_K_NMS,
nms_angle_threshold=cfgs.FAST_RCNN_NMS_ANGLES_THRESHOLD,
use_angle_condition=False,
level=cfgs.LEVEL,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.FAST_RCNN_IOU_POSITIVE_THRESHOLD,
boxes_angle_threshold=cfgs.FAST_RCNN_BOXES_ANGLES_THRESHOLD,
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
# test
init_op = tf.group(
tf.global_variables_initializer(),
tf.local_variables_initializer()
)
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label, _fast_rcnn_decode_boxes, \
_fast_rcnn_score, _detection_category \
= sess.run([img_name_batch, img_batch, gtboxes_and_label, fast_rcnn_decode_boxes,
fast_rcnn_score, detection_category])
end = time.time()
_img_batch = np.squeeze(_img_batch, axis=0)
_img_batch_fpn = help_utils.draw_box_cv(_img_batch,
boxes=_fast_rcnn_decode_boxes,
labels=_detection_category,
scores=_fast_rcnn_score)
cv2.imwrite(cfgs.TEST_SAVE_PATH + '/{}_fpn.jpg'.format(str(_img_name_batch[0]).split('.tif')[0]),
_img_batch_fpn)
temp_label = np.reshape(_gtboxes_and_label[:, -1:], [-1, ]).astype(np.int64)
_img_batch_gt = help_utils.draw_box_cv(_img_batch,
boxes=_gtboxes_and_label[:, :-1],
labels=temp_label,
scores=None)
cv2.imwrite(cfgs.TEST_SAVE_PATH + '/{}_gt.jpg'.format(str(_img_name_batch[0]).split('.tif')[0]),
_img_batch_gt)
view_bar('{} image cost {}s'.format(str(_img_name_batch[0]), (end - start)), i+1, img_num)
coord.request_stop()
coord.join(threads)
def model_fn(features, labels, mode, params, config):
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
net_config = params["net_config"]
if mode == tf.estimator.ModeKeys.TRAIN:
IS_TRAINING = True
else:
IS_TRAINING = False
origin_image_batch = features["image"]
image_window = features["image_window"]
image_batch = origin_image_batch - net_config.PIXEL_MEANS
# there is is_training means that bn is training, so it is important!
_, share_net = get_network_byname(inputs=image_batch,
config=net_config,
is_training=False,
reuse=tf.AUTO_REUSE)
# ***********************************************************************************************
# * fpn *
# ***********************************************************************************************
feature_pyramid = build_fpn.build_feature_pyramid(share_net, net_config)
# ***********************************************************************************************
# * rpn *
# ***********************************************************************************************
gtboxes_and_label_batch = labels.get("gt_box_labels")
rpn = build_rpn.RPN(feature_pyramid=feature_pyramid,
image_window=image_window,
config=net_config)
# rpn_proposals_scores==(2000,)
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(IS_TRAINING)
rpn_location_loss, rpn_classification_loss = rpn.rpn_losses(
labels["minibatch_indices"], labels["minibatch_encode_gtboxes"],
labels["minibatch_objects_one_hot"])
rpn_total_loss = rpn_classification_loss + rpn_location_loss
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
feature_pyramid=feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
origin_image=origin_image_batch,
gtboxes_and_label=gtboxes_and_label_batch,
config=net_config,
is_training=False,
image_window=image_window)
detections = fast_rcnn.fast_rcnn_detection()
if DEBUG:
rpn_proposals_vision = draw_boxes_with_scores(
origin_image_batch[0, :, :, :], rpn_proposals_boxes[0, :50, :],
rpn_proposals_scores[0, :50])
fast_rcnn_vision = draw_boxes_with_categories_and_scores(
origin_image_batch[0, :, :, :], detections[0, :, :4],
detections[0, :, 4], detections[0, :, 5])
tf.summary.image("rpn_proposals_vision", rpn_proposals_vision)
tf.summary.image("fast_rcnn_vision", fast_rcnn_vision)
fast_rcnn_location_loss, fast_rcnn_classification_loss = fast_rcnn.fast_rcnn_loss(
)
fast_rcnn_total_loss = fast_rcnn_location_loss + fast_rcnn_classification_loss
# train
with tf.variable_scope("regularization_losses"):
regularization_list = [
tf.nn.l2_loss(w.read_value()) * net_config.WEIGHT_DECAY /
tf.cast(tf.size(w.read_value()), tf.float32)
for w in tf.trainable_variables()
if 'gamma' not in w.name and 'beta' not in w.name
]
regularization_losses = tf.add_n(regularization_list)
total_loss = regularization_losses + fast_rcnn_total_loss + rpn_total_loss
global_step = slim.get_or_create_global_step()
tf.train.init_from_checkpoint(
net_config.CHECKPOINT_DIR,
{net_config.NET_NAME + "/": net_config.NET_NAME + "/"})
with tf.variable_scope("optimizer"):
lr = tf.train.piecewise_constant(global_step,
boundaries=[
np.int64(net_config.BOUNDARY[0]),
np.int64(net_config.BOUNDARY[1])
],
values=[
net_config.LEARNING_RATE,
net_config.LEARNING_RATE / 10,
net_config.LEARNING_RATE / 100
])
optimizer = tf.train.MomentumOptimizer(lr,
momentum=net_config.MOMENTUM)
optimizer = tf.contrib.estimator.TowerOptimizer(optimizer)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies([tf.group(*update_ops)]):
grads = optimizer.compute_gradients(total_loss)
# clip gradients
grads = tf.contrib.training.clip_gradient_norms(
grads, net_config.CLIP_GRADIENT_NORM)
train_op = optimizer.apply_gradients(grads, global_step)
# ***********************************************************************************************
# * Summary *
# ***********************************************************************************************
# rpn loss and image
tf.summary.scalar('rpn/rpn_location_loss', rpn_location_loss)
tf.summary.scalar('rpn/rpn_classification_loss', rpn_classification_loss)
tf.summary.scalar('rpn/rpn_total_loss', rpn_total_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_location_loss',
fast_rcnn_location_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_classification_loss',
fast_rcnn_classification_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_total_loss', fast_rcnn_total_loss)
tf.summary.scalar('learning_rate', lr)
tf.summary.scalar('total_loss', total_loss)
summary_hook = tf.train.SummarySaverHook(
save_steps=net_config.SAVE_EVERY_N_STEP,
output_dir=net_config.MODLE_DIR,
summary_op=tf.summary.merge_all())
if mode == tf.estimator.ModeKeys.TRAIN:
return tf.estimator.EstimatorSpec(mode,
loss=total_loss,
train_op=train_op,
training_hooks=[summary_hook])
def detect_img(file_paths, des_folder, det_th, h_len, w_len, show_res=False):
with tf.Graph().as_default():
img_plac = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8)
img_tensor = tf.cast(img_plac, tf.float32) - tf.constant(
[103.939, 116.779, 123.68])
img_batch = image_preprocess.short_side_resize_for_inference_data(
img_tensor,
target_shortside_len=cfgs.SHORT_SIDE_LEN,
is_resize=False)
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
gtboxes_and_label_minAreaRectangle=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=det_th,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
# iou>0.5 is positive, iou<0.5 is negative
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
for img_path in file_paths:
start = timer()
# gdal.AllRegister()
# ds = gdal.Open(img_path, gdalconst.GA_ReadOnly)
# if ds is None:
# print("Image %s open failed!" % img_path)
# sys.exit()
img = cv2.imread(img_path)
box_res = []
label_res = []
score_res = []
# imgH = ds.RasterYSize
# imgW = ds.RasterXSize
imgH = img.shape[0]
imgW = img.shape[1]
for hh in range(0, imgH, h_len):
h_size = min(h_len, imgH - hh)
if h_size < 10:
break
for ww in range(0, imgW, w_len):
w_size = min(w_len, imgW - ww)
if w_size < 10:
break
# src_img = ds.ReadAsArray(ww, hh, w_size, h_size)
src_img = img[hh:(hh + h_size), ww:(ww + w_size), :]
# if len(src_img.shape) == 2:
# src_img = cv2.cvtColor(src_img, cv2.COLOR_GRAY2RGB)
# else:
# src_img = chw2hwc(src_img)
boxes, labels, scores = sess.run(
[
fast_rcnn_decode_boxes, detection_category,
fast_rcnn_score
],
feed_dict={img_plac: src_img})
if show_res:
visualize_detection(src_img, boxes, scores)
if len(boxes) > 0:
for ii in range(len(boxes)):
box = boxes[ii]
box[0] = box[0] + hh
box[1] = box[1] + ww
box[2] = box[2] + hh
box[3] = box[3] + ww
box_res.append(box)
label_res.append(labels[ii])
score_res.append(scores[ii])
# ds = None
time_elapsed = timer() - start
print("{} detection time : {:.4f} sec".format(
img_path.split('/')[-1].split('.')[0], time_elapsed))
# if target_name == 'aircraft':
# img = cv2.imread(img_path)
# if len(img.shape) == 2:
# img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
# elif len(img.shape) == 3:
# img_gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
# img[:, :, 0] = img[:, :, 1] = img[:, :, 2] = img_gray
mkdir(des_folder)
img_np = draw_box_cv(img,
boxes=np.array(box_res),
labels=np.array(label_res),
scores=np.array(score_res)) - np.array(
[103.939, 116.779, 123.68])
cv2.imwrite(
des_folder + '/{}_fpn.jpg'.format(
img_path.split('/')[-1].split('.')[0]), img_np)
# clip_obj_imgs(src_img, box_res, label_res, score_res, des_folder)
# print(img_path)
# det_xml_path =img_path.replace(".tif", ".det.xml")
# obj_to_det_xml(img_path, box_res, label_res, score_res, det_xml_path)
coord.request_stop()
coord.join(threads)
def train():
with tf.Graph().as_default():
with tf.name_scope('get_batch'):
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME, # 'ship', 'spacenet', 'pascal', 'coco'
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=True)
gtboxes_and_label = tf.py_func(back_forward_convert,
inp=[tf.squeeze(gtboxes_and_label_batch, 0)],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
with tf.name_scope('draw_gtboxes'):
gtboxes_in_img = draw_box_with_color(img_batch, tf.reshape(gtboxes_and_label, [-1, 6])[:, :-1],
text=tf.shape(gtboxes_and_label_batch)[1])
# ***********************************************************************************************
# * shared CNN *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * rpn *
# * Note: here the rpn is Feature Pyramid Networks *
# ***********************************************************************************************
rpn = build_rpn.RPN(net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=gtboxes_and_label,
is_training=True,
share_head=cfgs.SHARED_HEADS,
share_net=share_net,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
anchor_angles=cfgs.ANCHOR_ANGLES,
scale_factors=cfgs.SCALE_FACTORS, # this parameter will affect the performance
base_anchor_size_list=cfgs.BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
anchor_stride=cfgs.ANCHOR_STRIDE,
top_k_nms=cfgs.RPN_TOP_K_NMS,
kernel_size=cfgs.KERNEL_SIZE,
use_angles_condition=False,
anchor_angle_threshold=cfgs.RPN_ANCHOR_ANGLES_THRESHOLD,
nms_angle_threshold=cfgs.RPN_NMS_ANGLES_THRESHOLD,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
# iou>=0.7 is positive box, iou< 0.3 is negative
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=cfgs.IS_FILTER_OUTSIDE_BOXES, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
scope='')
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals() # rpn_score shape: [300, ]
rpn_location_loss, rpn_classification_loss, rpn_predict_boxes, rpn_predict_scores = rpn.rpn_losses()
rpn_total_loss = rpn_classification_loss + rpn_location_loss
with tf.name_scope('draw_proposals'):
# score > 0.6 is object
rpn_object_boxes_indices = tf.reshape(tf.where(tf.greater(rpn_proposals_scores, cfgs.FINAL_SCORE_THRESHOLD)),
[-1])
rpn_object_boxes = tf.gather(rpn_proposals_boxes, rpn_object_boxes_indices)
rpn_object_soxres = tf.gather(rpn_proposals_scores, rpn_object_boxes_indices)
rpn_proposals_objcet_boxes_in_img = draw_boxes_with_scores(img_batch,
rpn_object_boxes,
scores=rpn_object_soxres)
# rpn_proposals_objcet_boxes_in_img = draw_box_with_color(img_batch, rpn_object_boxes,
# text=tf.shape(rpn_object_boxes)[0])
rpn_proposals_boxes_in_img = draw_box_with_color(img_batch, rpn_proposals_boxes,
text=tf.shape(rpn_proposals_boxes)[0])
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
stop_gradient_for_proposals=False,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=gtboxes_and_label,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
top_k_nms=cfgs.FAST_RCNN_TOP_K_NMS,
nms_angle_threshold=cfgs.FAST_RCNN_NMS_ANGLES_THRESHOLD,
use_angle_condition=False,
level=cfgs.LEVEL,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD, # show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.FAST_RCNN_IOU_POSITIVE_THRESHOLD,
# iou>0.5 is positive, iou<0.5 is negative
boxes_angle_threshold=cfgs.FAST_RCNN_BOXES_ANGLES_THRESHOLD,
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=True)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
fast_rcnn_location_loss, fast_rcnn_classification_loss = fast_rcnn.fast_rcnn_loss()
fast_rcnn_total_loss = fast_rcnn_location_loss + fast_rcnn_classification_loss
with tf.name_scope('draw_boxes_with_categories'):
fast_rcnn_predict_boxes_in_imgs = draw_boxes_with_categories(img_batch=img_batch,
boxes=fast_rcnn_decode_boxes,
labels=detection_category,
scores=fast_rcnn_score)
# train
total_loss = slim.losses.get_total_loss()
global_step = slim.get_or_create_global_step()
lr = tf.train.piecewise_constant(global_step,
boundaries=[np.int64(70000), np.int64(120000)],
values=[cfgs.LR, cfgs.LR/10, cfgs.LR/100])
# optimizer = tf.train.MomentumOptimizer(lr, momentum=cfgs.MOMENTUM)
optimizer = tf.train.MomentumOptimizer(lr, momentum=cfgs.MOMENTUM)
if cfgs.RPN_TRAIN:
train_op = slim.learning.create_train_op(rpn_total_loss, optimizer, global_step)
else:
train_op = slim.learning.create_train_op(total_loss, optimizer, global_step)
# train_op = optimizer.minimize(second_classification_loss, global_step)
# ***********************************************************************************************
# * Summary *
# ***********************************************************************************************
# ground truth and predict
tf.summary.image('img/gtboxes', gtboxes_in_img)
tf.summary.image('img/fast_rcnn_predict', fast_rcnn_predict_boxes_in_imgs)
# rpn loss and image
tf.summary.scalar('rpn/rpn_location_loss', rpn_location_loss)
tf.summary.scalar('rpn/rpn_classification_loss', rpn_classification_loss)
tf.summary.scalar('rpn/rpn_total_loss', rpn_total_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_location_loss', fast_rcnn_location_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_classification_loss', fast_rcnn_classification_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_total_loss', fast_rcnn_total_loss)
tf.summary.scalar('loss/total_loss', total_loss)
tf.summary.image('rpn/rpn_all_boxes', rpn_proposals_boxes_in_img)
tf.summary.image('rpn/rpn_object_boxes', rpn_proposals_objcet_boxes_in_img)
# learning_rate
tf.summary.scalar('learning_rate', lr)
summary_op = tf.summary.merge_all()
init_op = tf.group(
tf.global_variables_initializer(),
tf.local_variables_initializer()
)
restorer, restore_ckpt = restore_model.get_restorer()
saver = tf.train.Saver(max_to_keep=10)
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
summary_path = os.path.join(cfgs.SUMMARY_PATH, cfgs.VERSION)
tools.mkdir(summary_path)
summary_writer = tf.summary.FileWriter(summary_path, graph=sess.graph)
for step in range(cfgs.MAX_ITERATION):
training_time = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
start = time.time()
_global_step, _img_name_batch, _rpn_location_loss, _rpn_classification_loss, \
_rpn_total_loss, _fast_rcnn_location_loss, _fast_rcnn_classification_loss, \
_fast_rcnn_total_loss, _total_loss, _= \
sess.run([global_step, img_name_batch, rpn_location_loss, rpn_classification_loss,
rpn_total_loss, fast_rcnn_location_loss, fast_rcnn_classification_loss,
fast_rcnn_total_loss, total_loss, train_op])
end = time.time()
if step % 10 == 0:
print(""" {}: step{} image_name:{} |\t
rpn_loc_loss:{} |\t rpn_cla_loss:{} |\t rpn_total_loss:{} |
fast_rcnn_loc_loss:{} |\t fast_rcnn_cla_loss:{} |\t fast_rcnn_total_loss:{} |
total_loss:{} |\t per_cost_time:{}s""" \
.format(training_time, _global_step, str(_img_name_batch[0]), _rpn_location_loss,
_rpn_classification_loss, _rpn_total_loss, _fast_rcnn_location_loss,
_fast_rcnn_classification_loss, _fast_rcnn_total_loss, _total_loss,
(end - start)))
if (step % 50 == 0) and (step % 10000 != 0): # 50
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, _global_step)
summary_writer.flush()
if (step > 0 and step % 10000 == 0) or (step == cfgs.MAX_ITERATION - 1):
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, _global_step)
summary_writer.flush()
save_dir = os.path.join(cfgs.TRAINED_CKPT, cfgs.VERSION)
if not os.path.exists(save_dir):
os.mkdir(save_dir)
save_ckpt = os.path.join(save_dir, 'voc_'+str(_global_step)+'model.ckpt')
saver.save(sess, save_ckpt)
print(' weights had been saved')
coord.request_stop()
coord.join(threads)
def eval_ship(img_num, mode):
with tf.Graph().as_default():
img_name_batch, img_batch, gtboxes_and_label_batch, num_objects_batch = \
next_batch(dataset_name=cfgs.DATASET_NAME,
batch_size=cfgs.BATCH_SIZE,
shortside_len=cfgs.SHORT_SIDE_LEN,
is_training=False)
gtboxes_and_label = tf.py_func(
back_forward_convert,
inp=[tf.squeeze(gtboxes_and_label_batch, 0)],
Tout=tf.float32)
gtboxes_and_label = tf.reshape(gtboxes_and_label, [-1, 6])
gtboxes_and_label_minAreaRectangle = get_horizen_minAreaRectangle(
gtboxes_and_label)
gtboxes_and_label_minAreaRectangle = tf.reshape(
gtboxes_and_label_minAreaRectangle, [-1, 5])
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=False,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn1.FastRCNN(
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
gtboxes_and_label=None,
gtboxes_and_label_minAreaRectangle=
gtboxes_and_label_minAreaRectangle,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
# iou>0.5 is positive, iou<0.5 is negative
use_dropout=cfgs.USE_DROPOUT,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category, \
fast_rcnn_decode_boxes_rotate, fast_rcnn_score_rotate, num_of_objects_rotate, detection_category_rotate = \
fast_rcnn.fast_rcnn_predict()
if mode == 0:
fast_rcnn_decode_boxes_rotate = get_horizen_minAreaRectangle(
fast_rcnn_decode_boxes_rotate, False)
# train
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
with tf.Session() as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
gtboxes_horizontal_dict = {}
predict_horizontal_dict = {}
gtboxes_rotate_dict = {}
predict_rotate_dict = {}
for i in range(img_num):
start = time.time()
_img_name_batch, _img_batch, _gtboxes_and_label, _gtboxes_and_label_minAreaRectangle, \
_fast_rcnn_decode_boxes, _fast_rcnn_score, _detection_category, _fast_rcnn_decode_boxes_rotate, \
_fast_rcnn_score_rotate, _detection_category_rotate \
= sess.run([img_name_batch, img_batch, gtboxes_and_label, gtboxes_and_label_minAreaRectangle,
fast_rcnn_decode_boxes, fast_rcnn_score, detection_category, fast_rcnn_decode_boxes_rotate,
fast_rcnn_score_rotate, detection_category_rotate])
end = time.time()
# gtboxes convert dict
gtboxes_horizontal_dict[str(_img_name_batch[0])] = []
predict_horizontal_dict[str(_img_name_batch[0])] = []
gtboxes_rotate_dict[str(_img_name_batch[0])] = []
predict_rotate_dict[str(_img_name_batch[0])] = []
gtbox_horizontal_list, predict_horizontal_list = \
make_dict_packle(_gtboxes_and_label_minAreaRectangle, _fast_rcnn_decode_boxes,
_fast_rcnn_score, _detection_category)
if mode == 0:
gtbox_rotate_list, predict_rotate_list = \
make_dict_packle(_gtboxes_and_label_minAreaRectangle, _fast_rcnn_decode_boxes_rotate,
_fast_rcnn_score_rotate, _detection_category_rotate)
else:
gtbox_rotate_list, predict_rotate_list = \
make_dict_packle(_gtboxes_and_label, _fast_rcnn_decode_boxes_rotate,
_fast_rcnn_score_rotate, _detection_category_rotate)
gtboxes_horizontal_dict[str(
_img_name_batch[0])].extend(gtbox_horizontal_list)
predict_horizontal_dict[str(
_img_name_batch[0])].extend(predict_horizontal_list)
gtboxes_rotate_dict[str(
_img_name_batch[0])].extend(gtbox_rotate_list)
predict_rotate_dict[str(
_img_name_batch[0])].extend(predict_rotate_list)
view_bar(
'{} image cost {}s'.format(str(_img_name_batch[0]),
(end - start)), i + 1, img_num)
fw1 = open('gtboxes_horizontal_dict.pkl', 'w')
fw2 = open('predict_horizontal_dict.pkl', 'w')
fw3 = open('gtboxes_rotate_dict.pkl', 'w')
fw4 = open('predict_rotate_dict.pkl', 'w')
pickle.dump(gtboxes_horizontal_dict, fw1)
pickle.dump(predict_horizontal_dict, fw2)
pickle.dump(gtboxes_rotate_dict, fw3)
pickle.dump(predict_rotate_dict, fw4)
fw1.close()
fw2.close()
fw3.close()
fw4.close()
coord.request_stop()
coord.join(threads)
def train():
with tf.Graph().as_default():
##############
# input data #
##############
with tf.name_scope('get_batch'):
data = Read_tfrecord()
iterator, img_name, img, gtboxes_label, num_gtbox = data.get_batch_data(
)
with tf.name_scope('draw_gtboxes'):
gtboxes_in_img = draw_box_with_tensor(img,
tf.reshape(
gtboxes_label,
[-1, 5])[:, :-1],
text=img_name)
# original_img = tf.squeeze(img, axis=0)+tf.constant(cfg.DEPTH_MEAN)
# original_img = tf.reshape(original_img, shape=tf.shape(img))
# tf.summary.image('images/original_images', original_img)
####################
# backbone network #
####################
_, end_point = get_network_byname(net_name=cfg.NETWORK_NAME,
inputs=img,
num_classes=None,
is_training=True,
global_pool=False,
output_stride=None,
spatial_squeeze=False)
###############
# rpn network #
###############
rpn_net = build_rpn.RPN(
net_name=cfg.NETWORK_NAME,
inputs=img,
gtboxes_and_label=tf.squeeze(gtboxes_label, axis=0),
is_training=True,
end_point=end_point,
anchor_scales=cfg.ANCHOR_SCALES,
anchor_ratios=cfg.ANCHOR_RATIOS,
scale_factors=cfg.SCALE_FACTOR,
base_anchor_size_list=cfg.BASE_ANCHOR_SIZE_LIST,
stride=cfg.STRIDE,
level=cfg.LEVEL,
top_k_nms=cfg.TOP_K_NMS,
share_head=cfg.IS_SHARE_HEAD,
rpn_nms_iou_threshold=cfg.RPN_NMS_IOU_THRESHOLD,
max_proposal_num=cfg.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfg.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negtive_threshold=cfg.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batchsize=cfg.RPN_MINI_BATCH_SIZE,
rpn_positive_ratio=cfg.POSITIVE_RATIO,
remove_outside_anchors=cfg.IS_FILTER_OUTSIDE_ANCHORS,
rpn_weight_decay=cfg.RPN_WEIGHT_DECAY)
rpn_proposals_boxes, rpn_proposals_scores = rpn_net.rpn_proposals()
rpn_location_loss, rpn_classification_loss = rpn_net.rpn_loss()
rpn_net_loss = rpn_location_loss + rpn_classification_loss
with tf.name_scope('draw_proposals'):
rpn_object_indices = tf.reshape(tf.where(
tf.greater(rpn_proposals_scores, 0.5)),
shape=[-1])
# clip boxes into image shape
clip_rpn_proposals_boxes = clip_boxes_to_img_boundaries(
rpn_proposals_boxes, tf.shape(img))
rpn_object_boxes = tf.gather(clip_rpn_proposals_boxes,
indices=rpn_object_indices)
rpn_object_boxes_in_img = draw_box_with_tensor(
img_batch=img,
boxes=rpn_object_boxes,
text=tf.shape(rpn_object_boxes)[0])
rpn_proposals_boxes_in_img = draw_box_with_tensor(
img_batch=img,
boxes=clip_rpn_proposals_boxes,
text=tf.shape(rpn_proposals_boxes)[0])
#############
# fast-rcnn #
#############
fast_rcnn = build_fast_rcnn.FastRcnn(
img_batch=img,
feature_dict=rpn_net.feature_pyramid,
rpn_proposal_boxes=rpn_proposals_boxes,
rpn_proposal_scores=rpn_proposals_scores,
gtboxes_and_label=tf.squeeze(gtboxes_label, axis=0),
crop_size=cfg.CROP_SIZE,
roi_pooling_kernel_size=cfg.ROI_POOLING_KERNEL_SIZE,
levels=cfg.LEVEL,
is_training=True,
weights_regularizer=cfg.FAST_RCNN_WEIGHTS_DECAY,
num_cls=cfg.NUM_CLASSES,
scale_factors=cfg.SCALE_FACTOR,
fast_rcnn_nms_iou_threshold=cfg.FAST_RCNN_NMS_IOU_THRESHOLD,
max_num_per_class=cfg.MAX_NUM_PER_CLASS,
fast_rcnn_score_threshold=cfg.FAST_RCNN_SCORE_THRESHOLD,
fast_rcnn_positive_threshold_iou=cfg.
FAST_RCNN_POSITIVE_THRESHOLD_IOU,
fast_rcnn_minibatch_size=cfg.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positive_ratio=cfg.FAST_RCNN_POSITIVE_RATIO)
fast_rcnn_decode_boxes, fast_rcnn_category, fast_rcnn_scores, num_object = \
fast_rcnn.fast_rcnn_prediction()
fast_rcnn_boxes_loss, fast_rcnn_cls_loss = fast_rcnn.fast_rcnn_loss()
fast_rcnn_total_loss = fast_rcnn_boxes_loss + fast_rcnn_cls_loss
with tf.name_scope('fast_rcnn_prediction_boxes'):
fast_rcnn_prediction_in_image = draw_boxes_with_category(
img_batch=img,
boxes=fast_rcnn_decode_boxes,
category=fast_rcnn_category,
scores=fast_rcnn_scores)
#####################
# optimization part #
#####################
# global_step = tf.train.get_or_create_global_step()
# total_loss = slim.losses.get_losses()
# total_loss = tf.reduce_sum(total_loss * tf.constant(cfg.LOSS_WEIGHT, dtype=tf.float32))
#
# lr = tf.train.piecewise_constant(global_step,
# [60000],
# [cfg.BASE_LEARNING_RATE, cfg.BASE_LEARNING_RATE/10])
#
# optimizer = slim.train.MomentumOptimizer(learning_rate=lr,
# momentum=cfg.MOMENTUM,)
#
# train_op = optimizer.minimize(total_loss, global_step)
global_step = tf.train.get_or_create_global_step()
total_loss = slim.losses.get_total_loss()
lr = tf.train.piecewise_constant(
global_step, [60000],
[cfg.BASE_LEARNING_RATE, cfg.BASE_LEARNING_RATE / 10])
optimizer = tf.train.MomentumOptimizer(learning_rate=lr,
momentum=cfg.MOMENTUM)
train_op = slim.learning.create_train_op(total_loss, optimizer,
global_step)
###########
# summary #
###########
# ground truth boxes
tf.summary.image('images/gtboxes', gtboxes_in_img)
# rpn net's proposals
tf.summary.image('images/rpn/proposals', rpn_proposals_boxes_in_img)
tf.summary.image('images/rpn/objects', rpn_object_boxes_in_img)
# rpn loss scale
tf.summary.scalar('losses/rpn/location_loss', rpn_location_loss)
tf.summary.scalar('losses/rpn/cls_loss', rpn_classification_loss)
tf.summary.scalar('losses/rpn/total_loss', rpn_net_loss)
# fast rcnn prediction boxes
tf.summary.image('images/fast_rcnn/prediction_boxes',
fast_rcnn_prediction_in_image)
# fast loss part
tf.summary.scalar('losses/fast_rcnn/location_loss',
fast_rcnn_boxes_loss)
tf.summary.scalar('losses/fast_rcnn/cls_loss', fast_rcnn_cls_loss)
tf.summary.scalar('losses/fast_rcnn/total_loss', fast_rcnn_total_loss)
tf.summary.scalar('losses/total_loss', total_loss)
tf.summary.scalar('learing_rate', lr)
if debug:
# bcckbone network
for key in end_point.keys():
tf.summary.histogram('value/' + key, end_point[key])
# weights
for weight in slim.get_model_variables():
tf.summary.histogram('weight/' + weight.name, weight.value())
# rpn anchor
image_with_anchor_list = debug_rpn.debug_rpn(rpn_net, img)
for i, image_with_anchor in enumerate(image_with_anchor_list):
tf.summary.image('anchors/image_with_anchors_' + str(i),
image_with_anchor[0])
# fast rcnn prediction
tf.summary.tensor_summary('image_shape', tf.shape(img))
tf.summary.tensor_summary('fast_rcnn_prediction_boxes',
fast_rcnn_decode_boxes)
summary_op = tf.summary.merge_all()
summary_path = cfg.SUMMARY_PATH
check_and_create_paths([summary_path])
################
# session part #
################
init_op = tf.group(tf.local_variables_initializer(),
tf.global_variables_initializer())
checkpoint_path, restorer = get_restorer()
with tf.Session() as sess:
# initial part
sess.run(init_op)
sess.run(iterator.initializer)
summary_writer = tf.summary.FileWriter(summary_path,
graph=sess.graph)
saver = tf.train.Saver()
if checkpoint_path:
restorer.restore(sess, checkpoint_path)
print('restore is done!!!')
step = 0
while True:
try:
if step >= 30:
break
training_time = time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time()))
start_time = time.time()
_global_step,\
_img_name,\
_rpn_location_loss,\
_rpn_classification_loss,\
_rpn_net_loss,\
_fast_rcnn_boxes_loss,\
_fast_rcnn_cls_loss,\
_fast_rcnn_total_loss,\
_total_loss,\
_train_op,\
summary_str\
= sess.run([global_step,
img_name,
rpn_location_loss,
rpn_classification_loss,
rpn_net_loss,
fast_rcnn_boxes_loss,
fast_rcnn_cls_loss,
fast_rcnn_total_loss,
total_loss,
train_op,
summary_op])
end_time = time.time()
# print the result in screen
if 1: # step % 10 == 0:
cost_time = end_time - start_time
print(
"""-----time:%s---step:%d---image name:%s---cost_time:%.4fs-----\n
total_loss:%.4f\n
rpn_boxes_loss:%.4f rpn_class_loss:%.4f rpn_total_loss:%.4f\n
fast_rcnn_boxes_loss:%.4f fast_rcnn_class_loss:%.4f fast_rcnn_total_loss:%4f"""
% (training_time, _global_step, str(_img_name),
cost_time, _total_loss, _rpn_location_loss,
_rpn_classification_loss, _rpn_net_loss,
_fast_rcnn_boxes_loss, _fast_rcnn_cls_loss,
_fast_rcnn_total_loss))
# add summary
if step % 10 == 0:
# summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
# save ckpt
if step % 10000 == 0 and step > 1:
check_and_create_paths([cfg.CKPT_PATH])
save_path = os.path.join(cfg.CKPT_PATH,
'model_weights')
saver.save(sess, save_path, global_step)
step += 1
except tf.errors.OutOfRangeError:
break
summary_writer.close()
def inference():
with tf.Graph().as_default():
img_plac = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8)
img_tensor = tf.cast(img_plac, tf.float32) - tf.constant(
[103.939, 116.779, 123.68])
img_batch = image_preprocess.short_side_resize_for_inference_data(
img_tensor,
target_shortside_len=cfgs.SHORT_SIDE_LEN,
is_resize=True)
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
_, share_net = get_network_byname(net_name=cfgs.NET_NAME,
inputs=img_batch,
num_classes=None,
is_training=True,
output_stride=None,
global_pool=False,
spatial_squeeze=False)
# ***********************************************************************************************
# * RPN *
# ***********************************************************************************************
rpn = build_rpn.RPN(
net_name=cfgs.NET_NAME,
inputs=img_batch,
gtboxes_and_label=None,
is_training=False,
share_head=cfgs.SHARE_HEAD,
share_net=share_net,
stride=cfgs.STRIDE,
anchor_ratios=cfgs.ANCHOR_RATIOS,
anchor_scales=cfgs.ANCHOR_SCALES,
scale_factors=cfgs.SCALE_FACTORS,
base_anchor_size_list=cfgs.
BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6
level=cfgs.LEVEL,
top_k_nms=cfgs.RPN_TOP_K_NMS,
rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD,
max_proposals_num=cfgs.MAX_PROPOSAL_NUM,
rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD,
rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD,
rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE,
rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE,
remove_outside_anchors=False, # whether remove anchors outside
rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME])
# rpn predict proposals
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(
) # rpn_score shape: [300, ]
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
img_batch=img_batch,
feature_pyramid=rpn.feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
rpn_proposals_scores=rpn_proposals_scores,
img_shape=tf.shape(img_batch),
roi_size=cfgs.ROI_SIZE,
scale_factors=cfgs.SCALE_FACTORS,
roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE,
gtboxes_and_label=None,
fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD,
fast_rcnn_maximum_boxes_per_img=100,
fast_rcnn_nms_max_boxes_per_class=cfgs.
FAST_RCNN_NMS_MAX_BOXES_PER_CLASS,
show_detections_score_threshold=cfgs.FINAL_SCORE_THRESHOLD,
# show detections which score >= 0.6
num_classes=cfgs.CLASS_NUM,
fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE,
fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE,
fast_rcnn_positives_iou_threshold=cfgs.
FAST_RCNN_IOU_POSITIVE_THRESHOLD,
use_dropout=False,
weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME],
is_training=False,
level=cfgs.LEVEL)
fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category = \
fast_rcnn.fast_rcnn_predict()
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = restore_model.get_restorer()
config = tf.ConfigProto()
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess, coord)
imgs, img_names = get_imgs()
for i, img in enumerate(imgs):
start = time.time()
_img_batch, _fast_rcnn_decode_boxes, _fast_rcnn_score, _detection_category = \
sess.run([img_batch, fast_rcnn_decode_boxes, fast_rcnn_score, detection_category],
feed_dict={img_plac: img})
end = time.time()
img_np = np.squeeze(_img_batch, axis=0)
img_np = draw_box_cv(img_np,
boxes=_fast_rcnn_decode_boxes,
labels=_detection_category,
scores=_fast_rcnn_score)
mkdir(cfgs.INFERENCE_SAVE_PATH)
cv2.imwrite(
cfgs.INFERENCE_SAVE_PATH +
'/{}_fpn.jpg'.format(img_names[i]), img_np)
view_bar('{} cost {}s'.format(img_names[i], (end - start)),
i + 1, len(imgs))
coord.request_stop()
coord.join(threads)
def model_fn(features, labels, mode, params, config):
# ***********************************************************************************************
# * share net *
# ***********************************************************************************************
net_config = params["net_config"]
if mode == tf.estimator.ModeKeys.TRAIN:
IS_TRAINING = True
else:
IS_TRAINING = False
origin_image_batch = features["image"]
image_window = features["image_window"]
image_batch = origin_image_batch - net_config.PIXEL_MEANS
# there is is_training means that bn is training, so it is important!
_, share_net = get_network_byname(inputs=image_batch,
config=net_config,
is_training=False,
reuse=tf.AUTO_REUSE)
# ***********************************************************************************************
# * fpn *
# ***********************************************************************************************
feature_pyramid = build_fpn.build_feature_pyramid(share_net, net_config)
# ***********************************************************************************************
# * rpn *
# ***********************************************************************************************
gtboxes_and_label_batch = labels.get("gt_box_labels")
rpn = build_rpn.RPN(feature_pyramid=feature_pyramid,
image_window=image_window,
config=net_config)
# rpn_proposals_scores==(2000,)
rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals(IS_TRAINING)
rpn_location_loss, rpn_classification_loss = rpn.rpn_losses(
labels["minibatch_indices"], labels["minibatch_encode_gtboxes"],
labels["minibatch_objects_one_hot"])
rpn_total_loss = rpn_classification_loss + rpn_location_loss
# ***********************************************************************************************
# * Rerference image *
# ***********************************************************************************************
reference_image = load_reference_image()
reference_image = tf.cast(reference_image, tf.float32)
reference_image = reference_image - net_config.PIXEL_MEANS
_, reference_share_net = get_network_byname(inputs=reference_image,
config=net_config,
is_training=False,
reuse=tf.AUTO_REUSE)
reference_feature_pyramid = build_fpn.build_feature_pyramid(
reference_share_net, net_config)
# average the features of support images
# reference_feature_pyramid[key](C*S, H, W, 256)---->(C, 7, 7, 256)
with tf.variable_scope('reference_feature_origision'):
for key, value in reference_feature_pyramid.items():
reference_feature_pyramid[key] = tf.image.resize_bilinear(
reference_feature_pyramid[key],
(net_config.ROI_SIZE, net_config.ROI_SIZE))
reference_feature_pyramid[key] = tf.reduce_mean(tf.reshape(
reference_feature_pyramid[key],
(net_config.NUM_CLASS - 1, net_config.NUM_SUPPROTS,
net_config.ROI_SIZE, net_config.ROI_SIZE, 256)),
axis=1)
# average the features of fpn features
average_fpn_feature = []
for key, value in reference_feature_pyramid.items():
average_fpn_feature.append(value)
reference_fpn_features = tf.reduce_mean(tf.stack(average_fpn_feature,
axis=0),
axis=0)
# compute the negative features
with tf.variable_scope("reference_negative"):
with slim.arg_scope(
[slim.conv2d],
padding="SAME",
weights_initializer=tf.glorot_uniform_initializer(),
weights_regularizer=slim.l2_regularizer(
net_config.WEIGHT_DECAY)):
# the shape of positive features is (1, H, W, C*channels)
positive_features = tf.reshape(
tf.transpose(reference_fpn_features, (1, 2, 0, 3)),
(1, net_config.ROI_SIZE, net_config.ROI_SIZE,
(net_config.NUM_CLASS - 1) * 256))
# (1, H, W, channels)
negative_feature = slim.conv2d(positive_features,
num_outputs=256,
kernel_size=[3, 3],
stride=1)
total_refernece_feature = tf.concat(
[negative_feature, reference_fpn_features], axis=0)
# ***********************************************************************************************
# * Fast RCNN *
# ***********************************************************************************************
fast_rcnn = build_fast_rcnn.FastRCNN(
feature_pyramid=feature_pyramid,
rpn_proposals_boxes=rpn_proposals_boxes,
origin_image=origin_image_batch,
gtboxes_and_label=gtboxes_and_label_batch,
reference_feature=total_refernece_feature,
config=net_config,
is_training=False,
image_window=image_window)
detections = fast_rcnn.fast_rcnn_detection()
if DEBUG:
rpn_proposals_vision = draw_boxes_with_scores(
origin_image_batch[0, :, :, :], rpn_proposals_boxes[0, :50, :],
rpn_proposals_scores[0, :50])
fast_rcnn_vision = draw_boxes_with_categories_and_scores(
origin_image_batch[0, :, :, :], detections[0, :, :4],
detections[0, :, 4], detections[0, :, 5])
tf.summary.image("rpn_proposals_vision", rpn_proposals_vision)
tf.summary.image("fast_rcnn_vision", fast_rcnn_vision)
fast_rcnn_location_loss, fast_rcnn_classification_loss = fast_rcnn.fast_rcnn_loss(
)
fast_rcnn_total_loss = 5.0 * fast_rcnn_classification_loss + fast_rcnn_location_loss
# train
with tf.variable_scope("regularization_losses"):
regularization_list = [
tf.nn.l2_loss(w.read_value()) * net_config.WEIGHT_DECAY /
tf.cast(tf.size(w.read_value()), tf.float32)
for w in tf.trainable_variables()
if 'gamma' not in w.name and 'beta' not in w.name
]
regularization_losses = tf.add_n(regularization_list)
total_loss = regularization_losses + fast_rcnn_total_loss + rpn_total_loss
global_step = slim.get_or_create_global_step()
tf.train.init_from_checkpoint(
net_config.CHECKPOINT_DIR,
{net_config.NET_NAME + "/": net_config.NET_NAME + "/"})
with tf.variable_scope("optimizer"):
lr = tf.train.piecewise_constant(global_step,
boundaries=[
np.int64(net_config.BOUNDARY[0]),
np.int64(net_config.BOUNDARY[1])
],
values=[
net_config.LEARNING_RATE,
net_config.LEARNING_RATE / 10,
net_config.LEARNING_RATE / 100
])
optimizer = tf.train.MomentumOptimizer(lr,
momentum=net_config.MOMENTUM)
optimizer = tf.contrib.estimator.TowerOptimizer(optimizer)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies([tf.group(*update_ops)]):
grads = optimizer.compute_gradients(total_loss)
for i, (g, v) in enumerate(grads):
if g is not None:
grads[i] = (tf.clip_by_norm(g, 5.0), v) # clip gradients
train_op = optimizer.apply_gradients(grads, global_step)
# ***********************************************************************************************
# * Summary *
# ***********************************************************************************************
# rpn loss and image
tf.summary.scalar('rpn/rpn_location_loss', rpn_location_loss)
tf.summary.scalar('rpn/rpn_classification_loss', rpn_classification_loss)
tf.summary.scalar('rpn/rpn_total_loss', rpn_total_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_location_loss',
fast_rcnn_location_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_classification_loss',
fast_rcnn_classification_loss)
tf.summary.scalar('fast_rcnn/fast_rcnn_total_loss', fast_rcnn_total_loss)
tf.summary.scalar('learning_rate', lr)
tf.summary.scalar('total_loss', total_loss)
summary_hook = tf.train.SummarySaverHook(
save_steps=net_config.SAVE_EVERY_N_STEP,
output_dir=net_config.MODLE_DIR,
summary_op=tf.summary.merge_all())
if mode == tf.estimator.ModeKeys.TRAIN:
return tf.estimator.EstimatorSpec(mode,
loss=total_loss,
train_op=train_op,
training_hooks=[summary_hook])
if mode == tf.estimator.ModeKeys.EVAL:
predicts = {
"predict_bbox": detections[:, :, :4],
"predict_class_id": detections[:, :, 5],
"predict_scores": detections[:, :, 4]
}
return tf.estimator.EstimatorSpec(mode,
loss=total_loss,
predictions=predicts)
if mode == tf.estimator.ModeKeys.PREDICT:
predicts = {
"predict_bbox": detections[:, :, :4],
"predict_class_id": detections[:, :, 5],
"predict_scores": detections[:, :, 4]
}
return tf.estimator.EstimatorSpec(mode, predictions=predicts)
