def input_fn():
all_anchors, num_anchors_list = anchor_creator.get_all_anchors()
anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(
all_anchors,
num_classes=FLAGS.num_classes,
allowed_borders=[0.05],
positive_threshold=FLAGS.match_threshold,
ignore_threshold=FLAGS.neg_threshold,
prior_scaling=[0.1, 0.1, 0.2, 0.2])
list_from_batch, _ = dataset_factory.get_dataset(
FLAGS.dataset_name,
FLAGS.dataset_split_name,
FLAGS.data_dir,
image_preprocessing_fn,
file_pattern=None,
reader=None,
batch_size=FLAGS.batch_size,
num_readers=FLAGS.num_readers,
num_preprocessing_threads=FLAGS.num_preprocessing_threads,
num_epochs=FLAGS.train_epochs,
anchor_encoder=anchor_encoder_decoder.encode_all_anchors)
return list_from_batch[-1], {
'targets':
list_from_batch[:-1],
'decode_fn':
lambda pred: anchor_encoder_decoder.decode_all_anchors([pred])[0],
'num_anchors_list':
num_anchors_list
}
def input_fn():
all_anchors, num_anchors_list = anchor_creator.get_all_anchors()
anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(all_anchors,
num_classes = FLAGS.num_classes,
allowed_borders = [0.],
positive_threshold = FLAGS.rpn_match_threshold,
ignore_threshold = FLAGS.rpn_neg_threshold,
prior_scaling=[1., 1., 1., 1.],#[0.1, 0.1, 0.2, 0.2],
rpn_fg_thres = FLAGS.match_threshold,
rpn_bg_high_thres = FLAGS.neg_threshold_high,
rpn_bg_low_thres = FLAGS.neg_threshold_low)
list_from_batch, _ = dataset_factory.get_dataset(FLAGS.dataset_name,
FLAGS.dataset_split_name,
FLAGS.data_dir,
image_preprocessing_fn,
file_pattern = None,
reader = None,
batch_size = FLAGS.batch_size,
num_readers = FLAGS.num_readers,
num_preprocessing_threads = FLAGS.num_preprocessing_threads,
num_epochs = FLAGS.train_epochs,
anchor_encoder = anchor_encoder_decoder.encode_all_anchors)
#print(list_from_batch[-4], list_from_batch[-3])
return list_from_batch[-1], {'targets': list_from_batch[:-1],
'rpn_decode_fn': lambda pred : anchor_encoder_decoder.decode_all_anchors([pred], squeeze_inner=True)[0],
'head_decode_fn': lambda rois, pred : anchor_encoder_decoder.ext_decode_rois(rois, pred, head_prior_scaling=[1., 1., 1., 1.]),
'rpn_encode_fn': lambda rois : anchor_encoder_decoder.ext_encode_rois(rois, list_from_batch[-4], list_from_batch[-3], FLAGS.roi_one_image, FLAGS.fg_ratio, 0.1, head_prior_scaling=[1., 1., 1., 1.]),
'num_anchors_list': num_anchors_list}
def main(_):
print(tf.gfile.Glob('./debug/example_01?.jpg'))
if not FLAGS.data_dir:
raise ValueError(
'You must supply the dataset directory with --data_dir')
tf.logging.set_verbosity(tf.logging.DEBUG)
with tf.Graph().as_default():
global_step = slim.create_global_step()
#print(tf.gfile.Glob('./debug/example_01?.jpg'))
preprocessing_name = FLAGS.preprocessing_name or FLAGS.model_name
image_preprocessing_fn = lambda image_, shape_, glabels_, gbboxes_: preprocessing_factory.get_preprocessing(
preprocessing_name, is_training=True)(image_,
glabels_,
gbboxes_,
out_shape=
[FLAGS.train_image_size] * 2,
data_format=DATA_FORMAT)
anchor_creator = anchor_manipulator.AnchorCreator(
[FLAGS.train_image_size] * 2,
layers_shapes=[(38, 38), (19, 19), (10, 10)],
anchor_scales=[[0.1, 0.2], [0.3, 0.4], [0.5, 0.6]],
extra_anchor_scales=[[0.15], [0.35], [0.55]],
anchor_ratios=[[2, .5], [2, .5, 3, 1. / 3], [2, .5, 3, 1. / 3]],
layer_steps=[8, 16, 32])
all_anchors = anchor_creator.get_all_anchors()[0]
# sess = tf.Session()
# print(all_anchors)
# print(sess.run(all_anchors))
anchor_operator = anchor_manipulator.AnchorEncoder(
all_anchors,
num_classes=FLAGS.num_classes,
ignore_threshold=0.,
prior_scaling=[0.1, 0.1, 0.2, 0.2])
#anchor_encoder_fn = lambda
next_iter, _ = dataset_factory.get_dataset(
FLAGS.dataset_name,
FLAGS.dataset_split_name,
FLAGS.data_dir,
image_preprocessing_fn,
file_pattern=None,
reader=None,
batch_size=FLAGS.batch_size,
num_readers=FLAGS.num_readers,
num_preprocessing_threads=FLAGS.num_preprocessing_threads,
anchor_encoder=anchor_operator.encode_all_anchors)
sess = tf.Session()
sess.run(
tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer(),
tf.tables_initializer()))
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
count = 0
start_time = time.time()
try:
while not coord.should_stop():
count += 1
_ = sess.run([next_iter])
if count % 10 == 0:
time_elapsed = time.time() - start_time
print('time: {}'.format(time_elapsed / 10.))
start_time = time.time()
except tf.errors.OutOfRangeError:
log.info('Queue Done!')
finally:
pass
# Wait for threads to finish.
coord.join(threads)
sess.close()
for i in range(6):
list_from_batch = sess.run(next_iter)
# imsave('./debug/example_%03d.jpg' % (i,), list_from_batch[0][0])
# imsave('./debug/example_%03d_.jpg' % (i,), list_from_batch[1][0])
image = list_from_batch[-1]
shape = list_from_batch[-2]
glabels = list_from_batch[:len(all_anchors)]
gtargets = list_from_batch[len(all_anchors):2 * len(all_anchors)]
gscores = list_from_batch[2 * len(all_anchors):3 *
len(all_anchors)]
imsave('./debug/example_%03d.jpg' % (i, ), image[0])
print(image.shape, shape.shape, glabels[0].shape,
gtargets[0].shape, gscores[0].shape)
def main(_):
with tf.Graph().as_default():
image_input = tf.placeholder(tf.uint8, shape=(None, None, 3))
shape_input = tf.placeholder(tf.int32, shape=(2, ))
features = common_preprocessing.light_head_preprocess_for_test(
image_input, [FLAGS.train_image_size] * 2,
data_format=('NCHW'
if FLAGS.data_format == 'channels_first' else 'NHWC'))
features = tf.expand_dims(features, axis=0)
anchor_creator = anchor_manipulator.AnchorCreator(
[FLAGS.train_image_size] * 2,
layers_shapes=[(30, 30)],
anchor_scales=[[0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]],
extra_anchor_scales=[[0.1]],
anchor_ratios=[[1., 2., .5]],
layer_steps=[16])
all_anchors, num_anchors_list = anchor_creator.get_all_anchors()
anchor_encoder_decoder = anchor_manipulator.AnchorEncoder(
all_anchors,
num_classes=FLAGS.num_classes,
allowed_borders=None,
positive_threshold=None,
ignore_threshold=None,
prior_scaling=[1., 1., 1., 1.])
with tf.variable_scope(FLAGS.model_scope,
default_name=None,
values=[features],
reuse=tf.AUTO_REUSE):
rpn_feat_map, backbone_feat = xception_body.XceptionBody(
features,
FLAGS.num_classes,
is_training=False,
data_format=FLAGS.data_format)
#rpn_feat_map = tf.Print(rpn_feat_map,[tf.shape(rpn_feat_map), rpn_feat_map,backbone_feat])
rpn_cls_score, rpn_bbox_pred = xception_body.get_rpn(
rpn_feat_map, num_anchors_list[0], False, FLAGS.data_format,
'rpn_head')
large_sep_feature = xception_body.large_sep_kernel(
backbone_feat, 256, 10 * 7 * 7, False, FLAGS.data_format,
'large_sep_feature')
if FLAGS.data_format == 'channels_first':
rpn_cls_score = tf.transpose(rpn_cls_score, [0, 2, 3, 1])
rpn_bbox_pred = tf.transpose(rpn_bbox_pred, [0, 2, 3, 1])
rpn_cls_score = tf.reshape(rpn_cls_score, [-1, 2])
rpn_object_score = tf.nn.softmax(rpn_cls_score)[:, -1]
rpn_object_score = tf.reshape(rpn_object_score, [1, -1])
rpn_location_pred = tf.reshape(rpn_bbox_pred, [1, -1, 4])
rpn_bboxes_pred = anchor_encoder_decoder.decode_all_anchors(
[rpn_location_pred], squeeze_inner=True)[0]
proposals_bboxes = xception_body.get_proposals(
rpn_object_score, rpn_bboxes_pred, None,
FLAGS.rpn_pre_nms_top_n, FLAGS.rpn_post_nms_top_n,
FLAGS.rpn_nms_thres, FLAGS.rpn_min_size, False,
FLAGS.data_format)
cls_score, bboxes_reg = xception_body.get_head(
large_sep_feature, lambda input_, bboxes_,
grid_width_, grid_height_: ps_roi_align(
input_, bboxes_, grid_width_, grid_height_, pool_method),
7, 7, None, proposals_bboxes, FLAGS.num_classes, False, False,
0, FLAGS.data_format, 'final_head')
head_bboxes_pred = anchor_encoder_decoder.ext_decode_rois(
proposals_bboxes,
bboxes_reg,
head_prior_scaling=[1., 1., 1., 1.])
head_cls_score = tf.reshape(cls_score, [-1, FLAGS.num_classes])
head_cls_score = tf.nn.softmax(head_cls_score)
head_bboxes_pred = tf.reshape(head_bboxes_pred, [-1, 4])
with tf.device('/device:CPU:0'):
selected_scores, selected_bboxes = eval_helper.tf_bboxes_select(
[head_cls_score], [head_bboxes_pred],
FLAGS.select_threshold,
FLAGS.num_classes,
scope='xdet_v2_select')
selected_bboxes = eval_helper.bboxes_clip(
tf.constant([0., 0., 1., 1.]), selected_bboxes)
selected_scores, selected_bboxes = eval_helper.filter_boxes(
selected_scores,
selected_bboxes,
0.03,
shape_input, [FLAGS.train_image_size] * 2,
keep_top_k=FLAGS.nms_topk * 2)
# Resize bboxes to original image shape.
selected_bboxes = eval_helper.bboxes_resize(
tf.constant([0., 0., 1., 1.]), selected_bboxes)
selected_scores, selected_bboxes = eval_helper.bboxes_sort(
selected_scores, selected_bboxes, top_k=FLAGS.nms_topk * 2)
# Apply NMS algorithm.
selected_scores, selected_bboxes = eval_helper.bboxes_nms_batch(
selected_scores,
selected_bboxes,
nms_threshold=FLAGS.nms_threshold,
keep_top_k=FLAGS.nms_topk)
labels_list = []
for k, v in selected_scores.items():
labels_list.append(tf.ones_like(v, tf.int32) * k)
all_labels = tf.concat(labels_list, axis=0)
all_scores = tf.concat(list(selected_scores.values()), axis=0)
all_bboxes = tf.concat(list(selected_bboxes.values()), axis=0)
saver = tf.train.Saver()
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
saver.restore(sess, FLAGS.checkpoint_path)
np_image = imread('./demo/test.jpg')
labels_, scores_, bboxes_ = sess.run(
[all_labels, all_scores, all_bboxes],
feed_dict={
image_input: np_image,
shape_input: np_image.shape[:-1]
})
img_to_draw = draw_toolbox.bboxes_draw_on_img(np_image,
labels_,
scores_,
bboxes_,
thickness=2)
imsave(os.path.join(FLAGS.debug_dir, 'test_out.jpg'), img_to_draw)
