def bboxes_eval(org_image, image_shape, bbox_img, cls_pred_logits, bboxes_pred,
glabels_raw, gbboxes_raw, isdifficult, num_classes):
# Performing post-processing on CPU: loop-intensive, usually more efficient.
cls_pred_prob = tf.nn.softmax(
tf.reshape(cls_pred_logits, [-1, num_classes]))
bboxes_pred = tf.reshape(bboxes_pred, [-1, 4])
glabels_raw = tf.reshape(glabels_raw, [-1])
gbboxes_raw = tf.reshape(gbboxes_raw, [-1, 4])
gbboxes_raw = tf.boolean_mask(gbboxes_raw, glabels_raw > 0)
glabels_raw = tf.boolean_mask(glabels_raw, glabels_raw > 0)
isdifficult = tf.reshape(isdifficult, [-1])
with tf.device('/device:CPU:0'):
selected_scores, selected_bboxes = eval_helper.tf_bboxes_select(
[cls_pred_prob], [bboxes_pred],
FLAGS.select_threshold,
num_classes,
scope='xdet_v2_select')
selected_bboxes = eval_helper.bboxes_clip(bbox_img, selected_bboxes)
selected_scores, selected_bboxes = eval_helper.filter_boxes(
selected_scores,
selected_bboxes,
0.03,
image_shape, [FLAGS.train_image_size] * 2,
keep_top_k=FLAGS.nms_topk * 2)
# Resize bboxes to original image shape.
selected_bboxes = eval_helper.bboxes_resize(bbox_img, 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)
# label_scores, pred_labels, bboxes_pred = eval_helper.xdet_predict(bbox_img, cls_pred_prob, bboxes_pred, image_shape, FLAGS.train_image_size, FLAGS.nms_threshold, FLAGS.select_threshold, FLAGS.nms_topk, num_classes, nms_mode='union')
dict_metrics = {}
# Compute TP and FP statistics.
num_gbboxes, tp, fp = eval_helper.bboxes_matching_batch(
selected_scores.keys(), selected_scores, selected_bboxes,
glabels_raw, gbboxes_raw, isdifficult)
# FP and TP metrics.
tp_fp_metric = metrics.streaming_tp_fp_arrays(num_gbboxes, tp, fp,
selected_scores)
metrics_name = ('nobjects', 'ndetections', 'tp', 'fp', 'scores')
for c in tp_fp_metric[0].keys():
for _ in range(len(tp_fp_metric[0][c])):
dict_metrics['tp_fp_%s_%s' %
(label2name_table[c], metrics_name[_])] = (
tp_fp_metric[0][c][_], tp_fp_metric[1][c][_])
# Add to summaries precision/recall values.
aps_voc07 = {}
aps_voc12 = {}
for c in tp_fp_metric[0].keys():
# Precison and recall values.
prec, rec = metrics.precision_recall(*tp_fp_metric[0][c])
# Average precision VOC07.
v = metrics.average_precision_voc07(prec, rec)
summary_name = 'AP_VOC07/%s' % c
op = tf.summary.scalar(summary_name, v)
# op = tf.Print(op, [v], summary_name)
#tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
aps_voc07[c] = v
# Average precision VOC12.
v = metrics.average_precision_voc12(prec, rec)
summary_name = 'AP_VOC12/%s' % c
op = tf.summary.scalar(summary_name, v)
# op = tf.Print(op, [v], summary_name)
#tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
aps_voc12[c] = v
# Mean average precision VOC07.
summary_name = 'AP_VOC07/mAP'
mAP = tf.add_n(list(aps_voc07.values())) / len(aps_voc07)
mAP = tf.Print(mAP, [mAP], summary_name)
op = tf.summary.scalar(summary_name, mAP)
#tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
# Mean average precision VOC12.
summary_name = 'AP_VOC12/mAP'
mAP = tf.add_n(list(aps_voc12.values())) / len(aps_voc12)
mAP = tf.Print(mAP, [mAP], summary_name)
op = tf.summary.scalar(summary_name, mAP)
#tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
labels_list = []
for k, v in selected_scores.items():
labels_list.append(tf.ones_like(v, tf.int32) * k)
save_image_op = tf.py_func(
save_image_with_bbox,
[
org_image,
tf.concat(labels_list, axis=0),
#tf.convert_to_tensor(list(selected_scores.keys()), dtype=tf.int64),
tf.concat(list(selected_scores.values()), axis=0),
tf.concat(list(selected_bboxes.values()), axis=0)
],
tf.int64,
stateful=True)
#dict_metrics['save_image_with_bboxes'] = save_image_count#tf.tuple([save_image_count, save_image_count_update_op])
# for i, v in enumerate(l_precisions):
# summary_name = 'eval/precision_at_recall_%.2f' % LIST_RECALLS[i]
# op = tf.summary.scalar(summary_name, v, collections=[])
# op = tf.Print(op, [v], summary_name)
# tf.add_to_collection(tf.GraphKeys.SUMMARIES, op)
# print(dict_metrics)
# metric_names = dict_metrics.keys()
# value_ops, update_ops = zip(*dict_metrics.values())
# return dict(zip(metric_names, update_ops)), save_image_op
return dict_metrics, save_image_op
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)
