def precision_score(self, y_true, y_pred, **kwargs):
nms_flag = kwargs.pop('nms_flag', True)
if nms_flag:
bboxes = predict_nms_boxes(y_pred)
else:
bboxes = convert_boxes(y_pred)
gt_bboxes = convert_boxes(y_true)
score = cal_precision(gt_bboxes, bboxes)
return score
def score(self, y_true, y_pred, **kwargs):
"""Compute Recall for a given predicted bboxes"""
nms_flag = kwargs.pop('nms_flag', True)
if nms_flag:
bboxes = predict_nms_boxes(y_pred)
else:
bboxes = convert_boxes(y_pred)
gt_bboxes = convert_boxes(y_true)
score = cal_recall(gt_bboxes, bboxes)
return score
nms_flag = True
hp_d = dict()
# hp_d['image_mean'] = image_mean
hp_d['batch_size'] = 16
hp_d['nms_flag'] = nms_flag
""" 3. Build graph, load weights, initialize a session and start test """
# Initialize
graph = tf.get_default_graph()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
model = ConvNet([IM_SIZE[0], IM_SIZE[1], 3],
NUM_CLASS,
anchors,
grid_size=(IM_SIZE[0] // 32, IM_SIZE[1] // 32))
saver = tf.train.Saver()
sess = tf.Session(graph=graph, config=config)
saver.restore(sess, '/tmp/model.ckpt')
test_y_pred = model.predict(sess, test_set, **hp_d)
""" 4. Draw boxes on image """
draw_dir = os.path.join(test_dir, 'draws')
for idx, (img, y_pred) in enumerate(zip(test_set.images, test_y_pred)):
draw_path = os.path.join(draw_dir, '{}_test_images.png'.format(idx + 1))
if nms_flag:
bboxes = predict_nms_boxes(y_pred)
else:
bboxes = convert_boxes(y_pred)
bboxes = bboxes[np.nonzero(np.any(bboxes > 0, axis=1))]
boxed_img = draw_pred_boxes(img, bboxes, class_map, score=True)
cv2.imwrite(draw_path, boxed_img)