def inference(det_net, data_dir):
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3])
img_batch = tf.cast(img_plac, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(
img_tensor=img_batch, target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN)
det_boxes_r, det_scores_r, det_category_r = det_net.build_whole_detection_network(
input_img_batch=img_batch, gtboxes_batch=None)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = det_net.get_restorer()
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')
imgs = os.listdir(data_dir)
for i, a_img_name in enumerate(imgs):
# f = open('./res_icdar_r/res_{}.txt'.format(a_img_name.split('.jpg')[0]), 'w')
raw_img = cv2.imread(os.path.join(data_dir, a_img_name))
# raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
start = time.time()
resized_img, det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[img_batch, det_boxes_r, det_scores_r, det_category_r],
feed_dict={img_plac: raw_img}
)
end = time.time()
# res_r = coordinate_convert.forward_convert(det_boxes_r_, False)
# res_r = np.array(res_r, np.int32)
# for r in res_r:
# f.write('{},{},{},{},{},{},{},{}\n'.format(r[0], r[1], r[2], r[3],
# r[4], r[5], r[6], r[7]))
# f.close()
det_detections_r = draw_box_in_img.draw_rotate_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_r_,
labels=det_category_r_,
scores=det_scores_r_)
save_dir = os.path.join(cfgs.INFERENCE_SAVE_PATH, cfgs.VERSION)
tools.mkdir(save_dir)
cv2.imwrite(save_dir + '/' + a_img_name + '_r.jpg',
det_detections_r)
view_bar('{} cost {}s'.format(a_img_name, (end - start)), i + 1,
len(imgs))
def inference(self, image):
# if not self.restorer is None:
# self.restorer.restore(self.sess, self.restore_ckpt)
# print('restore model')
inference_start = time.time()
resized_img, det_boxes_h_, det_scores_h_, det_category_h_, \
det_boxes_r_, det_scores_r_, det_category_r_ = \
self.sess.run(
[self.img_batch, self.det_boxes_h, self.det_scores_h, self.det_category_h,
self.det_boxes_r, self.det_scores_r, self.det_category_r],
feed_dict={self.img_plac: image}
)
inference_end = time.time()
inference_time = inference_end - inference_start
print('R2CNN inference time : ', inference_time)
result_image = draw_box_in_img.draw_rotate_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_r_,
labels=det_category_r_,
scores=det_scores_r_)
return result_image, inference_time
def inference(det_net,
file_paths,
des_folder,
h_len,
w_len,
h_overlap,
w_overlap,
save_res=False):
if save_res:
assert cfgs.SHOW_SCORE_THRSHOLD >= 0.5, \
'please set score threshold (example: SHOW_SCORE_THRSHOLD = 0.5) in cfgs.py'
else:
assert cfgs.SHOW_SCORE_THRSHOLD < 0.005, \
'please set score threshold (example: SHOW_SCORE_THRSHOLD = 0.00) in cfgs.py'
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3])
img_batch = tf.cast(img_plac, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(
img_tensor=img_batch,
target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN,
is_resize=False)
det_boxes_h, det_scores_h, det_category_h, \
det_boxes_r, det_scores_r, det_category_r = det_net.build_whole_detection_network(input_img_batch=img_batch,
gtboxes_h_batch=None,
gtboxes_r_batch=None)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = det_net.get_restorer()
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')
for count, img_path in enumerate(file_paths):
start = timer()
img = cv2.imread(img_path)
box_res = []
label_res = []
score_res = []
box_res_rotate = []
label_res_rotate = []
score_res_rotate = []
imgH = img.shape[0]
imgW = img.shape[1]
if imgH < h_len:
temp = np.zeros([h_len, imgW, 3], np.float32)
temp[0:imgH, :, :] = img
img = temp
imgH = h_len
if imgW < w_len:
temp = np.zeros([imgH, w_len, 3], np.float32)
temp[:, 0:imgW, :] = img
img = temp
imgW = w_len
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), :]
det_boxes_h_, det_scores_h_, det_category_h_, \
det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[det_boxes_h, det_scores_h, det_category_h,
det_boxes_r, det_scores_r, det_category_r],
feed_dict={img_plac: src_img[:, :, ::-1]}
)
if len(det_boxes_h_) > 0:
for ii in range(len(det_boxes_h_)):
box = det_boxes_h_[ii]
box[0] = box[0] + ww_
box[1] = box[1] + hh_
box[2] = box[2] + ww_
box[3] = box[3] + hh_
box_res.append(box)
label_res.append(det_category_h_[ii])
score_res.append(det_scores_h_[ii])
if len(det_boxes_r_) > 0:
for ii in range(len(det_boxes_r_)):
box_rotate = det_boxes_r_[ii]
box_rotate[0] = box_rotate[0] + ww_
box_rotate[1] = box_rotate[1] + hh_
box_res_rotate.append(box_rotate)
label_res_rotate.append(det_category_r_[ii])
score_res_rotate.append(det_scores_r_[ii])
box_res = np.array(box_res)
label_res = np.array(label_res)
score_res = np.array(score_res)
box_res_rotate = np.array(box_res_rotate)
label_res_rotate = np.array(label_res_rotate)
score_res_rotate = np.array(score_res_rotate)
box_res_rotate_, label_res_rotate_, score_res_rotate_ = [], [], []
box_res_, label_res_, score_res_ = [], [], []
r_threshold = {
'roundabout': 0.1,
'tennis-court': 0.3,
'swimming-pool': 0.1,
'storage-tank': 0.2,
'soccer-ball-field': 0.3,
'small-vehicle': 0.2,
'ship': 0.05,
'plane': 0.3,
'large-vehicle': 0.1,
'helicopter': 0.2,
'harbor': 0.0001,
'ground-track-field': 0.3,
'bridge': 0.0001,
'basketball-court': 0.3,
'baseball-diamond': 0.3
}
h_threshold = {
'roundabout': 0.35,
'tennis-court': 0.35,
'swimming-pool': 0.4,
'storage-tank': 0.3,
'soccer-ball-field': 0.3,
'small-vehicle': 0.4,
'ship': 0.35,
'plane': 0.35,
'large-vehicle': 0.4,
'helicopter': 0.4,
'harbor': 0.3,
'ground-track-field': 0.4,
'bridge': 0.3,
'basketball-court': 0.4,
'baseball-diamond': 0.3
}
for sub_class in range(1, cfgs.CLASS_NUM + 1):
index = np.where(label_res_rotate == sub_class)[0]
if len(index) == 0:
continue
tmp_boxes_r = box_res_rotate[index]
tmp_label_r = label_res_rotate[index]
tmp_score_r = score_res_rotate[index]
tmp_boxes_r = np.array(tmp_boxes_r)
tmp = np.zeros(
[tmp_boxes_r.shape[0], tmp_boxes_r.shape[1] + 1])
tmp[:, 0:-1] = tmp_boxes_r
tmp[:, -1] = np.array(tmp_score_r)
try:
inx = nms_rotate.nms_rotate_cpu(
boxes=np.array(tmp_boxes_r),
scores=np.array(tmp_score_r),
iou_threshold=r_threshold[LABEl_NAME_MAP[sub_class]],
max_output_size=500)
except:
# Note: the IoU of two same rectangles is 0, which is calculated by rotate_gpu_nms
jitter = np.zeros(
[tmp_boxes_r.shape[0], tmp_boxes_r.shape[1] + 1])
jitter[:,
0] += np.random.rand(tmp_boxes_r.shape[0], ) / 1000
inx = rotate_gpu_nms(
np.array(tmp, np.float32) +
np.array(jitter, np.float32),
float(r_threshold[LABEl_NAME_MAP[sub_class]]), 0)
box_res_rotate_.extend(np.array(tmp_boxes_r)[inx])
score_res_rotate_.extend(np.array(tmp_score_r)[inx])
label_res_rotate_.extend(np.array(tmp_label_r)[inx])
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=h_threshold[LABEl_NAME_MAP[sub_class]],
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
if save_res:
det_detections_h = draw_box_in_img.draw_box_cv(
np.array(img, np.float32) - np.array(cfgs.PIXEL_MEAN),
boxes=np.array(box_res_),
labels=np.array(label_res_),
scores=np.array(score_res_))
det_detections_r = draw_box_in_img.draw_rotate_box_cv(
np.array(img, np.float32) - np.array(cfgs.PIXEL_MEAN),
boxes=np.array(box_res_rotate_),
labels=np.array(label_res_rotate_),
scores=np.array(score_res_rotate_))
save_dir = os.path.join(des_folder, cfgs.VERSION)
tools.mkdir(save_dir)
cv2.imwrite(
save_dir + '/' + img_path.split('/')[-1].split('.')[0] +
'_h.jpg', det_detections_h)
cv2.imwrite(
save_dir + '/' + img_path.split('/')[-1].split('.')[0] +
'_r.jpg', det_detections_r)
view_bar(
'{} cost {}s'.format(
img_path.split('/')[-1].split('.')[0], time_elapsed),
count + 1, len(file_paths))
else:
# eval txt
CLASS_DOTA = NAME_LABEL_MAP.keys()
# Task1
write_handle_r = {}
write_handle_h_ = {}
txt_dir_r = os.path.join('txt_output', cfgs.VERSION + '_r')
txt_dir_h_minAreaRect = os.path.join(
'txt_output', cfgs.VERSION + '_h_minAreaRect')
tools.mkdir(txt_dir_r)
tools.mkdir(txt_dir_h_minAreaRect)
for sub_class in CLASS_DOTA:
if sub_class == 'back_ground':
continue
write_handle_r[sub_class] = open(
os.path.join(txt_dir_r, 'Task1_%s.txt' % sub_class),
'a+')
write_handle_h_[sub_class] = open(
os.path.join(txt_dir_h_minAreaRect,
'Task2_%s.txt' % sub_class), 'a+')
rboxes = coordinate_convert.forward_convert(box_res_rotate_,
with_label=False)
for i, rbox in enumerate(rboxes):
command = '%s %.3f %.1f %.1f %.1f %.1f %.1f %.1f %.1f %.1f\n' % (
img_path.split('/')[-1].split('.')[0],
score_res_rotate_[i],
rbox[0],
rbox[1],
rbox[2],
rbox[3],
rbox[4],
rbox[5],
rbox[6],
rbox[7],
)
command_ = '%s %.3f %.1f %.1f %.1f %.1f\n' % (
img_path.split('/')[-1].split('.')[0],
score_res_rotate_[i], min(rbox[::2]), min(
rbox[1::2]), max(rbox[::2]), max(rbox[1::2]))
write_handle_r[LABEl_NAME_MAP[label_res_rotate_[i]]].write(
command)
write_handle_h_[LABEl_NAME_MAP[
label_res_rotate_[i]]].write(command_)
for sub_class in CLASS_DOTA:
if sub_class == 'back_ground':
continue
write_handle_r[sub_class].close()
# Task2
write_handle_h = {}
txt_dir_h = os.path.join('txt_output', cfgs.VERSION + '_h')
tools.mkdir(txt_dir_h)
for sub_class in CLASS_DOTA:
if sub_class == 'back_ground':
continue
write_handle_h[sub_class] = open(
os.path.join(txt_dir_h, 'Task2_%s.txt' % sub_class),
'a+')
for i, hbox in enumerate(box_res_):
command = '%s %.3f %.1f %.1f %.1f %.1f\n' % (
img_path.split('/')[-1].split('.')[0], score_res_[i],
hbox[0], hbox[1], hbox[2], hbox[3])
write_handle_h[LABEl_NAME_MAP[label_res_[i]]].write(
command)
for sub_class in CLASS_DOTA:
if sub_class == 'back_ground':
continue
write_handle_h[sub_class].close()
view_bar(
'{} cost {}s'.format(
img_path.split('/')[-1].split('.')[0], time_elapsed),
count + 1, len(file_paths))
def inference(det_net, cap):
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3])
img_batch = tf.cast(img_plac, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(
img_tensor=img_batch,
target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN,
is_resize=False)
det_boxes_h, det_scores_h, det_category_h, \
det_boxes_r, det_scores_r, det_category_r = det_net.build_whole_detection_network(input_img_batch=img_batch,
gtboxes_h_batch=None,
gtboxes_r_batch=None)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = det_net.get_restorer()
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')
fourcc = cv2.VideoWriter_fourcc(*'xvid')
out = cv2.VideoWriter('./camera_demo.avi', fourcc, 10, (640, 480))
ret, frame = cap.read()
while ret:
ret, frame = cap.read()
start = time.time()
resized_img, det_boxes_h_, det_scores_h_, det_category_h_, \
det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[img_batch, det_boxes_h, det_scores_h, det_category_h, det_boxes_r, det_scores_r, det_category_r],
feed_dict={img_plac: frame}
)
end = time.time()
# det_detections_h = draw_box_in_img.draw_box_cv(np.squeeze(resized_img, 0),
# boxes=det_boxes_h_,
# labels=det_category_h_,
# scores=det_scores_h_)
det_detections_r = draw_box_in_img.draw_rotate_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_r_,
labels=det_category_r_,
scores=det_scores_r_)
# det_detections_h = cv2.resize(det_detections_h,
# (det_detections_h.shape[0] // 2, det_detections_h.shape[1] // 2))
# cv2.putText(det_detections_h,
# text="horizon bbox",
# org=(0, 0),
# fontFace=3,
# fontScale=1,
# color=(255, 0, 0))
# det_detections_r = cv2.resize(det_detections_r,
# (det_detections_r.shape[0] // 2, det_detections_r.shape[1] // 2))
cv2.putText(det_detections_r,
text="rotated bbox--%3.2f" % (1 / (end - start)),
org=(0, 10),
fontFace=1,
fontScale=1,
color=(0, 255, 0))
out.write(det_detections_r)
# hmerge = np.hstack((det_detections_h, det_detections_r)) # 水平拼接
cv2.imshow("faceDetection", det_detections_r)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
out.release()
cv2.destroyAllWindows()
def eval_with_plac(img_dir, det_net, image_ext, draw_imgs=False):
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None,
3]) # is RGB. not GBR
img_batch = tf.cast(img_plac, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(
img_tensor=img_batch,
target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN,
is_resize=False)
det_boxes_r, det_scores_r, det_category_r = det_net.build_whole_detection_network(
input_img_batch=img_batch, gtboxes_h_batch=None, gtboxes_r_batch=None)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = det_net.get_restorer()
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_h = []
all_boxes_r = []
imgs = os.listdir(img_dir)
for i, a_img_name in enumerate(imgs):
a_img_name = a_img_name.split(image_ext)[0]
recs = {}
recs[a_img_name] = parse_rec(
os.path.join(test_annotation_path, a_img_name + '.xml'))
#R = [obj for obj in recs[a_img_name]]
bbox = np.squeeze(np.array([x['bbox'] for x in recs[a_img_name]]))
#labels = bbox[:, -1]
if len(bbox.shape) == 1:
bbox = np.expand_dims(bbox, axis=0)
labels = bbox[:, -1]
raw_img = cv2.imread(os.path.join(img_dir, a_img_name + image_ext))
raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
start = time.time()
resized_img, \
det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[img_batch,
det_boxes_r, det_scores_r, det_category_r],
feed_dict={img_plac: raw_img}
)
end = time.time()
det_boxes_r_ = det_boxes_r_[det_scores_r_ >= 0.4]
det_category_r_ = det_category_r_[det_scores_r_ >= 0.4]
det_scores_r_ = det_scores_r_[det_scores_r_ >= 0.4]
keep = nms_rotate.nms_rotate_cpu(det_boxes_r_, det_scores_r_, 0.3,
20)
det_boxes_r_ = det_boxes_r_[keep]
det_scores_r_ = det_scores_r_[keep]
det_category_r_ = det_category_r_[keep]
##### box_ratio > 2 or < 1/2
index = (det_boxes_r_[:, 2] / det_boxes_r_[:, 3] >
2) | (det_boxes_r_[:, 2] / det_boxes_r_[:, 3] <= 0.5)
det_boxes_r_ = det_boxes_r_[index]
det_scores_r_ = det_scores_r_[index]
det_category_r_ = det_category_r_[index]
# print("{} cost time : {} ".format(img_name, (end - start)))
if draw_imgs:
det_detections_h = draw_box_in_img.draw_rotate_box_cv1(
np.squeeze(resized_img, 0),
boxes=bbox,
labels=labels,
scores=np.ones(bbox.shape[0]))
det_detections_r = draw_box_in_img.draw_rotate_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_r_,
labels=det_category_r_,
scores=det_scores_r_)
save_dir = os.path.join(cfgs.TEST_SAVE_PATH, cfgs.VERSION)
tools.mkdir(save_dir)
cv2.imwrite(save_dir + '/' + a_img_name + '_h.jpg',
det_detections_h[:, :, ::-1])
cv2.imwrite(save_dir + '/' + a_img_name + '_r.jpg',
det_detections_r[:, :, ::-1])
# xmin, ymin, xmax, ymax = det_boxes_h_[:, 0], det_boxes_h_[:, 1], \
# det_boxes_h_[:, 2], det_boxes_h_[:, 3]
if det_boxes_r_.shape[0] != 0:
resized_h, resized_w = resized_img.shape[1], resized_img.shape[
2]
det_boxes_r_ = forward_convert(det_boxes_r_, False)
det_boxes_r_[:, 0::2] *= (raw_w / resized_w)
det_boxes_r_[:, 1::2] *= (raw_h / resized_h)
det_boxes_r_ = back_forward_convert(det_boxes_r_, False)
x_c, y_c, w, h, theta = det_boxes_r_[:, 0], det_boxes_r_[:, 1], det_boxes_r_[:, 2], \
det_boxes_r_[:, 3], det_boxes_r_[:, 4]
# 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_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((det_category_h_.reshape(-1, 1),
# det_scores_h_.reshape(-1, 1),
# boxes_h))
dets_r = np.hstack((det_category_r_.reshape(-1, 1),
det_scores_r_.reshape(-1, 1), boxes_r))
# all_boxes_h.append(dets_h)
all_boxes_r.append(dets_r)
tools.view_bar(
'{} image cost {}s'.format(a_img_name, (end - start)), i + 1,
len(imgs))
fw1 = open(cfgs.VERSION + '_detections_h.pkl', 'w')
fw2 = open(cfgs.VERSION + '_detections_r.pkl', 'w')
pickle.dump(all_boxes_h, fw1)
pickle.dump(all_boxes_r, fw2)
def eval_with_plac(img_dir, det_net, num_imgs, image_ext, draw_imgs=False):
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3]) # is RGB. not GBR
img_batch = tf.cast(img_plac, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(img_tensor=img_batch,
target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN,
is_resize=False)
det_boxes_h, det_scores_h, det_category_h, \
det_boxes_r, det_scores_r, det_category_r = det_net.build_whole_detection_network(
input_img_batch=img_batch,
gtboxes_h_batch=None, gtboxes_r_batch=None)
init_op = tf.group(
tf.global_variables_initializer(),
tf.local_variables_initializer()
)
restorer, restore_ckpt = det_net.get_restorer()
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_r = []
imgs = os.listdir(img_dir)
for i, a_img_name in enumerate(imgs):
a_img_name = a_img_name.split(image_ext)[0]
raw_img = cv2.imread(os.path.join(img_dir,
a_img_name + image_ext))
raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
start = time.time()
resized_img, det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[img_batch, det_boxes_h, det_scores_h, det_category_h,
det_boxes_r, det_scores_r, det_category_r],
feed_dict={img_plac: raw_img}
)
end = time.time()
# print("{} cost time : {} ".format(img_name, (end - start)))
if draw_imgs:
det_detections_r = draw_box_in_img.draw_rotate_box_cv(np.squeeze(resized_img, 0),
boxes=det_boxes_r_,
labels=det_category_r_,
scores=det_scores_r_)
save_dir = os.path.join(cfgs.TEST_SAVE_PATH, cfgs.VERSION)
tools.mkdir(save_dir)
cv2.imwrite(save_dir + '/' + a_img_name + '_r.jpg',
det_detections_r[:, :, ::-1])
resized_h, resized_w = resized_img.shape[1], resized_img.shape[2]
det_boxes_r_ = forward_convert(det_boxes_r_, False)
det_boxes_r_[:, 0::2] *= (raw_w / resized_w)
det_boxes_r_[:, 1::2] *= (raw_h / resized_h)
det_boxes_r_ = back_forward_convert(det_boxes_r_, False)
x_c, y_c, w, h, theta = det_boxes_r_[:, 0], det_boxes_r_[:, 1], det_boxes_r_[:, 2], \
det_boxes_r_[:, 3], det_boxes_r_[:, 4]
boxes_r = np.transpose(np.stack([x_c, y_c, w, h, theta]))
dets_r = np.hstack((det_category_r_.reshape(-1, 1),
det_scores_r_.reshape(-1, 1),
boxes_r))
all_boxes_r.append(dets_r)
tools.view_bar('{} image cost {}s'.format(a_img_name, (end - start)), i + 1, len(imgs))
fw2 = open(cfgs.VERSION + '_detections_r.pkl', 'w')
pickle.dump(all_boxes_r, fw2)
def inference(det_net, data_dir):
TIME = 0
TIME_NUM = 0
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3])
img_batch = tf.cast(img_plac, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(
img_tensor=img_batch,
target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN,
is_resize=IS_RESIZE)
det_boxes_h, det_scores_h, det_category_h, \
det_boxes_r, det_scores_r, det_category_r = det_net.build_whole_detection_network(input_img_batch=img_batch,
gtboxes_h_batch=None,
gtboxes_r_batch=None)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = det_net.get_restorer()
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')
imgs = os.listdir(data_dir)
# print(imgs)
for i, a_img_name in enumerate(imgs):
file_text, extension = os.path.splitext(a_img_name)
if extension != ".jpg" and extension != ".tif" and extension != ".png":
continue
# f = open('./res_icdar_r/res_{}.txt'.format(a_img_name.split('.jpg')[0]), 'w')
raw_img = cv2.imread(os.path.join(data_dir, a_img_name))
# raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
start = time.time()
resized_img, det_boxes_h_, det_scores_h_, det_category_h_, \
det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[img_batch, det_boxes_h, det_scores_h, det_category_h,
det_boxes_r, det_scores_r, det_category_r],
feed_dict={img_plac: raw_img}
)
end = time.time()
TIME += end - start
TIME_NUM += 1
if WRITE_VOC == True:
boxes = np.array(det_boxes_r_, np.int64)
scores = np.array(det_scores_r_, np.float32)
labels = np.array(det_category_r_, np.int32)
det_save_dir = cfgs.INFERENCE_SAVE_PATH
write_voc_results_file(boxes, labels, scores,
a_img_name.split('.')[0], det_save_dir)
write_pixel_results(boxes, labels, scores,
a_img_name.split('.')[0], det_save_dir)
det_detections_h = draw_box_in_img.draw_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_h_,
labels=det_category_h_,
scores=det_scores_h_)
det_detections_r = draw_box_in_img.draw_rotate_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_r_,
labels=det_category_r_,
scores=det_scores_r_)
save_dir = os.path.join(cfgs.INFERENCE_SAVE_PATH, cfgs.VERSION)
tools.mkdir(save_dir)
if OUTPUT_H_IMG:
cv2.imwrite(save_dir + '/' + a_img_name + '_h.jpg',
det_detections_h)
cv2.imwrite(save_dir + '/' + a_img_name + '_r.jpg',
det_detections_r)
view_bar('{} cost {}s'.format(a_img_name, (end - start)), i + 1,
len(imgs))
print('avg time:{}'.format(TIME / TIME_NUM))
def inference(det_net, device_index):
# preprocessing data
img_placeholder = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3])
img_batch = tf.cast(img_placeholder, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(
img_tensor=img_batch,
target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN,
is_resize=False)
# img_batch: [1, h, w, c]
det_boxes_h, det_scores_h, det_category_h, \
det_boxes_r, det_scores_r, det_category_r = det_net.build_whole_detection_network(input_img_batch=img_batch,
gtboxes_r_batch=None,
gtboxes_h_batch=None)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
restorer, restore_ckpt = det_net.get_restorer()
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')
cap = cv2.VideoCapture(device_index)
fps = cap.get(cv2.CAP_PROP_FPS)
# size = (width, height)
size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
tmp_directory = current_directory + "/../tmp"
if not os.path.exists(tmp_directory):
os.makedirs(tmp_directory)
# Define the codec and create VideoWriter object
fourcc = cv2.VideoWriter_fourcc(*'XVID')
video_writer = cv2.VideoWriter(
'%s/OBB_camera_face.avi' % (tmp_directory), fourcc, fps, size)
cv2.namedWindow("Press q on keyboard to exit.", cv2.WINDOW_NORMAL)
while (cap.isOpened()):
# Capture frame-by-frame
ret, frame = cap.read()
if True != ret:
break
start = time.time()
# print("tf.shape(frame):", sess.run(tf.shape(frame))) # tf.shape(frame): [480 640 3]
resized_img, det_boxes_h_, det_scores_h_, det_category_h_, det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[img_batch, det_boxes_h, det_scores_h, det_category_h, det_boxes_r, det_scores_r, det_category_r],
feed_dict={img_placeholder: frame})
# feed_dict={img_placeholder: frame} Color image loaded by OpenCV is in BGR mode.
# feed_dict={img_plac: frame[:, :, ::-1]} BGR mode -> RGB mode.
end = time.time()
# print("resized_img.shape:", resized_img.shape)
det_detections_h = draw_box_in_img.draw_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_h_,
labels=det_category_h_,
scores=det_scores_h_)
det_detections_r = draw_box_in_img.draw_rotate_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_r_,
labels=det_category_r_,
scores=det_scores_r_)
# height, width, number of channels in image
# height = image.shape[0], width = image.shape[1], channels = image.shape[2]
det_detections_h = cv2.resize(det_detections_h,
(det_detections_h.shape[1] // 2,
det_detections_h.shape[0] // 2))
cv2.putText(det_detections_h,
text="HBB - %3.2fps" % (1 / (end - start)),
org=(10, 10),
fontFace=1,
fontScale=1,
color=(0, 255, 0))
det_detections_r = cv2.resize(det_detections_r,
(det_detections_r.shape[1] // 2,
det_detections_r.shape[0] // 2))
cv2.putText(det_detections_r,
text="OBB - %3.2fps" % (1.0 / (end - start)),
org=(10, 10),
fontFace=1,
fontScale=1,
color=(0, 255, 0))
# Stack arrays in sequence horizontally (column wise).
hstack_data = np.hstack((det_detections_h, det_detections_r))
video_writer.write(frame)
# Display the resulting frame
cv2.imshow("Press q on keyboard to exit.", hstack_data)
# Press q on keyboard to exit.
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# When everything done, release the capture.
cap.release()
video_writer.release()
cv2.destroyAllWindows()
def eval_with_plac(img_dir, det_net, num_imgs, image_ext, draw_imgs,
test_annotation_path):
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None,
3]) # is RGB. not GBR
img_batch = tf.cast(img_plac, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(
img_tensor=img_batch,
target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN,
is_resize=False)
det_boxes_h, det_scores_h, det_category_h, \
det_boxes_r, det_scores_r, det_category_r = det_net.build_whole_detection_network(
input_img_batch=img_batch,
gtboxes_h_batch=None, gtboxes_r_batch=None)
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
global_step_tensor = slim.get_or_create_global_step()
eval_result = []
last_checkpoint_name = None
while True:
restorer, restore_ckpt = det_net.get_restorer()
#saver = tf.train.Saver(max_to_keep=10)
start_time = time.time()
model_path = os.path.splitext(os.path.basename(restore_ckpt))[0]
if model_path == None:
print("Wait for available checkpoint")
elif last_checkpoint_name == model_path:
print(
"Already evaluated checkpoint {}, we will try evaluation in {} seconds"
.format(model_path, EVAL_INTERVAL))
#continue
else:
print('Last ckpt was {}, new ckpt is {}'.format(
last_checkpoint_name, model_path))
last_checkpoint_name = model_path
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
sess.run(init_op)
sess.run(global_step_tensor.initializer)
if not restorer is None:
restorer.restore(sess, restore_ckpt)
print('restore model', restore_ckpt)
global_stepnp = tf.train.global_step(sess, global_step_tensor)
print('#########################', global_stepnp)
all_boxes_h = []
all_boxes_r = []
imgs = os.listdir(img_dir)
imgs_len = len(imgs)
none_detected_image = []
for i, a_img_name in enumerate(imgs[:]):
a_img_name = a_img_name.split(image_ext)[0]
image_name = a_img_name + image_ext
print('\n', a_img_name)
raw_img = cv2.imread(
os.path.join(img_dir, a_img_name + image_ext))
raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
start = time.time()
resized_img, det_boxes_h_, det_scores_h_, det_category_h_, \
det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[img_batch, det_boxes_h, det_scores_h, det_category_h,
det_boxes_r, det_scores_r, det_category_r],
feed_dict={img_plac: raw_img}
)
end = time.time()
print("det category H : ", det_category_h_)
print("det category R : ", det_category_r_)
# print("{} cost time : {} ".format(img_name, (end - start)))
if draw_imgs:
det_detections_h = draw_box_in_img.draw_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_h_,
labels=det_category_h_,
scores=det_scores_h_)
det_detections_r = draw_box_in_img.draw_rotate_box_cv(
np.squeeze(resized_img, 0),
boxes=det_boxes_r_,
labels=det_category_r_,
scores=det_scores_r_)
save_dir = os.path.join(cfgs.TEST_SAVE_PATH,
cfgs.VERSION)
tools.mkdir(save_dir)
cv2.imwrite(save_dir + '/' + a_img_name + '_h.jpg',
det_detections_h[:, :, ::-1])
cv2.imwrite(save_dir + '/' + a_img_name + '_r.jpg',
det_detections_r[:, :, ::-1])
xmin, ymin, xmax, ymax = det_boxes_h_[:, 0], det_boxes_h_[:, 1], \
det_boxes_h_[:, 2], det_boxes_h_[:, 3]
if det_boxes_r_.shape[0] != 0:
#print('### Has box ###')
resized_h, resized_w = resized_img.shape[
1], resized_img.shape[2]
det_boxes_r_ = forward_convert(det_boxes_r_, False)
det_boxes_r_[:, 0::2] *= (raw_w / resized_w)
det_boxes_r_[:, 1::2] *= (raw_h / resized_h)
det_boxes_r_ = back_forward_convert(
det_boxes_r_, False)
x_c, y_c, w, h, theta = det_boxes_r_[:, 0], det_boxes_r_[:, 1], det_boxes_r_[:, 2], \
det_boxes_r_[:, 3], det_boxes_r_[:, 4]
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_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((det_category_h_.reshape(-1, 1),
det_scores_h_.reshape(-1,
1), boxes_h))
dets_r = np.hstack((det_category_r_.reshape(-1, 1),
det_scores_r_.reshape(-1,
1), boxes_r))
all_boxes_h.append(dets_h)
all_boxes_r.append(dets_r)
else:
imgs.remove(image_name)
none_detected_image.append(image_name)
print('No detected')
tools.view_bar(
'{} image cost {}s'.format(a_img_name, (end - start)),
i + 1, imgs_len)
fw1 = open(cfgs.VERSION + '_detections_h.pkl', 'wb')
fw2 = open(cfgs.VERSION + '_detections_r.pkl', 'wb')
pickle.dump(all_boxes_h, fw1)
pickle.dump(all_boxes_r, fw2)
# with open(cfgs.VERSION + '_detections_h.pkl', 'rb') as f1:
# all_boxes_h = pickle.load(f1, encoding='unicode')
# print(10 * "###")
# print(len(all_boxes_h))
#
# with open(cfgs.VERSION + '_detections_r.pkl', 'rb') as f2:
# all_boxes_r = pickle.load(f2, encoding='unicode')
#
# print(len(all_boxes_r))
# imgs = os.listdir(img_dir)
real_test_imgname_list = [i.split(image_ext)[0] for i in imgs]
print(10 * "**")
print('horizon eval:')
# print(len(all_boxes_h), len(all_boxes_r))
# print(len(real_test_imgname_list))
mAP_h, recall_h, precision_h, total_mAP_h, total_recall_h, total_precision_h = voc_eval.voc_evaluate_detections(
all_boxes=all_boxes_h,
test_imgid_list=real_test_imgname_list,
test_annotation_path=test_annotation_path)
print('mAP_h: ', mAP_h)
print('mRecall_h:', recall_h)
print('mPrecision_h:', precision_h)
print('total_mAP_h: ', total_mAP_h)
print('total_recall_h_list:', total_recall_h)
print('total_precision_h_list:', total_precision_h)
print(10 * "**")
print('rotation eval:')
mAP_r, recall_r, precision_r, total_mAP_r, total_recall_r, total_precision_r = voc_eval_r.voc_evaluate_detections(
all_boxes=all_boxes_r,
test_imgid_list=real_test_imgname_list,
test_annotation_path=test_annotation_path)
f1score_h_check = (1 + 1**2) * precision_h * recall_h / (
1**2 * precision_h + recall_h)
f1score_h = calc_fscore(precision_h, recall_h, 1)
f1score_r_check = (1 + 1**2) * precision_r * recall_r / (
1**2 * precision_r + recall_r)
f1score_r = calc_fscore(precision_r, recall_r, 1)
print(10 * '##')
print('mAP_r:', mAP_r)
print('mRecall_r:', recall_r)
print('mPrecision_r:', precision_r)
print('total_mAP_r_list: ', total_mAP_r)
print('total_recall_r_list:', total_recall_r)
print('total_precision_r_list:', total_precision_r)
print('f1score_r:', f1score_r)
summary_path = os.path.join(cfgs.SUMMARY_PATH,
cfgs.VERSION + '/eval_0')
tools.mkdir(summary_path)
summary_writer = tf.summary.FileWriter(summary_path,
graph=sess.graph)
mAP_h_summ = tf.Summary()
mAP_h_summ.value.add(tag='EVAL_Global/mAP_h',
simple_value=mAP_h)
summary_writer.add_summary(mAP_h_summ, global_stepnp)
mAP_r_summ = tf.Summary()
mAP_r_summ.value.add(tag='EVAL_Global/mAP_r',
simple_value=mAP_r)
summary_writer.add_summary(mAP_r_summ, global_stepnp)
mRecall_h_summ = tf.Summary()
mRecall_h_summ.value.add(tag='EVAL_Global/Recall_h',
simple_value=recall_h)
summary_writer.add_summary(mRecall_h_summ, global_stepnp)
mRecall_r_summ = tf.Summary()
mRecall_r_summ.value.add(tag='EVAL_Global/Recall_r',
simple_value=recall_r)
summary_writer.add_summary(mRecall_r_summ, global_stepnp)
mPrecision_h_summ = tf.Summary()
mPrecision_h_summ.value.add(tag='EVAL_Global/Precision_h',
simple_value=precision_h)
summary_writer.add_summary(mPrecision_h_summ, global_stepnp)
mPrecision_r_summ = tf.Summary()
mPrecision_r_summ.value.add(tag='EVAL_Global/Precision_r',
simple_value=precision_r)
summary_writer.add_summary(mPrecision_r_summ, global_stepnp)
mF1Score_h_summ = tf.Summary()
mF1Score_h_summ.value.add(tag='EVAL_Global/F1Score_h',
simple_value=f1score_h)
summary_writer.add_summary(mF1Score_h_summ, global_stepnp)
mF1Score_r_summ = tf.Summary()
mF1Score_r_summ.value.add(tag='EVAL_Global/F1Score_r',
simple_value=f1score_r)
summary_writer.add_summary(mF1Score_r_summ, global_stepnp)
mAP_h_class_dict = {}
mAP_r_class_dict = {}
recall_h_class_dict = {}
recall_r_class_dict = {}
precision_h_class_dict = {}
precision_r_class_dict = {}
f1score_h_class_dict = {}
f1score_r_class_dict = {}
label_list = list(NAME_LABEL_MAP.keys())
label_list.remove('back_ground')
for cls in label_list:
mAP_h_class_dict["cls_%s_mAP_h_summ" % cls] = tf.Summary()
mAP_r_class_dict["cls_%s_mAP_r_summ" % cls] = tf.Summary()
recall_h_class_dict["cls_%s_recall_h_summ" %
cls] = tf.Summary()
recall_r_class_dict["cls_%s_recall_r_summ" %
cls] = tf.Summary()
precision_h_class_dict["cls_%s_precision_h_summ" %
cls] = tf.Summary()
precision_r_class_dict["cls_%s_precision_r_summ" %
cls] = tf.Summary()
f1score_h_class_dict["cls_%s_f1score_h_summ" %
cls] = tf.Summary()
f1score_r_class_dict["cls_%s_f1score_r_summ" %
cls] = tf.Summary()
for cls in label_list:
mAP_h_class_dict["cls_%s_mAP_h_summ" % cls].value.add(
tag='EVAL_Class_mAP/{}_mAP_h'.format(cls),
simple_value=total_mAP_h[cls])
mAP_r_class_dict["cls_%s_mAP_r_summ" % cls].value.add(
tag='EVAL_Class_mAP/{}_mAP_r'.format(cls),
simple_value=total_mAP_r[cls])
recall_h_class_dict[
"cls_%s_recall_h_summ" % cls].value.add(
tag='EVAL_Class_recall/{}_recall_h'.format(cls),
simple_value=total_recall_h[cls])
recall_r_class_dict[
"cls_%s_recall_r_summ" % cls].value.add(
tag='EVAL_Class_recall/{}_recall_r'.format(cls),
simple_value=total_recall_r[cls])
precision_h_class_dict[
"cls_%s_precision_h_summ" % cls].value.add(
tag='EVAL_Class_precision/{}_precision_h'.format(
cls),
simple_value=total_precision_h[cls])
precision_r_class_dict[
"cls_%s_precision_r_summ" % cls].value.add(
tag='EVAL_Class_precision/{}_precision_r'.format(
cls),
simple_value=total_precision_r[cls])
f1score_h_cls = calc_fscore(total_precision_h[cls],
total_recall_h[cls], 1)
f1score_r_cls = calc_fscore(total_precision_r[cls],
total_recall_r[cls], 1)
f1score_h_class_dict[
"cls_%s_f1score_h_summ" % cls].value.add(
tag='EVAL_Class_f1score/{}_f1score_h'.format(cls),
simple_value=f1score_h_cls)
f1score_r_class_dict[
"cls_%s_f1score_r_summ" % cls].value.add(
tag='EVAL_Class_f1score/{}_f1score_r'.format(cls),
simple_value=f1score_r_cls)
for cls in label_list:
summary_writer.add_summary(
mAP_h_class_dict["cls_%s_mAP_h_summ" % cls],
global_stepnp)
summary_writer.add_summary(
mAP_r_class_dict["cls_%s_mAP_r_summ" % cls],
global_stepnp)
summary_writer.add_summary(
recall_h_class_dict["cls_%s_recall_h_summ" % cls],
global_stepnp)
summary_writer.add_summary(
recall_r_class_dict["cls_%s_recall_r_summ" % cls],
global_stepnp)
summary_writer.add_summary(
precision_h_class_dict["cls_%s_precision_h_summ" %
cls], global_stepnp)
summary_writer.add_summary(
precision_r_class_dict["cls_%s_precision_r_summ" %
cls], global_stepnp)
summary_writer.add_summary(
f1score_h_class_dict["cls_%s_f1score_h_summ" % cls],
global_stepnp)
summary_writer.add_summary(
f1score_r_class_dict["cls_%s_f1score_r_summ" % cls],
global_stepnp)
summary_writer.flush()
if not os.path.exists(save_dir):
os.makedirs(save_dir)
save_ckpt = os.path.join(save_dir,
'voc_' + str(global_stepnp) + 'model.ckpt')
#saver.save(sess, save_ckpt)
print(' weights had been saved')
time_to_next_eval = start_time + EVAL_INTERVAL - time.time()
if time_to_next_eval > 0:
time.sleep(time_to_next_eval)
def inference(det_net, data_dir):
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3])
img_batch = tf.cast(img_plac, tf.float32)
img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN)
img_batch = short_side_resize_for_inference_data(img_tensor=img_batch,
target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN)
rois, roi_scores, det_boxes_h, det_scores_h, det_category_h, \
all_boxes_r, all_scores_r, all_category_r = det_net.build_whole_detection_network(input_img_batch=img_batch,
gtboxes_h_batch=None,
gtboxes_r_batch=None)
init_op = tf.group(
tf.global_variables_initializer(),
tf.local_variables_initializer()
)
restorer, restore_ckpt = det_net.get_restorer()
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')
imgs = os.listdir(data_dir)
for i, a_img_name in enumerate(imgs):
raw_img = cv2.imread(os.path.join(data_dir,
a_img_name))
# raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
start = time.time()
resized_img, rois_, roi_scores_, det_boxes_h_, det_scores_h_, det_category_h_, \
all_boxes_r_, all_scores_r_, all_category_r_ = \
sess.run(
[img_batch, rois, roi_scores, det_boxes_h, det_scores_h, det_category_h,
all_boxes_r, all_scores_r, all_category_r],
feed_dict={img_plac: raw_img}
)
end = time.time()
print('all rois shape:', rois_.shape)
all_boxes_new = all_boxes_r_ # [-1, 5]
all_scores_new = all_scores_r_ # [-1]
all_category_new = all_category_r_ # [-1]
print('all dets shape:', all_boxes_new.shape)
# draw all rois from proposals
#rois_img_all = mylibs.draw_rois_scores(np.squeeze(resized_img, 0), rois_, roi_scores_)
#score_gre_05 = np.reshape(np.where(np.greater_equal(roi_scores_, 0.5)), -1)
#score_gre_05_rois = rois_[score_gre_05]
#score_gre_05_scores = roi_scores_[score_gre_05]
#rois_img_part = mylibs.draw_rois_scores(np.squeeze(resized_img, 0), score_gre_05_rois, score_gre_05_scores)
# draw all 800 detection boxes
all_indices = np.reshape(np.where(np.greater_equal(all_scores_new, cfgs.SHOW_SCORE_THRSHOLD)), -1)
left_boxes = all_boxes_new[all_indices]
left_scores = all_scores_new[all_indices]
left_category = all_category_new[all_indices]
#print('greater than score shape:', left_boxes.shape)
detection_r = draw_box_in_img.draw_rotate_box_cv(np.squeeze(resized_img, 0),
boxes=left_boxes,
labels=left_category,
scores=left_scores,
imgname=a_img_name)
"""
while True:
# nms
keep = mylibs.nmsRotate(all_boxes_new, all_scores_new,
cfgs.FAST_RCNN_NMS_IOU_THRESHOLD, cfgs.FAST_RCNN_NMS_MAX_BOXES_PER_CLASS)
final_boxes = all_boxes_new[keep]
final_scores = all_scores_new[keep]
final_category = all_category_new[keep]
kept_indices = np.reshape(np.where(np.greater_equal(final_scores, cfgs.SHOW_SCORE_THRSHOLD)), -1)
det_boxes_new = final_boxes[kept_indices]
det_scores_new = final_scores[kept_indices]
det_category_new = final_category[kept_indices]
# detected boxes
contours, angles = mylibs.draw_rotate_box_cv_my(det_boxes_new, det_category_new)
dtbox = mylibs.getRboxDegree(contours, angles) # n
#print('dtbox shape is', dtbox.shape)
fuv, features = mylibs.geneTestImageFeats(dtbox) # n-2
if fuv.shape[0] == 0:
print(a_img_name, 'left none bones')
break
dtbox_idx = mylibs.svmPred(fuv, features) # deleted bones index
#print('dtbox_idx shape is', dtbox_idx.shape)
contour_idx = np.reshape(dtbox[dtbox_idx][:, -1], -1).astype(np.int32)
kept_idx = kept_indices[contour_idx]
keep_index = keep[kept_idx]
#print('keep_index shape is', keep_index.shape)
#n = det_boxes_new.shape[0]
if len(dtbox_idx) == 0: # no svm deleted bones
break
else:
# delete some rows
all_boxes_new = np.delete(all_boxes_new, keep_index, axis=0)
all_scores_new = np.delete(all_scores_new, keep_index, axis=0)
all_category_new = np.delete(all_category_new, keep_index, axis=0)
# unsorted
fcontours = contours
fangles = angles
fscores = det_scores_new
"""
"""
# save contours and angles to showSVMdecision scores
detection_r = draw_box_in_img.draw_rotate_box_cv(np.squeeze(resized_img, 0),
boxes=det_boxes_new,
labels=det_category_new,
scores=det_scores_new,
imgname=a_img_name)
"""
"""
# final_dtbox[i, :] = [x0, y0, x1, y1, x2, y2, x3, y3, dg, ycenter, from_idx]
final_dtbox = mylibs.getRboxDegree(fcontours, fangles)
dt_idx = final_dtbox[:, -1].astype(np.int32) # sorted
# sorted
fcontours = fcontours[dt_idx]
fangles = fangles[dt_idx]
fscores = fscores[dt_idx]
img, tcontours, tangles = mylibs.draw_contour_box(np.squeeze(resized_img, 0), fcontours, fangles, fscores)
t_dtbox = mylibs.getRboxDegree(tcontours, tangles)
cobb_img = mylibs.getCobb(t_dtbox, img)
"""
save_dir = os.path.join(cfgs.INFERENCE_SAVE_PATH, cfgs.VERSION)
tools.mkdir(save_dir)
cv2.imwrite(save_dir + '/' + a_img_name + '_roi.jpg',
detection_r)
view_bar('{} cost {}s'.format(a_img_name, (end - start)), i + 1, len(imgs))
print()
