def parse_rec(self, filename):
""" Parse a PASCAL VOC xml file """
tree = ET.parse(filename)
objects = []
for obj in tree.findall('object'):
obj_struct = {}
obj_struct['name'] = obj.find('name').text
# obj_struct['pose'] = obj.find('pose').text
# obj_struct['truncated'] = int(obj.find('truncated').text)
# obj_struct['difficult'] = int(obj.find('difficult').text)
obj_struct['difficult'] = 0
bbox = obj.find('bndbox')
rbox = [
eval(bbox.find('x1').text),
eval(bbox.find('y1').text),
eval(bbox.find('x2').text),
eval(bbox.find('y2').text),
eval(bbox.find('x3').text),
eval(bbox.find('y3').text),
eval(bbox.find('x4').text),
eval(bbox.find('y4').text)
]
rbox = np.array([rbox], np.float32)
rbox = coordinate_convert.backward_convert(rbox, with_label=False)
obj_struct['bbox'] = rbox
objects.append(obj_struct)
return objects
def clip_image(file_idx, image, boxes_all, width, height, stride_w, stride_h):
min_pixel = 5
print(file_idx)
boxes_all_5 = backward_convert(boxes_all[:, :8], False)
print(boxes_all[np.logical_or(boxes_all_5[:, 2] <= min_pixel, boxes_all_5[:, 3] <= min_pixel), :])
boxes_all = boxes_all[np.logical_and(boxes_all_5[:, 2] > min_pixel, boxes_all_5[:, 3] > min_pixel), :]
if boxes_all.shape[0] > 0:
shape = image.shape
for start_h in range(0, shape[0], stride_h):
for start_w in range(0, shape[1], stride_w):
boxes = copy.deepcopy(boxes_all)
box = np.zeros_like(boxes_all)
start_h_new = start_h
start_w_new = start_w
if start_h + height > shape[0]:
start_h_new = shape[0] - height
if start_w + width > shape[1]:
start_w_new = shape[1] - width
top_left_row = max(start_h_new, 0)
top_left_col = max(start_w_new, 0)
bottom_right_row = min(start_h + height, shape[0])
bottom_right_col = min(start_w + width, shape[1])
subImage = image[top_left_row:bottom_right_row, top_left_col: bottom_right_col]
box[:, 0] = boxes[:, 0] - top_left_col
box[:, 2] = boxes[:, 2] - top_left_col
box[:, 4] = boxes[:, 4] - top_left_col
box[:, 6] = boxes[:, 6] - top_left_col
box[:, 1] = boxes[:, 1] - top_left_row
box[:, 3] = boxes[:, 3] - top_left_row
box[:, 5] = boxes[:, 5] - top_left_row
box[:, 7] = boxes[:, 7] - top_left_row
box[:, 8] = boxes[:, 8]
center_y = 0.25 * (box[:, 1] + box[:, 3] + box[:, 5] + box[:, 7])
center_x = 0.25 * (box[:, 0] + box[:, 2] + box[:, 4] + box[:, 6])
cond1 = np.intersect1d(np.where(center_y[:] >= 0)[0], np.where(center_x[:] >= 0)[0])
cond2 = np.intersect1d(np.where(center_y[:] <= (bottom_right_row - top_left_row))[0],
np.where(center_x[:] <= (bottom_right_col - top_left_col))[0])
idx = np.intersect1d(cond1, cond2)
if len(idx) > 0 and (subImage.shape[0] > 5 and subImage.shape[1] > 5):
makedirs(os.path.join(save_dir, 'images'))
img = os.path.join(save_dir, 'images',
"%s_%04d_%04d.png" % (file_idx, top_left_row, top_left_col))
cv2.imwrite(img, subImage)
makedirs(os.path.join(save_dir, 'labeltxt'))
xml = os.path.join(save_dir, 'labeltxt',
"%s_%04d_%04d.xml" % (file_idx, top_left_row, top_left_col))
save_to_xml(xml, subImage.shape[0], subImage.shape[1], box[idx, :], class_list)
def worker(self, gpu_id, images, det_net, result_queue):
os.environ["CUDA_VISIBLE_DEVICES"] = str(gpu_id)
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None,
3]) # is RGB. not BGR
img_batch = tf.cast(img_plac, tf.float32)
if self.cfgs.NET_NAME in [
'resnet152_v1d', 'resnet101_v1d', 'resnet50_v1d'
]:
img_batch = (img_batch / 255 - tf.constant(
self.cfgs.PIXEL_MEAN_)) / tf.constant(self.cfgs.PIXEL_STD)
else:
img_batch = img_batch - tf.constant(self.cfgs.PIXEL_MEAN)
img_batch = tf.expand_dims(img_batch, axis=0)
detection_boxes, detection_scores, detection_category = det_net.build_whole_detection_network(
input_img_batch=img_batch)
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 %d ...' % gpu_id)
for img_path in images:
# if 'P0006' not in img_path:
# continue
img = cv2.imread(img_path)
box_res_rotate = []
label_res_rotate = []
score_res_rotate = []
imgH = img.shape[0]
imgW = img.shape[1]
img_short_side_len_list = self.cfgs.IMG_SHORT_SIDE_LEN if isinstance(
self.cfgs.IMG_SHORT_SIDE_LEN,
list) else [self.cfgs.IMG_SHORT_SIDE_LEN]
img_short_side_len_list = [
img_short_side_len_list[0]
] if not self.args.multi_scale else img_short_side_len_list
if imgH < self.args.h_len:
temp = np.zeros([self.args.h_len, imgW, 3], np.float32)
temp[0:imgH, :, :] = img
img = temp
imgH = self.args.h_len
if imgW < self.args.w_len:
temp = np.zeros([imgH, self.args.w_len, 3], np.float32)
temp[:, 0:imgW, :] = img
img = temp
imgW = self.args.w_len
for hh in range(0, imgH,
self.args.h_len - self.args.h_overlap):
if imgH - hh - 1 < self.args.h_len:
hh_ = imgH - self.args.h_len
else:
hh_ = hh
for ww in range(0, imgW,
self.args.w_len - self.args.w_overlap):
if imgW - ww - 1 < self.args.w_len:
ww_ = imgW - self.args.w_len
else:
ww_ = ww
src_img = img[hh_:(hh_ + self.args.h_len),
ww_:(ww_ + self.args.w_len), :]
for short_size in img_short_side_len_list:
max_len = self.cfgs.IMG_MAX_LENGTH
if self.args.h_len < self.args.w_len:
new_h, new_w = short_size, min(
int(short_size * float(self.args.w_len) /
self.args.h_len), max_len)
else:
new_h, new_w = min(
int(short_size * float(self.args.h_len) /
self.args.w_len), max_len), short_size
img_resize = cv2.resize(src_img, (new_w, new_h))
resized_img, det_boxes_r_, det_scores_r_, det_category_r_ = \
sess.run(
[img_batch, detection_boxes, detection_scores, detection_category],
feed_dict={img_plac: img_resize[:, :, ::-1]}
)
resized_h, resized_w = resized_img.shape[
1], resized_img.shape[2]
src_h, src_w = src_img.shape[0], src_img.shape[1]
if len(det_boxes_r_) > 0:
det_boxes_r_ = forward_convert(
det_boxes_r_, False)
det_boxes_r_[:, 0::2] *= (src_w / resized_w)
det_boxes_r_[:, 1::2] *= (src_h / resized_h)
for ii in range(len(det_boxes_r_)):
box_rotate = det_boxes_r_[ii]
box_rotate[0::2] = box_rotate[0::2] + ww_
box_rotate[1::2] = box_rotate[1::2] + hh_
box_res_rotate.append(box_rotate)
label_res_rotate.append(
det_category_r_[ii])
score_res_rotate.append(det_scores_r_[ii])
if self.args.flip_img:
det_boxes_r_flip, det_scores_r_flip, det_category_r_flip = \
sess.run(
[detection_boxes, detection_scores, detection_category],
feed_dict={img_plac: cv2.flip(img_resize, flipCode=1)[:, :, ::-1]}
)
if len(det_boxes_r_flip) > 0:
det_boxes_r_flip = forward_convert(
det_boxes_r_flip, False)
det_boxes_r_flip[:, 0::2] *= (src_w /
resized_w)
det_boxes_r_flip[:, 1::2] *= (src_h /
resized_h)
for ii in range(len(det_boxes_r_flip)):
box_rotate = det_boxes_r_flip[ii]
box_rotate[0::2] = (
src_w - box_rotate[0::2]) + ww_
box_rotate[
1::2] = box_rotate[1::2] + hh_
box_res_rotate.append(box_rotate)
label_res_rotate.append(
det_category_r_flip[ii])
score_res_rotate.append(
det_scores_r_flip[ii])
det_boxes_r_flip, det_scores_r_flip, det_category_r_flip = \
sess.run(
[detection_boxes, detection_scores, detection_category],
feed_dict={img_plac: cv2.flip(img_resize, flipCode=0)[:, :, ::-1]}
)
if len(det_boxes_r_flip) > 0:
det_boxes_r_flip = forward_convert(
det_boxes_r_flip, False)
det_boxes_r_flip[:, 0::2] *= (src_w /
resized_w)
det_boxes_r_flip[:, 1::2] *= (src_h /
resized_h)
for ii in range(len(det_boxes_r_flip)):
box_rotate = det_boxes_r_flip[ii]
box_rotate[
0::2] = box_rotate[0::2] + ww_
box_rotate[1::2] = (
src_h - box_rotate[1::2]) + hh_
box_res_rotate.append(box_rotate)
label_res_rotate.append(
det_category_r_flip[ii])
score_res_rotate.append(
det_scores_r_flip[ii])
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_ = []
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': 0.2,
'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
}
for sub_class in range(1, self.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_ = backward_convert(tmp_boxes_r, False)
try:
inx = nms_rotate.nms_rotate_cpu(
boxes=np.array(tmp_boxes_r_),
scores=np.array(tmp_score_r),
iou_threshold=threshold[
self.label_name_map[sub_class]],
max_output_size=5000)
except:
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)
# 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(threshold[self.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])
result_dict = {
'boxes': np.array(box_res_rotate_),
'scores': np.array(score_res_rotate_),
'labels': np.array(label_res_rotate_),
'image_id': img_path
}
result_queue.put_nowait(result_dict)
def test_dota(self, det_net, real_test_img_list, txt_name):
save_path = os.path.join('./test_dota', self.cfgs.VERSION)
nr_records = len(real_test_img_list)
pbar = tqdm(total=nr_records)
gpu_num = len(self.args.gpus.strip().split(','))
nr_image = math.ceil(nr_records / gpu_num)
result_queue = Queue(500)
procs = []
for i, gpu_id in enumerate(self.args.gpus.strip().split(',')):
start = i * nr_image
end = min(start + nr_image, nr_records)
split_records = real_test_img_list[start:end]
proc = Process(target=self.worker,
args=(int(gpu_id), split_records, det_net,
result_queue))
print('process:%d, start:%d, end:%d' % (i, start, end))
proc.start()
procs.append(proc)
for i in range(nr_records):
res = result_queue.get()
if self.args.show_box:
nake_name = res['image_id'].split('/')[-1]
tools.makedirs(os.path.join(save_path, 'dota_img_vis'))
draw_path = os.path.join(save_path, 'dota_img_vis', nake_name)
draw_img = np.array(cv2.imread(res['image_id']), np.float32)
detected_boxes = backward_convert(res['boxes'],
with_label=False)
detected_indices = res['scores'] >= self.cfgs.VIS_SCORE
detected_scores = res['scores'][detected_indices]
detected_boxes = detected_boxes[detected_indices]
detected_categories = res['labels'][detected_indices]
drawer = DrawBox(self.cfgs)
final_detections = drawer.draw_boxes_with_label_and_scores(
draw_img,
boxes=detected_boxes,
labels=detected_categories,
scores=detected_scores,
method=1,
is_csl=True,
in_graph=False)
cv2.imwrite(draw_path, final_detections)
else:
CLASS_DOTA = self.name_label_map.keys()
write_handle = {}
tools.makedirs(os.path.join(save_path, 'dota_res'))
for sub_class in CLASS_DOTA:
if sub_class == 'back_ground':
continue
write_handle[sub_class] = open(
os.path.join(save_path, 'dota_res',
'Task1_%s.txt' % sub_class), 'a+')
for i, rbox in enumerate(res['boxes']):
command = '%s %.3f %.1f %.1f %.1f %.1f %.1f %.1f %.1f %.1f\n' % (
res['image_id'].split('/')[-1].split('.')[0],
res['scores'][i],
rbox[0],
rbox[1],
rbox[2],
rbox[3],
rbox[4],
rbox[5],
rbox[6],
rbox[7],
)
write_handle[self.label_name_map[res['labels'][i]]].write(
command)
for sub_class in CLASS_DOTA:
if sub_class == 'back_ground':
continue
write_handle[sub_class].close()
fw = open(txt_name, 'a+')
fw.write('{}\n'.format(res['image_id'].split('/')[-1]))
fw.close()
pbar.set_description("Test image %s" %
res['image_id'].split('/')[-1])
pbar.update(1)
for p in procs:
p.join()
def eval_with_plac(self, img_dir, det_net, image_ext):
os.environ["CUDA_VISIBLE_DEVICES"] = self.args.gpu
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None,
3]) # is RGB. not BGR
img_batch = tf.cast(img_plac, tf.float32)
pretrain_zoo = PretrainModelZoo()
if self.cfgs.NET_NAME in pretrain_zoo.pth_zoo or self.cfgs.NET_NAME in pretrain_zoo.mxnet_zoo:
img_batch = (img_batch / 255 - tf.constant(
self.cfgs.PIXEL_MEAN_)) / tf.constant(self.cfgs.PIXEL_STD)
else:
img_batch = img_batch - tf.constant(self.cfgs.PIXEL_MEAN)
img_batch = tf.expand_dims(img_batch, axis=0)
detection_boxes, detection_scores, detection_category = det_net.build_whole_detection_network(
input_img_batch=img_batch)
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)
pbar = tqdm(imgs)
for a_img_name in pbar:
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]
det_boxes_r_all, det_scores_r_all, det_category_r_all = [], [], []
img_short_side_len_list = self.cfgs.IMG_SHORT_SIDE_LEN if isinstance(
self.cfgs.IMG_SHORT_SIDE_LEN,
list) else [self.cfgs.IMG_SHORT_SIDE_LEN]
img_short_side_len_list = [
img_short_side_len_list[0]
] if not self.args.multi_scale else img_short_side_len_list
for short_size in img_short_side_len_list:
max_len = self.cfgs.IMG_MAX_LENGTH
if raw_h < raw_w:
new_h, new_w = short_size, min(
int(short_size * float(raw_w) / raw_h), max_len)
else:
new_h, new_w = min(
int(short_size * float(raw_h) / raw_w),
max_len), short_size
img_resize = cv2.resize(raw_img, (new_w, new_h))
resized_img, detected_boxes, detected_scores, detected_categories = \
sess.run(
[img_batch, detection_boxes, detection_scores, detection_category],
feed_dict={img_plac: img_resize[:, :, ::-1]}
)
if detected_boxes.shape[0] == 0:
continue
resized_h, resized_w = resized_img.shape[
1], resized_img.shape[2]
detected_boxes = forward_convert(detected_boxes, False)
detected_boxes[:, 0::2] *= (raw_w / resized_w)
detected_boxes[:, 1::2] *= (raw_h / resized_h)
det_boxes_r_all.extend(detected_boxes)
det_scores_r_all.extend(detected_scores)
det_category_r_all.extend(detected_categories)
det_boxes_r_all = np.array(det_boxes_r_all)
det_scores_r_all = np.array(det_scores_r_all)
det_category_r_all = np.array(det_category_r_all)
box_res_rotate_ = []
label_res_rotate_ = []
score_res_rotate_ = []
if det_scores_r_all.shape[0] != 0:
for sub_class in range(1, self.cfgs.CLASS_NUM + 1):
index = np.where(det_category_r_all == sub_class)[0]
if len(index) == 0:
continue
tmp_boxes_r = det_boxes_r_all[index]
tmp_label_r = det_category_r_all[index]
tmp_score_r = det_scores_r_all[index]
if self.args.multi_scale:
tmp_boxes_r_ = backward_convert(tmp_boxes_r, False)
# try:
# inx = nms_rotate.nms_rotate_cpu(boxes=np.array(tmp_boxes_r_),
# scores=np.array(tmp_score_r),
# iou_threshold=self.cfgs.NMS_IOU_THRESHOLD,
# max_output_size=5000)
# except:
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)
# 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(self.cfgs.NMS_IOU_THRESHOLD), 0)
else:
inx = np.arange(0, tmp_score_r.shape[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])
if len(box_res_rotate_) == 0:
all_boxes_r.append(np.array([]))
continue
det_boxes_r_ = np.array(box_res_rotate_)
det_scores_r_ = np.array(score_res_rotate_)
det_category_r_ = np.array(label_res_rotate_)
if self.args.draw_imgs:
detected_indices = det_scores_r_ >= self.cfgs.VIS_SCORE
detected_scores = det_scores_r_[detected_indices]
detected_boxes = det_boxes_r_[detected_indices]
detected_categories = det_category_r_[detected_indices]
detected_boxes = backward_convert(detected_boxes, False)
drawer = DrawBox(self.cfgs)
det_detections_r = drawer.draw_boxes_with_label_and_scores(
raw_img[:, :, ::-1],
boxes=detected_boxes,
labels=detected_categories,
scores=detected_scores,
method=1,
in_graph=True)
save_dir = os.path.join('test_hrsc', self.cfgs.VERSION,
'hrsc2016_img_vis')
tools.makedirs(save_dir)
cv2.imwrite(save_dir + '/{}.jpg'.format(a_img_name),
det_detections_r[:, :, ::-1])
det_boxes_r_ = backward_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)
pbar.set_description("Eval image %s" % a_img_name)
# fw1 = open(cfgs.VERSION + '_detections_r.pkl', 'wb')
# pickle.dump(all_boxes_r, fw1)
return all_boxes_r
def worker(self, gpu_id, images, det_net, result_queue):
os.environ["CUDA_VISIBLE_DEVICES"] = str(gpu_id)
# 1. preprocess img
img_plac = tf.placeholder(dtype=tf.uint8, shape=[None, None, 3]) # is RGB. not BGR
img_batch = tf.cast(img_plac, tf.float32)
if self.cfgs.NET_NAME in ['resnet152_v1d', 'resnet101_v1d', 'resnet50_v1d',
'resnet152_v1b', 'resnet101_v1b', 'resnet50_v1b', 'resnet34_v1b', 'resnet18_v1b']:
img_batch = (img_batch / 255 - tf.constant(self.cfgs.PIXEL_MEAN_)) / tf.constant(self.cfgs.PIXEL_STD)
else:
img_batch = img_batch - tf.constant(self.cfgs.PIXEL_MEAN)
img_batch = tf.expand_dims(img_batch, axis=0)
detection_boxes, detection_scores, detection_category = det_net.build_whole_detection_network(
input_img_batch=img_batch,
gtboxes_batch_h=None,
gtboxes_batch_r=None,
gpu_id=0)
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 %d ...' % gpu_id)
for a_img in images:
raw_img = cv2.imread(a_img)
raw_h, raw_w = raw_img.shape[0], raw_img.shape[1]
det_boxes_r_all, det_scores_r_all, det_category_r_all = [], [], []
img_short_side_len_list = self.cfgs.IMG_SHORT_SIDE_LEN if isinstance(self.cfgs.IMG_SHORT_SIDE_LEN, list) else [
self.cfgs.IMG_SHORT_SIDE_LEN]
img_short_side_len_list = [img_short_side_len_list[0]] if not self.args.multi_scale else img_short_side_len_list
for short_size in img_short_side_len_list:
max_len = self.cfgs.IMG_MAX_LENGTH
if raw_h < raw_w:
new_h, new_w = short_size, min(int(short_size * float(raw_w) / raw_h), max_len)
else:
new_h, new_w = min(int(short_size * float(raw_h) / raw_w), max_len), short_size
img_resize = cv2.resize(raw_img, (new_w, new_h))
resized_img, detected_boxes, detected_scores, detected_categories = \
sess.run(
[img_batch, detection_boxes, detection_scores, detection_category],
feed_dict={img_plac: img_resize[:, :, ::-1]}
)
detected_indices = detected_scores >= self.cfgs.VIS_SCORE
detected_scores = detected_scores[detected_indices]
detected_boxes = detected_boxes[detected_indices]
detected_categories = detected_categories[detected_indices]
if detected_boxes.shape[0] == 0:
continue
resized_h, resized_w = resized_img.shape[1], resized_img.shape[2]
detected_boxes = forward_convert(detected_boxes, False)
detected_boxes[:, 0::2] *= (raw_w / resized_w)
detected_boxes[:, 1::2] *= (raw_h / resized_h)
det_boxes_r_all.extend(detected_boxes)
det_scores_r_all.extend(detected_scores)
det_category_r_all.extend(detected_categories)
if self.args.flip_img:
detected_boxes, detected_scores, detected_categories = \
sess.run(
[detection_boxes, detection_scores, detection_category],
feed_dict={img_plac: cv2.flip(img_resize, flipCode=1)[:, :, ::-1]}
)
detected_indices = detected_scores >= self.cfgs.VIS_SCORE
detected_scores = detected_scores[detected_indices]
detected_boxes = detected_boxes[detected_indices]
detected_categories = detected_categories[detected_indices]
if detected_boxes.shape[0] == 0:
continue
resized_h, resized_w = resized_img.shape[1], resized_img.shape[2]
detected_boxes = forward_convert(detected_boxes, False)
detected_boxes[:, 0::2] *= (raw_w / resized_w)
detected_boxes[:, 0::2] = (raw_w - detected_boxes[:, 0::2])
detected_boxes[:, 1::2] *= (raw_h / resized_h)
det_boxes_r_all.extend(sort_corners(detected_boxes))
det_scores_r_all.extend(detected_scores)
det_category_r_all.extend(detected_categories)
detected_boxes, detected_scores, detected_categories = \
sess.run(
[detection_boxes, detection_scores, detection_category],
feed_dict={img_plac: cv2.flip(img_resize, flipCode=0)[:, :, ::-1]}
)
detected_indices = detected_scores >= self.cfgs.VIS_SCORE
detected_scores = detected_scores[detected_indices]
detected_boxes = detected_boxes[detected_indices]
detected_categories = detected_categories[detected_indices]
if detected_boxes.shape[0] == 0:
continue
resized_h, resized_w = resized_img.shape[1], resized_img.shape[2]
detected_boxes = forward_convert(detected_boxes, False)
detected_boxes[:, 0::2] *= (raw_w / resized_w)
detected_boxes[:, 1::2] *= (raw_h / resized_h)
detected_boxes[:, 1::2] = (raw_h - detected_boxes[:, 1::2])
det_boxes_r_all.extend(sort_corners(detected_boxes))
det_scores_r_all.extend(detected_scores)
det_category_r_all.extend(detected_categories)
det_boxes_r_all = np.array(det_boxes_r_all)
det_scores_r_all = np.array(det_scores_r_all)
det_category_r_all = np.array(det_category_r_all)
box_res_rotate_ = []
label_res_rotate_ = []
score_res_rotate_ = []
if det_scores_r_all.shape[0] != 0:
for sub_class in range(1, self.cfgs.CLASS_NUM + 1):
index = np.where(det_category_r_all == sub_class)[0]
if len(index) == 0:
continue
tmp_boxes_r = det_boxes_r_all[index]
tmp_label_r = det_category_r_all[index]
tmp_score_r = det_scores_r_all[index]
if self.args.multi_scale:
tmp_boxes_r_ = backward_convert(tmp_boxes_r, False)
# try:
# inx = nms_rotate.nms_rotate_cpu(boxes=np.array(tmp_boxes_r_),
# scores=np.array(tmp_score_r),
# iou_threshold=self.cfgs.NMS_IOU_THRESHOLD,
# max_output_size=5000)
# except:
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)
# 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(self.cfgs.NMS_IOU_THRESHOLD), 0)
else:
inx = np.arange(0, tmp_score_r.shape[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])
box_res_rotate_ = np.array(box_res_rotate_)
score_res_rotate_ = np.array(score_res_rotate_)
label_res_rotate_ = np.array(label_res_rotate_)
result_dict = {'scales': [1, 1], 'boxes': box_res_rotate_,
'scores': score_res_rotate_, 'labels': label_res_rotate_,
'image_id': a_img}
result_queue.put_nowait(result_dict)
def test_icdar2015(self, det_net, real_test_img_list, txt_name):
save_path = os.path.join('./test_icdar2015', self.cfgs.VERSION)
tools.makedirs(save_path)
nr_records = len(real_test_img_list)
pbar = tqdm(total=nr_records)
gpu_num = len(self.args.gpus.strip().split(','))
nr_image = math.ceil(nr_records / gpu_num)
result_queue = Queue(500)
procs = []
for i, gpu_id in enumerate(self.args.gpus.strip().split(',')):
start = i * nr_image
end = min(start + nr_image, nr_records)
split_records = real_test_img_list[start:end]
proc = Process(target=self.worker, args=(int(gpu_id), split_records, det_net, result_queue))
print('process:%d, start:%d, end:%d' % (i, start, end))
proc.start()
procs.append(proc)
for i in range(nr_records):
res = result_queue.get()
tools.makedirs(os.path.join(save_path, 'icdar2015_res'))
if res['boxes'].shape[0] == 0:
fw_txt_dt = open(os.path.join(save_path, 'icdar2015_res', 'res_{}.txt'.format(res['image_id'].split('/')[-1].split('.')[0])),
'w')
fw_txt_dt.close()
pbar.update(1)
fw = open(txt_name, 'a+')
fw.write('{}\n'.format(res['image_id'].split('/')[-1]))
fw.close()
continue
x1, y1, x2, y2, x3, y3, x4, y4 = res['boxes'][:, 0], res['boxes'][:, 1], res['boxes'][:, 2], res['boxes'][:, 3],\
res['boxes'][:, 4], res['boxes'][:, 5], res['boxes'][:, 6], res['boxes'][:, 7]
x1, y1 = x1 * res['scales'][0], y1 * res['scales'][1]
x2, y2 = x2 * res['scales'][0], y2 * res['scales'][1]
x3, y3 = x3 * res['scales'][0], y3 * res['scales'][1]
x4, y4 = x4 * res['scales'][0], y4 * res['scales'][1]
boxes = np.transpose(np.stack([x1, y1, x2, y2, x3, y3, x4, y4]))
if self.args.show_box:
boxes = backward_convert(boxes, False)
nake_name = res['image_id'].split('/')[-1]
tools.makedirs(os.path.join(save_path, 'icdar2015_img_vis'))
draw_path = os.path.join(save_path, 'icdar2015_img_vis', nake_name)
draw_img = np.array(cv2.imread(res['image_id']), np.float32)
drawer = DrawBox(self.cfgs)
final_detections = drawer.draw_boxes_with_label_and_scores(draw_img,
boxes=boxes,
labels=res['labels'],
scores=res['scores'],
method=1,
in_graph=False)
cv2.imwrite(draw_path, final_detections)
else:
fw_txt_dt = open(os.path.join(save_path, 'icdar2015_res', 'res_{}.txt'.format(res['image_id'].split('/')[-1].split('.')[0])), 'w')
for box in boxes:
line = '%d,%d,%d,%d,%d,%d,%d,%d\n' % (box[0], box[1], box[2], box[3],
box[4], box[5], box[6], box[7])
fw_txt_dt.write(line)
fw_txt_dt.close()
fw = open(txt_name, 'a+')
fw.write('{}\n'.format(res['image_id'].split('/')[-1]))
fw.close()
pbar.set_description("Test image %s" % res['image_id'].split('/')[-1])
pbar.update(1)
for p in procs:
p.join()
def clip_image(file_idx, image, boxes_all, width, height, w_overlap,
h_overlap):
print(file_idx)
# fill useless boxes
min_pixel = 5
boxes_all_5 = backward_convert(boxes_all[:, :8], False)
small_boxes = boxes_all[np.logical_or(boxes_all_5[:, 2] <= min_pixel,
boxes_all_5[:, 3] <= min_pixel), :]
cv2.fillConvexPoly(image,
np.reshape(small_boxes, [-1, 2]),
color=(0, 0, 0))
different_boxes = boxes_all[boxes_all[:, 9] == 1]
cv2.fillConvexPoly(image,
np.reshape(different_boxes, [-1, 2]),
color=(0, 0, 0))
boxes_all = boxes_all[np.logical_and(boxes_all_5[:, 2] > min_pixel,
boxes_all_5[:, 3] > min_pixel), :]
boxes_all = boxes_all[boxes_all[:, 9] == 0]
if boxes_all.shape[0] > 0:
imgH = image.shape[0]
imgW = image.shape[1]
if imgH < height:
temp = np.zeros([height, imgW, 3], np.float32)
temp[0:imgH, :, :] = image
image = temp
imgH = height
if imgW < width:
temp = np.zeros([imgH, width, 3], np.float32)
temp[:, 0:imgW, :] = image
image = temp
imgW = width
for hh in range(0, imgH, height - h_overlap):
if imgH - hh - 1 < height:
hh_ = imgH - height
else:
hh_ = hh
for ww in range(0, imgW, width - w_overlap):
if imgW - ww - 1 < width:
ww_ = imgW - width
else:
ww_ = ww
subimg = image[hh_:(hh_ + height), ww_:(ww_ + width), :]
boxes = copy.deepcopy(boxes_all)
box = np.zeros_like(boxes_all)
top_left_row = max(hh_, 0)
top_left_col = max(ww_, 0)
bottom_right_row = min(hh_ + height, imgH)
bottom_right_col = min(ww_ + width, imgW)
box[:, :8:2] = boxes[:, :8:2] - top_left_col
box[:, 1:8:2] = boxes[:, 1:8:2] - top_left_row
box[:, 8:] = boxes[:, 8:]
center_y = 0.25 * (box[:, 1] + box[:, 3] + box[:, 5] +
box[:, 7])
center_x = 0.25 * (box[:, 0] + box[:, 2] + box[:, 4] +
box[:, 6])
cond1 = np.intersect1d(
np.where(center_y[:] >= 0)[0],
np.where(center_x[:] >= 0)[0])
cond2 = np.intersect1d(
np.where(
center_y[:] <= (bottom_right_row - top_left_row))[0],
np.where(
center_x[:] <= (bottom_right_col - top_left_col))[0])
idx = np.intersect1d(cond1, cond2)
if len(idx) > 0:
makedirs(os.path.join(save_dir, 'images'))
img = os.path.join(
save_dir, 'images', "%s_%04d_%04d.png" %
(file_idx, top_left_row, top_left_col))
cv2.imwrite(img, subimg)
makedirs(os.path.join(save_dir, 'labeltxt'))
xml = os.path.join(
save_dir, 'labeltxt', "%s_%04d_%04d.xml" %
(file_idx, top_left_row, top_left_col))
save_to_xml(xml, subimg.shape[0], subimg.shape[1],
box[idx, :], class_list)
