def worker(gpu_id, images, det_net, args, 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) img_batch = short_side_resize_for_inference_data( img_tensor=img_batch, target_shortside_len=cfgs.IMG_SHORT_SIDE_LEN, length_limitation=cfgs.IMG_MAX_LENGTH) if cfgs.NET_NAME in ['resnet152_v1d', 'resnet101_v1d', 'resnet50_v1d']: img_batch = (img_batch / 255 - tf.constant( cfgs.PIXEL_MEAN_)) / tf.constant(cfgs.PIXEL_STD) else: img_batch = img_batch - tf.constant(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) 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 'P0016' 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] if imgH < args.h_len: temp = np.zeros([args.h_len, imgW, 3], np.float32) temp[0:imgH, :, :] = img img = temp imgH = args.h_len if imgW < args.w_len: temp = np.zeros([imgH, args.w_len, 3], np.float32) temp[:, 0:imgW, :] = img img = temp imgW = args.w_len for hh in range(0, imgH, args.h_len - args.h_overlap): if imgH - hh - 1 < args.h_len: hh_ = imgH - args.h_len else: hh_ = hh for ww in range(0, imgW, args.w_len - args.w_overlap): if imgW - ww - 1 < args.w_len: ww_ = imgW - args.w_len else: ww_ = ww src_img = img[hh_:(hh_ + args.h_len), ww_:(ww_ + args.w_len), :] 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: src_img[:, :, ::-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) det_boxes_r_ = backward_convert(det_boxes_r_, False) 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_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': 0.05, '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 } 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=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(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]) 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 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 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(det_net, args): # 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 cfgs.NET_NAME in ['resnet152_v1d', 'resnet101_v1d', 'resnet50_v1d']: img_batch = (img_batch / 255 - tf.constant( cfgs.PIXEL_MEAN_)) / tf.constant(cfgs.PIXEL_STD) else: img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN) img_batch = tf.expand_dims(img_batch, axis=0) detection_boxes, detection_scores, detection_category, detection_boxes_angle = det_net.build_whole_detection_network( input_img_batch=img_batch, gtboxes_batch_h=None, gtboxes_batch_r=None, gt_smooth_label=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 = [] img_short_side_len_list = cfgs.IMG_SHORT_SIDE_LEN if isinstance( cfgs.IMG_SHORT_SIDE_LEN, list) else [cfgs.IMG_SHORT_SIDE_LEN] img_short_side_len_list = [ img_short_side_len_list[0] ] if not args.multi_scale else img_short_side_len_list imgs = os.listdir(args.img_dir) pbar = tqdm(imgs) for a_img_name in pbar: a_img_name = a_img_name.split(args.image_ext)[0] raw_img = cv2.imread( os.path.join(args.img_dir, a_img_name + args.image_ext)) raw_h, raw_w = raw_img.shape[0], raw_img.shape[1] box_res_rotate = [] label_res_rotate = [] score_res_rotate = [] for short_size in img_short_side_len_list: max_len = 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, det_boxes_r_, det_scores_r_, det_category_r_ = \ sess.run( [img_batch, detection_boxes_angle, detection_scores, detection_category], feed_dict={img_plac: img_resize[:, :, ::-1]} ) resized_h, resized_w = resized_img.shape[1], resized_img.shape[ 2] if len(det_boxes_r_) > 0: 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) for ii in range(len(det_boxes_r_)): box_rotate = det_boxes_r_[ii] box_res_rotate.append(box_rotate) label_res_rotate.append(det_category_r_[ii]) score_res_rotate.append(det_scores_r_[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 = {'car': 0.2, 'plane': 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_ = 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[LABEL_NAME_MAP[sub_class]], max_output_size=150) 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[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]) box_res_rotate_ = np.array(box_res_rotate_) score_res_rotate_ = np.array(score_res_rotate_) label_res_rotate_ = np.array(label_res_rotate_) if args.draw_imgs: detected_indices = score_res_rotate_ >= cfgs.VIS_SCORE detected_scores = score_res_rotate_[detected_indices] detected_boxes = box_res_rotate_[detected_indices] detected_boxes = backward_convert(detected_boxes, with_label=False) detected_categories = label_res_rotate_[detected_indices] det_detections_r = draw_box_in_img.draw_boxes_with_label_and_scores( np.array(raw_img, np.float32), boxes=detected_boxes, labels=detected_categories, scores=detected_scores, method=1, in_graph=False, is_csl=True) save_dir = os.path.join('test_ucas_aod', cfgs.VERSION, 'ucas_aod_img_vis') tools.mkdir(save_dir) cv2.imwrite(save_dir + '/{}.jpg'.format(a_img_name), det_detections_r[:, :, ::-1]) if box_res_rotate_.shape[0] != 0: box_res_rotate_ = backward_convert(box_res_rotate_, False) x_c, y_c, w, h, theta = box_res_rotate_[:, 0], box_res_rotate_[:, 1], box_res_rotate_[:, 2], \ box_res_rotate_[:, 3], box_res_rotate_[:, 4] boxes_r = np.transpose(np.stack([x_c, y_c, w, h, theta])) dets_r = np.hstack((label_res_rotate_.reshape(-1, 1), score_res_rotate_.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 detect_img(file_paths, des_folder, det_th, h_len, w_len, h_overlap, w_overlap, show_res=False): with tf.Graph().as_default(): img_plac = tf.placeholder(shape=[None, None, 3], dtype=tf.uint8) img_tensor = tf.cast(img_plac, tf.float32) - tf.constant([103.939, 116.779, 123.68]) img_batch = image_preprocess.short_side_resize_for_inference_data(img_tensor, target_shortside_len=cfgs.SHORT_SIDE_LEN) # *********************************************************************************************** # * share net * # *********************************************************************************************** _, share_net = get_network_byname(net_name=cfgs.NET_NAME, inputs=img_batch, num_classes=None, is_training=True, output_stride=None, global_pool=False, spatial_squeeze=False) # *********************************************************************************************** # * RPN * # *********************************************************************************************** rpn = build_rpn.RPN(net_name=cfgs.NET_NAME, inputs=img_batch, gtboxes_and_label=None, is_training=False, share_head=cfgs.SHARE_HEAD, share_net=share_net, stride=cfgs.STRIDE, anchor_ratios=cfgs.ANCHOR_RATIOS, anchor_scales=cfgs.ANCHOR_SCALES, scale_factors=cfgs.SCALE_FACTORS, base_anchor_size_list=cfgs.BASE_ANCHOR_SIZE_LIST, # P2, P3, P4, P5, P6 level=cfgs.LEVEL, top_k_nms=cfgs.RPN_TOP_K_NMS, rpn_nms_iou_threshold=cfgs.RPN_NMS_IOU_THRESHOLD, max_proposals_num=cfgs.MAX_PROPOSAL_NUM, rpn_iou_positive_threshold=cfgs.RPN_IOU_POSITIVE_THRESHOLD, rpn_iou_negative_threshold=cfgs.RPN_IOU_NEGATIVE_THRESHOLD, rpn_mini_batch_size=cfgs.RPN_MINIBATCH_SIZE, rpn_positives_ratio=cfgs.RPN_POSITIVE_RATE, remove_outside_anchors=False, # whether remove anchors outside rpn_weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME]) # rpn predict proposals rpn_proposals_boxes, rpn_proposals_scores = rpn.rpn_proposals() # rpn_score shape: [300, ] # *********************************************************************************************** # * Fast RCNN * # *********************************************************************************************** fast_rcnn = build_fast_rcnn.FastRCNN(feature_pyramid=rpn.feature_pyramid, rpn_proposals_boxes=rpn_proposals_boxes, rpn_proposals_scores=rpn_proposals_scores, img_shape=tf.shape(img_batch), img_batch=img_batch, roi_size=cfgs.ROI_SIZE, roi_pool_kernel_size=cfgs.ROI_POOL_KERNEL_SIZE, scale_factors=cfgs.SCALE_FACTORS, gtboxes_and_label=None, gtboxes_and_label_minAreaRectangle=None, fast_rcnn_nms_iou_threshold=cfgs.FAST_RCNN_NMS_IOU_THRESHOLD, fast_rcnn_maximum_boxes_per_img=100, fast_rcnn_nms_max_boxes_per_class=cfgs.FAST_RCNN_NMS_MAX_BOXES_PER_CLASS, show_detections_score_threshold=det_th, # show detections which score >= 0.6 num_classes=cfgs.CLASS_NUM, fast_rcnn_minibatch_size=cfgs.FAST_RCNN_MINIBATCH_SIZE, fast_rcnn_positives_ratio=cfgs.FAST_RCNN_POSITIVE_RATE, fast_rcnn_positives_iou_threshold=cfgs.FAST_RCNN_IOU_POSITIVE_THRESHOLD, # iou>0.5 is positive, iou<0.5 is negative use_dropout=cfgs.USE_DROPOUT, weight_decay=cfgs.WEIGHT_DECAY[cfgs.NET_NAME], is_training=False, level=cfgs.LEVEL, head_quadrant=None) fast_rcnn_decode_boxes, fast_rcnn_score, num_of_objects, detection_category, \ fast_rcnn_decode_boxes_rotate, fast_rcnn_score_rotate, fast_rcnn_head_quadrant, \ num_of_objects_rotate, detection_category_rotate = fast_rcnn.fast_rcnn_predict() init_op = tf.group( tf.global_variables_initializer(), tf.local_variables_initializer() ) restorer, restore_ckpt = restore_model.get_restorer() config = tf.ConfigProto() # config.gpu_options.per_process_gpu_memory_fraction = 0.5 config.gpu_options.allow_growth = True # *********************************************************************************************** # * 运行定义好的图 * # *********************************************************************************************** with tf.Session(config=config) as sess: sess.run(init_op) if not restorer is None: restorer.restore(sess, restore_ckpt) print('restore model') coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess, coord) for img_path in file_paths: start = timer() # gdal.AllRegister() # ds = gdal.Open(img_path, gdalconst.GA_ReadOnly) # if ds is None: # print("Image %s open failed!" % img_path) # sys.exit() img = cv2.imread(img_path) box_res = [] label_res = [] score_res = [] box_res_rotate = [] label_res_rotate = [] score_res_rotate = [] head_rotate = [] # imgH = ds.RasterYSize # imgW = ds.RasterXSize imgH = img.shape[0] imgW = img.shape[1] for hh in range(0, imgH, h_len): h_size = min(h_len, imgH - hh - h_overlap) if h_size < 10: break for ww in range(0, imgW, w_len): w_size = min(w_len, imgW - ww - w_overlap) if w_size < 10: break # src_img = ds.ReadAsArray(ww, hh, w_size, h_size) src_img = img[hh:(hh + h_size), ww:(ww + w_size), :] # if len(src_img.shape) == 2: # src_img = cv2.cvtColor(src_img, cv2.COLOR_GRAY2RGB) # else: # src_img = chw2hwc(src_img) boxes, labels, scores = sess.run([fast_rcnn_decode_boxes, detection_category, fast_rcnn_score], feed_dict={img_plac: src_img}) boxes_rotate, labels_rotate, scores_rotate, _fast_rcnn_head_quadrant = \ sess.run([fast_rcnn_decode_boxes_rotate, detection_category_rotate, fast_rcnn_score_rotate, fast_rcnn_head_quadrant], feed_dict={img_plac: src_img}) if show_res: visualize_detection(src_img, boxes, scores) # 可视化检测结果 if len(boxes) > 0: for ii in range(len(boxes)): box = boxes[ii] box[0] = box[0] + hh box[1] = box[1] + ww box[2] = box[2] + hh box[3] = box[3] + ww box_res.append(box) label_res.append(labels[ii]) score_res.append(scores[ii]) if len(boxes_rotate) > 0: for ii in range(len(boxes_rotate)): box_rotate = boxes_rotate[ii] box_rotate[0] = box_rotate[0] + hh box_rotate[1] = box_rotate[1] + ww box_res_rotate.append(box_rotate) label_res_rotate.append(labels_rotate[ii]) score_res_rotate.append(scores_rotate[ii]) head_rotate.append(_fast_rcnn_head_quadrant[ii]) inx = nms_rotate.nms_rotate_cpu(boxes=np.array(box_res_rotate), scores=np.array(score_res_rotate), iou_threshold=0.5, max_output_size=100) box_res_rotate = np.array(box_res_rotate)[inx] score_res_rotate = np.array(score_res_rotate)[inx] label_res_rotate = np.array(label_res_rotate)[inx] head_rotate = np.array(head_rotate)[inx] # ds = None time_elapsed = timer() - start print("{} detection time : {:.4f} sec".format(img_path.split('/')[-1].split('.')[0], time_elapsed)) # if target_name == 'aircraft': # img = cv2.imread(img_path) # if len(img.shape) == 2: # img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB) # elif len(img.shape) == 3: # img_gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) # img[:, :, 0] = img[:, :, 1] = img[:, :, 2] = img_gray mkdir(des_folder) img_np = draw_box_cv(np.array(img, np.float32) - np.array([103.939, 116.779, 123.68]), boxes=np.array(box_res), labels=np.array(label_res), scores=np.array(score_res)) img_np_rotate = draw_rotate_box_cv(np.array(img, np.float32) - np.array([103.939, 116.779, 123.68]), boxes=np.array(box_res_rotate), labels=np.array(label_res_rotate), scores=np.array(score_res_rotate), head=np.argmax(head_rotate, axis=1)) cv2.imwrite(des_folder + '/{}_horizontal_fpn.jpg'.format(img_path.split('/')[-1].split('.')[0]), img_np) cv2.imwrite(des_folder + '/{}_rotate_fpn.jpg'.format(img_path.split('/')[-1].split('.')[0]), img_np_rotate) # clip_obj_imgs(src_img, box_res, label_res, score_res, des_folder) # print(img_path) # det_xml_path =img_path.replace(".tif", ".det.xml") # obj_to_det_xml(img_path, box_res, label_res, score_res, det_xml_path) coord.request_stop() coord.join(threads)
def worker(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 cfgs.NET_NAME in ['resnet152_v1d', 'resnet101_v1d', 'resnet50_v1d']: img_batch = (img_batch / 255 - tf.constant( cfgs.PIXEL_MEAN_)) / tf.constant(cfgs.PIXEL_STD) else: img_batch = img_batch - tf.constant(cfgs.PIXEL_MEAN) img_batch = tf.expand_dims(img_batch, axis=0) detection_boxes, detection_scores, detection_category, detection_boxes_angle = det_net.build_whole_detection_network( input_img_batch=img_batch, gtboxes_batch_h=None, gtboxes_batch_r=None, gt_smooth_label=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 = cfgs.IMG_SHORT_SIDE_LEN if isinstance( cfgs.IMG_SHORT_SIDE_LEN, list) else [cfgs.IMG_SHORT_SIDE_LEN] img_short_side_len_list = [ img_short_side_len_list[0] ] if not args.multi_scale else img_short_side_len_list for short_size in img_short_side_len_list: max_len = 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_angle, detection_scores, detection_category], feed_dict={img_plac: img_resize[:, :, ::-1]} ) detected_indices = detected_scores >= 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 = backward_convert(detected_boxes, False) 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, 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] 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=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(cfgs.NMS_IOU_THRESHOLD), 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)