diff --git a/README_cn.md b/README_cn.md index 0865e6745aff5d3304cc9c0aa3428431306ec759..ebeab2ec12da265fb1ab48489fcff5e559cc1513 100644 --- a/README_cn.md +++ b/README_cn.md @@ -18,6 +18,7 @@ PaddleDetection模块化地实现了多种主流目标检测算法，提供了
+
### 产品动态 diff --git a/configs/keypoint/README.md b/configs/keypoint/README.md index 4b193986d9cd5619ed7e128d229a7802ba3c842a..b4285bc9bc6748fcc2adf2fc96c85154083e8a15 100644 --- a/configs/keypoint/README.md +++ b/configs/keypoint/README.md @@ -76,5 +76,5 @@ python deploy/python/keypoint_infer.py --model_dir=output_inference/higherhrnet_ python deploy/python/keypoint_infer.py --model_dir=output_inference/hrnet_w32_384x288/ --image_file=./demo/hrnet_demo.jpg --use_gpu=True --threshold=0.5 #keypoint top-down模型 + detector 检测联合部署推理（联合推理只支持top-down方式） -python deploy/python/keypoint_det_unite_infer.py --det_model_dir=output_inference/ppyolo_r50vd_dcn_2x_coco/ --keypoint_model_dir=output_inference/hrnet_w32_384x288/ --video_file=../video/xxx.mp4 +python deploy/python/keypoint_det_unite_infer.py --det_model_dir=output_inference/ppyolo_r50vd_dcn_2x_coco/ --keypoint_model_dir=output_inference/hrnet_w32_384x288/ --video_file=../video/xxx.mp4 --use_gpu=True ``` diff --git a/deploy/python/infer.py b/deploy/python/infer.py index ee44f61b14e6365315a48273a0f0e5c22ce95dba..47a18d8005e2f80edda85e23f5e11de5f0acc682 100644 --- a/deploy/python/infer.py +++ b/deploy/python/infer.py @@ -191,7 +191,7 @@ class DetectorSOLOv2(Detector): cpu_threads=1, enable_mkldnn=False): self.pred_config = pred_config - self.predictor, self.config = load_predictor( + self.predictor, self.config = load_predictor( model_dir, run_mode=run_mode, min_subgraph_size=self.pred_config.min_subgraph_size, @@ -541,8 +541,8 @@ def main(): detector.det_times.info(average=True) else: mems = { - 'cpu_rss': detector.cpu_mem / len(img_list), - 'gpu_rss': detector.gpu_mem / len(img_list), + 'cpu_rss_mb': detector.cpu_mem / len(img_list), + 'gpu_rss_mb': detector.gpu_mem / len(img_list), 'gpu_util': detector.gpu_util * 100 / len(img_list) } @@ -550,16 +550,16 @@ def main(): model_dir = FLAGS.model_dir mode = FLAGS.run_mode model_info = { - 'model_name': model_dir.strip('/').split('/')[-1], - 'precision': mode.split('_')[-1] + 'model_name': model_dir.strip('/').split('/')[-1], + 'precision': mode.split('_')[-1] } data_info = { 'batch_size': 1, 'shape': "dynamic_shape", 'data_num': perf_info['img_num'] } - det_log = PaddleInferBenchmark( - detector.config, model_info, data_info, perf_info, mems) + det_log = PaddleInferBenchmark(detector.config, model_info, + data_info, perf_info, mems) det_log('Det') diff --git a/deploy/python/keypoint_det_unite_infer.py b/deploy/python/keypoint_det_unite_infer.py index b27abe32af690c6db5176f142fc1416f7ecdd2d5..dd80b290ff89377562dfb7149ed05a9257fd079b 100644 --- a/deploy/python/keypoint_det_unite_infer.py +++ b/deploy/python/keypoint_det_unite_infer.py @@ -13,7 +13,6 @@ # limitations under the License. import os - from PIL import Image import cv2 import numpy as np @@ -52,7 +51,7 @@ def get_person_from_rect(images, results): org_rects = [] for rect in valid_rects: rect_image, new_rect, org_rect = expand_crop(images, rect) - if rect_image is None: + if rect_image is None or rect_image.size == 0: continue image_buff.append([rect_image, new_rect]) org_rects.append(org_rect) @@ -113,13 +112,13 @@ def topdown_unite_predict_video(detector, topdown_keypoint_detector, camera_id): os.makedirs(FLAGS.output_dir) out_path = os.path.join(FLAGS.output_dir, video_name) writer = cv2.VideoWriter(out_path, fourcc, fps, (width, height)) - index = 1 + index = 0 while (1): ret, frame = capture.read() if not ret: break - print('detect frame:%d' % (index)) index += 1 + print('detect frame:%d' % (index)) frame2 = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) results = detector.predict(frame2, FLAGS.det_threshold) @@ -136,7 +135,7 @@ def topdown_unite_predict_video(detector, topdown_keypoint_detector, camera_id): keypoint_res = {} keypoint_res['keypoint'] = [ np.vstack(keypoint_vector), np.vstack(score_vector) - ] + ] if len(keypoint_vector) > 0 else [[], []] keypoint_res['bbox'] = rect_vecotr im = draw_pose( frame, @@ -189,8 +188,6 @@ def main(): # predict from image img_list = get_test_images(FLAGS.image_dir, FLAGS.image_file) topdown_unite_predict(detector, topdown_keypoint_detector, img_list) - detector.det_times.info(average=True) - topdown_keypoint_detector.det_times.info(average=True) if __name__ == '__main__': diff --git a/deploy/python/keypoint_infer.py b/deploy/python/keypoint_infer.py index 61a9fb8aea97a8dd33d8912bc19576e26806cf08..49d8b344118fcb5da15eff9b97bae8980edba586 100644 --- a/deploy/python/keypoint_infer.py +++ b/deploy/python/keypoint_infer.py @@ -28,7 +28,8 @@ from keypoint_postprocess import HrHRNetPostProcess, HRNetPostProcess from keypoint_visualize import draw_pose from paddle.inference import Config from paddle.inference import create_predictor -from utils import argsparser, Timer, get_current_memory_mb, LoggerHelper +from utils import argsparser, Timer, get_current_memory_mb +from benchmark_utils import PaddleInferBenchmark from infer import get_test_images, print_arguments # Global dictionary @@ -66,7 +67,7 @@ class KeyPoint_Detector(object): cpu_threads=1, enable_mkldnn=False): self.pred_config = pred_config - self.predictor = load_predictor( + self.predictor, self.config = load_predictor( model_dir, run_mode=run_mode, min_subgraph_size=self.pred_config.min_subgraph_size, @@ -129,7 +130,7 @@ class KeyPoint_Detector(object): MaskRCNN's results include 'masks': np.ndarray: shape: [N, im_h, im_w] ''' - self.det_times.preprocess_time.start() + self.det_times.preprocess_time_s.start() inputs = self.preprocess(image) np_boxes, np_masks = None, None input_names = self.predictor.get_input_names() @@ -137,7 +138,7 @@ class KeyPoint_Detector(object): for i in range(len(input_names)): input_tensor = self.predictor.get_input_handle(input_names[i]) input_tensor.copy_from_cpu(inputs[input_names[i]]) - self.det_times.preprocess_time.end() + self.det_times.preprocess_time_s.end() for i in range(warmup): self.predictor.run() output_names = self.predictor.get_output_names() @@ -152,7 +153,7 @@ class KeyPoint_Detector(object): inds_k.copy_to_cpu() ] - self.det_times.inference_time.start() + self.det_times.inference_time_s.start() for i in range(repeats): self.predictor.run() output_names = self.predictor.get_output_names() @@ -166,12 +167,12 @@ class KeyPoint_Detector(object): masks_tensor.copy_to_cpu(), heat_k.copy_to_cpu(), inds_k.copy_to_cpu() ] - self.det_times.inference_time.end(repeats=repeats) + self.det_times.inference_time_s.end(repeats=repeats) - self.det_times.postprocess_time.start() + self.det_times.postprocess_time_s.start() results = self.postprocess( np_boxes, np_masks, inputs, threshold=threshold) - self.det_times.postprocess_time.end() + self.det_times.postprocess_time_s.end() self.det_times.img_num += 1 return results @@ -318,7 +319,7 @@ def load_predictor(model_dir, # disable feed, fetch OP, needed by zero_copy_run config.switch_use_feed_fetch_ops(False) predictor = create_predictor(config) - return predictor + return predictor, config def predict_image(detector, image_list): @@ -347,7 +348,8 @@ def predict_video(detector, camera_id): video_name = 'output.mp4' else: capture = cv2.VideoCapture(FLAGS.video_file) - video_name = os.path.basename(os.path.split(FLAGS.video_file)[-1]) + video_name = os.path.splitext(os.path.basename(FLAGS.video_file))[ + 0] + '.mp4' fps = 30 width = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH)) height = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)) @@ -403,13 +405,25 @@ def main(): detector.det_times.info(average=True) else: mems = { - 'cpu_rss': detector.cpu_mem / len(img_list), - 'gpu_rss': detector.gpu_mem / len(img_list), + 'cpu_rss_mb': detector.cpu_mem / len(img_list), + 'gpu_rss_mb': detector.gpu_mem / len(img_list), 'gpu_util': detector.gpu_util * 100 / len(img_list) } - det_logger = LoggerHelper( - FLAGS, detector.det_times.report(average=True), mems) - det_logger.report() + perf_info = detector.det_times.report(average=True) + model_dir = FLAGS.model_dir + mode = FLAGS.run_mode + model_info = { + 'model_name': model_dir.strip('/').split('/')[-1], + 'precision': mode.split('_')[-1] + } + data_info = { + 'batch_size': 1, + 'shape': "dynamic_shape", + 'data_num': perf_info['img_num'] + } + det_log = PaddleInferBenchmark(detector.config, model_info, + data_info, perf_info, mems) + det_log('KeyPoint') if __name__ == '__main__': diff --git a/deploy/python/keypoint_visualize.py b/deploy/python/keypoint_visualize.py index 94793810a505987a3a754e24f055b994dbdc2135..b379bd7029817f6e6daef73492bb80039118190f 100644 --- a/deploy/python/keypoint_visualize.py +++ b/deploy/python/keypoint_visualize.py @@ -19,11 +19,6 @@ import numpy as np import math -def map_coco_to_personlab(keypoints): - permute = [0, 6, 8, 10, 5, 7, 9, 12, 14, 16, 11, 13, 15, 2, 1, 4, 3] - return keypoints[:, permute, :] - - def draw_pose(imgfile, results, visual_thread=0.6, @@ -39,9 +34,9 @@ def draw_pose(imgfile, 'for example: `pip install matplotlib`.') raise e - EDGES = [(0, 14), (0, 13), (0, 4), (0, 1), (14, 16), (13, 15), (4, 10), - (1, 7), (10, 11), (7, 8), (11, 12), (8, 9), (4, 5), (1, 2), (5, 6), - (2, 3)] + EDGES = [(0, 1), (0, 2), (1, 3), (2, 4), (3, 5), (4, 6), (5, 7), (6, 8), + (7, 9), (8, 10), (5, 11), (6, 12), (11, 13), (12, 14), (13, 15), + (14, 16), (11, 12)] NUM_EDGES = len(EDGES) colors = [[255, 0, 0], [255, 85, 0], [255, 170, 0], [255, 255, 0], [170, 255, 0], [85, 255, 0], [0, 255, 0], \ @@ -52,25 +47,28 @@ def draw_pose(imgfile, img = cv2.imread(imgfile) if type(imgfile) == str else imgfile skeletons, scores = results['keypoint'] + color_set = results['colors'] if 'colors' in results else None if 'bbox' in results: bboxs = results['bbox'] - for idx, rect in enumerate(bboxs): + for j, rect in enumerate(bboxs): xmin, ymin, xmax, ymax = rect - cv2.rectangle(img, (xmin, ymin), (xmax, ymax), colors[0], 1) + color = colors[0] if color_set is None else colors[color_set[j] % + len(colors)] + cv2.rectangle(img, (xmin, ymin), (xmax, ymax), color, 1) canvas = img.copy() for i in range(17): - rgba = np.array(cmap(1 - i / 17. - 1. / 34)) - rgba[0:3] *= 255 for j in range(len(skeletons)): if skeletons[j][i, 2] < visual_thread: continue + color = colors[i] if color_set is None else colors[color_set[j] % + len(colors)] cv2.circle( canvas, tuple(skeletons[j][i, 0:2].astype('int32')), 2, - colors[i], + color, thickness=-1) to_plot = cv2.addWeighted(img, 0.3, canvas, 0.7, 0) @@ -78,7 +76,6 @@ def draw_pose(imgfile, stickwidth = 2 - skeletons = map_coco_to_personlab(skeletons) for i in range(NUM_EDGES): for j in range(len(skeletons)): edge = EDGES[i] @@ -96,7 +93,9 @@ def draw_pose(imgfile, polygon = cv2.ellipse2Poly((int(mY), int(mX)), (int(length / 2), stickwidth), int(angle), 0, 360, 1) - cv2.fillConvexPoly(cur_canvas, polygon, colors[i]) + color = colors[i] if color_set is None else colors[color_set[j] % + len(colors)] + cv2.fillConvexPoly(cur_canvas, polygon, color) canvas = cv2.addWeighted(canvas, 0.4, cur_canvas, 0.6, 0) if returnimg: return canvas diff --git a/docs/images/mot_pose_demo_640x360.gif b/docs/images/mot_pose_demo_640x360.gif new file mode 100644 index 0000000000000000000000000000000000000000..a4b6fe0178c891c3840e2b647e26d5b9010da741 Binary files /dev/null and b/docs/images/mot_pose_demo_640x360.gif differ