From e926afd02be87b4d212c1cbbd4fb7267a1b9885e Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Sat, 31 Aug 2019 18:58:30 +0200 Subject: [PATCH] updates --- detect.py | 66 ++++++++++++++++++++++--------------------------------- test.py | 4 ++-- 2 files changed, 28 insertions(+), 42 deletions(-) diff --git a/detect.py b/detect.py index dd482ab9..e3fcf92a 100644 --- a/detect.py +++ b/detect.py @@ -7,36 +7,30 @@ from utils.datasets import * from utils.utils import * -def detect(cfg, - data, - weights, - images='data/samples', # input folder - output='output', # output folder - fourcc='mp4v', # video codec - img_size=416, - conf_thres=0.5, - nms_thres=0.5, - save_txt=False, +def detect(save_txt=False, save_images=True): + out = opt.output + img_size = opt.img_size + # Initialize device = torch_utils.select_device(force_cpu=ONNX_EXPORT) torch.backends.cudnn.benchmark = False # set False for reproducible results - if os.path.exists(output): - shutil.rmtree(output) # delete output folder - os.makedirs(output) # make new output folder + if os.path.exists(out): + shutil.rmtree(out) # delete output folder + os.makedirs(out) # make new output folder # Initialize model if ONNX_EXPORT: s = (320, 192) # (320, 192) or (416, 256) or (608, 352) onnx model image size (height, width) - model = Darknet(cfg, s) + model = Darknet(opt.cfg, s) else: - model = Darknet(cfg, img_size) + model = Darknet(opt.cfg, img_size) # Load weights - if weights.endswith('.pt'): # pytorch format - model.load_state_dict(torch.load(weights, map_location=device)['model']) + if opt.weights.endswith('.pt'): # pytorch format + model.load_state_dict(torch.load(opt.weights, map_location=device)['model']) else: # darknet format - _ = load_darknet_weights(model, weights) + _ = load_darknet_weights(model, opt.weights) # Fuse Conv2d + BatchNorm2d layers # model.fuse() @@ -61,22 +55,22 @@ def detect(cfg, save_images = False dataloader = LoadWebcam(img_size=img_size, half=opt.half) else: - dataloader = LoadImages(images, img_size=img_size, half=opt.half) + dataloader = LoadImages(opt.input, img_size=img_size, half=opt.half) # Get classes and colors - classes = load_classes(parse_data_cfg(data)['names']) + classes = load_classes(parse_data_cfg(opt.data)['names']) colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(classes))] # Run inference t0 = time.time() - for i, (path, img, im0, vid_cap) in enumerate(dataloader): + for path, img, im0, vid_cap in dataloader: t = time.time() - save_path = str(Path(output) / Path(path).name) + save_path = str(Path(out) / Path(path).name) # Get detections img = torch.from_numpy(img).unsqueeze(0).to(device) pred, _ = model(img) - det = non_max_suppression(pred.float(), conf_thres, nms_thres)[0] + det = non_max_suppression(pred.float(), opt.conf_thres, opt.nms_thres)[0] if det is not None and len(det) > 0: # Rescale boxes from 416 to true image size @@ -101,7 +95,7 @@ def detect(cfg, print('Done. (%.3fs)' % (time.time() - t)) if opt.webcam: # Show live webcam - cv2.imshow(weights, im0) + cv2.imshow(opt.weights, im0) if save_images: # Save image with detections if dataloader.mode == 'images': @@ -115,13 +109,13 @@ def detect(cfg, fps = vid_cap.get(cv2.CAP_PROP_FPS) width = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH)) height = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) - vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (width, height)) + vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*opt.fourcc), fps, (width, height)) vid_writer.write(im0) if save_images: - print('Results saved to %s' % os.getcwd() + os.sep + output) - if platform == 'darwin': # macos - os.system('open ' + output + ' ' + save_path) + print('Results saved to %s' % os.getcwd() + os.sep + out) + if platform == 'darwin': # MacOS + os.system('open ' + out + ' ' + save_path) print('Done. (%.3fs)' % (time.time() - t0)) @@ -131,24 +125,16 @@ if __name__ == '__main__': parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path') parser.add_argument('--data', type=str, default='data/coco.data', help='coco.data file path') parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file') - parser.add_argument('--images', type=str, default='data/samples', help='path to images') + parser.add_argument('--input', type=str, default='data/samples', help='input folder') # input folder + parser.add_argument('--output', type=str, default='output', help='output folder') # output folder parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)') parser.add_argument('--conf-thres', type=float, default=0.3, help='object confidence threshold') parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression') - parser.add_argument('--fourcc', type=str, default='mp4v', help='fourcc output video codec (verify ffmpeg support)') - parser.add_argument('--output', type=str, default='output', help='specifies the output path for images and videos') + parser.add_argument('--fourcc', type=str, default='mp4v', help='output video codec (verify ffmpeg support)') parser.add_argument('--half', action='store_true', help='half precision FP16 inference') parser.add_argument('--webcam', action='store_true', help='use webcam') opt = parser.parse_args() print(opt) with torch.no_grad(): - detect(opt.cfg, - opt.data, - opt.weights, - images=opt.images, - img_size=opt.img_size, - conf_thres=opt.conf_thres, - nms_thres=opt.nms_thres, - fourcc=opt.fourcc, - output=opt.output) + detect() diff --git a/test.py b/test.py index b638a22e..be4cf627 100644 --- a/test.py +++ b/test.py @@ -195,15 +195,15 @@ def test(cfg, if __name__ == '__main__': parser = argparse.ArgumentParser(prog='test.py') - parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch') parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='cfg file path') parser.add_argument('--data', type=str, default='data/coco.data', help='coco.data file path') parser.add_argument('--weights', type=str, default='weights/yolov3-spp.weights', help='path to weights file') + parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch') + parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)') parser.add_argument('--iou-thres', type=float, default=0.5, help='iou threshold required to qualify as detected') parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold') parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression') parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file') - parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)') opt = parser.parse_args() print(opt)