search

sxl142 / GLoT

Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation
57 stars 3 forks source link

An issue about yolo.weight #14

Open lisaner000 opened 1 day ago

lisaner000 commented 1 day ago

I have a question about yolo.weight you provided. Traceback (most recent call last): File "demo.py", line 382, in main(args, cfgs) File "demo.py", line 78, in main yolo_img_size=args.yolo_img_size, File "/root/miniconda3/envs/glot/lib/python3.7/site-packages/multi_person_tracker/mpt.py", line 53, in init device=self.device, img_size=yolo_img_size, person_detector=True, video=True, return_dict=True File "/root/miniconda3/envs/glot/lib/python3.7/site-packages/yolov3/yolo.py", line 51, in init self.model.load_darknet_weights(weights_path) File "/root/miniconda3/envs/glot/lib/python3.7/site-packages/yolov3/models.py", line 315, in load_darknet_weights conv_w = torch.from_numpy(weights[ptr : ptr + num_w]).view_as(conv_layer.weight) RuntimeError: shape '[512, 256, 3, 3]' is invalid for input of size 971393

sxl142 commented 22 hours ago

Please check your Python environment, and ensure that it is aligned with our provided.