PoseFormerV2 icon indicating copy to clipboard operation
PoseFormerV2 copied to clipboard

Weight mismatch error

Open eliflali opened this issue 5 months ago • 0 comments

Traceback (most recent call last): File "/content/PoseFormerV2/demo/vis.py", line 286, in get_pose2D(video_path, output_dir) File "/content/PoseFormerV2/demo/vis.py", line 90, in get_pose2D keypoints, scores = hrnet_pose(video_path, det_dim=416, num_peroson=1, gen_output=True) File "/content/PoseFormerV2/demo/lib/hrnet/gen_kpts.py", line 95, in gen_video_kpts human_model = yolo_model(inp_dim=det_dim) File "/content/PoseFormerV2/demo/lib/yolov3/human_detector.py", line 88, in load_model model.load_weights(args.weight_file) File "/content/PoseFormerV2/demo/lib/yolov3/darknet.py", line 432, in load_weights conv_weights = conv_weights.view_as(conv.weight.data) RuntimeError: shape '[256, 128, 3, 3]' is invalid for input of size 108955

eliflali avatar Sep 19 '24 15:09 eliflali