demo_video.py error

[zhohn0]

Loading model from D:\PythonProjects\HybrIK\pretrained_w_cam_res50.pth... Traceback (most recent call last): File "D:\PythonProjects\HybrIK\scripts\demo_video.py", line 101, in hybrik_model.load_state_dict(torch.load(CKPT, map_location='cpu'), strict=False) File "C:\Users\hanzhao\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1667, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for Simple3DPoseBaseSMPLCam: size mismatch for init_cam: copying a param with shape torch.Size([3]) from checkpoint, the shape in current model is torch.Size([1]). size mismatch for preact.layer1.0.conv1.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for preact.layer1.1.conv1.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for preact.layer1.2.conv1.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for preact.layer2.0.conv1.weight: copying a param with shape torch.Size([128, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 256, 1, 1]). size mismatch for preact.layer2.0.downsample.0.weight: copying a param with shape torch.Size([128, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 256, 1, 1]). size mismatch for preact.layer2.0.downsample.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for preact.layer2.0.downsample.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for preact.layer2.0.downsample.1.running_mean: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for preact.layer2.0.downsample.1.running_var: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for preact.layer2.1.conv1.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for preact.layer2.2.conv1.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for preact.layer2.3.conv1.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for preact.layer3.0.conv1.weight: copying a param with shape torch.Size([256, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 512, 1, 1]). size mismatch for preact.layer3.0.downsample.0.weight: copying a param with shape torch.Size([256, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 512, 1, 1]). size mismatch for preact.layer3.0.downsample.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for preact.layer3.0.downsample.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for preact.layer3.0.downsample.1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for preact.layer3.0.downsample.1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([1024]). size mismatch for preact.layer3.1.conv1.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for preact.layer3.2.conv1.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for preact.layer3.3.conv1.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for preact.layer3.4.conv1.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for preact.layer3.5.conv1.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for preact.layer4.0.conv1.weight: copying a param with shape torch.Size([512, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 1024, 1, 1]). size mismatch for preact.layer4.0.downsample.0.weight: copying a param with shape torch.Size([512, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 1024, 1, 1]). size mismatch for preact.layer4.0.downsample.1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for preact.layer4.0.downsample.1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for preact.layer4.0.downsample.1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for preact.layer4.0.downsample.1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([2048]). size mismatch for preact.layer4.1.conv1.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 2048, 1, 1]). size mismatch for preact.layer4.2.conv1.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 2048, 1, 1]). size mismatch for deconv_layers.0.weight: copying a param with shape torch.Size([512, 256, 4, 4]) from checkpoint, the shape in current model is torch.Size([2048, 256, 4, 4]). size mismatch for fc1.weight: copying a param with shape torch.Size([1024, 512]) from checkpoint, the shape in current model is torch.Size([1024, 2048]). size mismatch for deccam.weight: copying a param with shape torch.Size([3, 1024]) from checkpoint, the shape in current model is torch.Size([1, 1024]). size mismatch for deccam.bias: copying a param with shape torch.Size([3]) from checkpoint, the shape in current model is torch.Size([1]).

Process finished with exit code 1

[Xiyan-Xu]

Do you fixed it? I encountered the same issue

[Xiyan-Xu]

problem solved. use the last model in model zoo instead of others.