I have googled it, but it has not been solved yet. I have the following problem, please help me

[HaoWeiHsueh]

I suspect it's the PyTorch version and StackOverflow doesn't have a solution to the problem
1. The following error occurs when I execute python demo.py --gpu 0 --stage param --test_epoch 8

RuntimeError: Error(s) in loading state_dict for DataParallel:
size mismatch for module.param_regressor.fc_pose.0.weight: copying a param with shape torch.Size([144, 512]) from checkpoint, the shape in current model is torch.Size([96, 512])
.
size mismatch for module.param_regressor.fc_pose.0.bias: copying a param with shape torch.Size([144]) from checkpoint, the shape in current model is torch.Size([96]).
size mismatch for module.human_model_layer.th_shapedirs: copying a param with shape torch.Size([6890, 3, 10]) from checkpoint, the shape in current model is torch.Size([778, 3,
10]).
size mismatch for module.human_model_layer.th_posedirs: copying a param with shape torch.Size([6890, 3, 207]) from checkpoint, the shape in current model is torch.Size([778, 3,
135]).
size mismatch for module.human_model_layer.th_v_template: copying a param with shape torch.Size([1, 6890, 3]) from checkpoint, the shape in current model is torch.Size([1, 778,
3]).
size mismatch for module.human_model_layer.th_J_regressor: copying a param with shape torch.Size([24, 6890]) from checkpoint, the shape in current model is torch.Size([16, 778])
.
size mismatch for module.human_model_layer.th_weights: copying a param with shape torch.Size([6890, 24]) from checkpoint, the shape in current model is torch.Size([778, 16]).
size mismatch for module.human_model_layer.th_faces: copying a param with shape torch.Size([13776, 3]) from checkpoint, the shape in current model is torch.Size([1538, 3]).

2.The following error occurs when I execute python demo.py --gpu 0 --stage param --test_epoch 12
Traceback (most recent call last):
File "demo.py", line 99, in
out = model(inputs, targets, meta_info, 'test')
File "E:\Software\Anaconda3\envs\I2L\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "E:\Software\Anaconda3\envs\I2L\lib\site-packages\torch\nn\parallel\data_parallel.py", line 166, in forward
return self.module(*inputs[0], **kwargs[0])
File "E:\Software\Anaconda3\envs\I2L\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "..\main\model.py", line 75, in forward
joint_img_from_mesh = torch.bmm(torch.from_numpy(self.joint_regressor).cuda()[None,:,:].repeat(mesh_coord_img.shape[0],1,1), mesh_coord_img)
RuntimeError: batch1 dim 2 must match batch2 dim 1