Hi, trying to use the pretrained model but there seemed to be mismatched between the definition in the code and the provided weights.
here is the error fully -
----------path: Models/MESH2IR/netG_epoch_40.pth
----------path: Models/MESH2IR/mesh_net_epoch_40.pth
thus STAGE1_G(
(cond_net): COND_NET(
(fc): Linear(in_features=14, out_features=10, bias=True)
(relu): PReLU(num_parameters=1)
)
(fc): Sequential(
(0): Linear(in_features=10, out_features=32768, bias=False)
(1): BatchNorm1d(32768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): PReLU(num_parameters=1)
)
(upsample1): Sequential(
(0): ConvTranspose1d(2048, 1024, kernel_size=(41,), stride=(4,), padding=(19,), output_padding=(1,))
(1): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): PReLU(num_parameters=1)
)
(upsample2): Sequential(
(0): ConvTranspose1d(1024, 512, kernel_size=(41,), stride=(4,), padding=(19,), output_padding=(1,))
(1): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): PReLU(num_parameters=1)
)
(upsample3): Sequential(
(0): ConvTranspose1d(512, 256, kernel_size=(41,), stride=(4,), padding=(19,), output_padding=(1,))
(1): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): PReLU(num_parameters=1)
)
(upsample4): Sequential(
(0): ConvTranspose1d(256, 128, kernel_size=(41,), stride=(2,), padding=(20,), output_padding=(1,))
(1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): PReLU(num_parameters=1)
)
(upsample5): Sequential(
(0): ConvTranspose1d(128, 128, kernel_size=(41,), stride=(2,), padding=(20,), output_padding=(1,))
(1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): PReLU(num_parameters=1)
)
(RIR): Sequential(
(0): ConvTranspose1d(128, 2, kernel_size=(41,), stride=(1,), padding=(20,))
(1): Tanh()
)
)
Load from: Models/MESH2IR/netG_epoch_40.pth
Traceback (most recent call last):
File "C:\Users\noamk\OneDrive\Desktop\NOAM\Miluim\L2S-main\L2S-main\evaluate.py", line 191, in
evaluate()
File "C:\Users\noamk\OneDrive\Desktop\NOAM\Miluim\L2S-main\L2S-main\evaluate.py", line 111, in evaluate
netG, mesh_net = load_network_stageI(netG_path,mesh_net_path)
File "C:\Users\noamk\OneDrive\Desktop\NOAM\Miluim\L2S-main\L2S-main\evaluate.py", line 73, in load_network_stageI
mesh_net.load_state_dict(state_dict)
File "C:\Users\noamk\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\module.py", line 2152, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for MESH_NET:
Missing key(s) in state_dict: "pool1.select.weight", "pool2.select.weight", "pool3.select.weight".
Unexpected key(s) in state_dict: "pool1.weight", "pool2.weight", "pool3.weight".
[Finished in 6.9s]
Would love your help!
Thanks!

Hello,
Thank you for your interesting works!

I have frequent connection and permission issues with Google Drive.
Are there other ways to download the data?