search

vincent-thevenin / Realistic-Neural-Talking-Head-Models

My implementation of Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (Egor Zakharov et al.).
GNU General Public License v3.0
828 stars 195 forks source link

IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 2) #41

Closed rperdon closed 4 years ago

rperdon commented 4 years ago

File "train.py", line 91, in for i_batch, (f_lm, x, g_y, i) in enumerate(dataLoader, start=i_batch_current): File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 345, in next data = self._next_data() File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 385, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/media/shared/Realistic-Neural-Talking-Head-Models-master/dataset/dataset_class.py", line 42, in getitem frame_mark = frame_mark.transpose(2,4).to(self.device) #K,2,3,224,224 IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 2)

Downloaded the vggceleb2 set and tried to run the train.py. Kept getting this error. Tried this on the test vggset and same error.

Also when running webcam_inference, getting only a black screen on the fake image.

Bip3 commented 4 years ago

Most likely the name of one of your variables is wrong. Make sure your dataset folder, weights, e_hat, etc has the correct name when declared.

rperdon commented 4 years ago

I haven't touched the code yet, I just downloaded the git repo and tried running it.

Bip3 commented 4 years ago

You have to touch the code. The necessary paths are declared in several of the scripts.

rperdon commented 4 years ago

I have all the correct paths now. I renamed the vox2celeb folder from dev to mp4 which gave the initial error. I pulled out the mp4 directory of the vox2celeb set into the main path of the project. I have all the appropriate files in the correct folders.

path_to_chkpt = 'model_weights.tar' path_to_backup = 'backup_model_weights.tar' #missing this file, but it is a backup dataset = VidDataSet(K=8, path_to_mp4 = 'mp4', device=device)

criterionG = LossG(VGGFace_body_path='Pytorch_VGGFACE_IR.py', VGGFace_weight_path='Pytorch_VGGFACE.pth', device=device)

After confirming the correct folders and path to vox2celeb, I now get this error:

RuntimeError: Error(s) in loading state_dict for Discriminator: size mismatch for W_i: copying a param with shape torch.Size([512, 145740]) from checkpoint, the shape in current model is torch.Size([512, 1092009]).

So is this an indication of a problem with one of the files from the vox2celeb set? I get the same error from the test data set from vox2celeb as well.

Bip3 commented 4 years ago

You might be using the old trained weights with the save_disc branch

Bip3 commented 4 years ago

If you want, delete your old model weights and retry

rperdon commented 4 years ago

I've deleted the model_weights.tar file and am re-running train.py.

rperdon commented 4 years ago

deleting the old model worked.