NVlabs/few-shot-vid2vid

tile cannot extend outside image

vnyk opened this issue · 0 comments

vnyk commented

I am trying to run few shot pose on my data, I tried running it on small batches of data, it ran successfully. But, when I tried to train it on full dataset then it gave me the following error

Run command

python train.py --dataroot ./datasets/cvdata/09 --name 09_data --dataset_mode fewshot_pose --adaptive_spade --warp_ref --spade_combine --remove_face_labels --add_face_D --niter_single 100 --niter 200 --batchSize 4 --gpu_ids 2

Error output

CustomDatasetDataLoader
1 sequences
dataset [PoseDataset] was created
create web directory ./checkpoints/09_data/web...
---------- Networks initialized -------------
---------- Optimizers initialized -------------
model [Vid2VidModel] was created
/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/torch/nn/functional.py:2479: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
  "See the documentation of nn.Upsample for details.".format(mode))
Traceback (most recent call last):
  File "train.py", line 73, in <module>
    train()
  File "train.py", line 40, in train
    for idx, data in enumerate(dataset, start=trainer.epoch_iter):
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 819, in __next__
    return self._process_data(data)
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data
    data.reraise()
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/torch/_utils.py", line 369, in reraise
    raise self.exc_type(msg)
ValueError: Caught ValueError in DataLoader worker process 1.
Original Traceback (most recent call last):
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/developer/workspace/dance/few-shot-vid2vid/data/fewshot_pose_dataset.py", line 109, in __getitem__
    crop_coords, self.ref_face_pts)
  File "/home/developer/workspace/dance/few-shot-vid2vid/data/fewshot_pose_dataset.py", line 129, in get_images
    O, op, crop_coords, face_pts = self.get_image(op_path, size, params, crop_coords, input_type='openpose', ref_face_pts=ref_face_pts)
  File "/home/developer/workspace/dance/few-shot-vid2vid/data/fewshot_pose_dataset.py", line 152, in get_image
    A_img, crop_coords = self.crop_person_region(A_img, crop_coords, pose_pts, size)
  File "/home/developer/workspace/dance/few-shot-vid2vid/data/fewshot_pose_dataset.py", line 182, in crop_person_region
    A_img = Image.fromarray(A_img[ys:ye, xs:xe, :])
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/PIL/Image.py", line 2670, in fromarray
    return frombuffer(mode, size, obj, "raw", rawmode, 0, 1)
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/PIL/Image.py", line 2613, in frombuffer
    return frombytes(mode, size, data, decoder_name, args)
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/PIL/Image.py", line 2546, in frombytes
    im.frombytes(data, decoder_name, args)
  File "/home/developer/anaconda3/envs/fewshot-dev/lib/python3.7/site-packages/PIL/Image.py", line 829, in frombytes
    d.setimage(self.im)
ValueError: tile cannot extend outside image

I know there is some issue with my data but I am not able to figure out the exact problem, since it worked on small sample batches of my data.
Any help will be appreciated