junyanz / VON

[NeurIPS 2018] Visual Object Networks: Image Generation with Disentangled 3D Representation.
http://von.csail.mit.edu
Other
530 stars 91 forks source link

Training images #31

Open CroMocha opened 3 years ago

CroMocha commented 3 years ago

Running into an error when feeding data into the model

I'm trying to train the model for top view car images, so after I downloaded the training data

However, I got the error below. Are there additional steps I'm missing in creating the training data?

Traceback (most recent call last): File "train.py", line 22, in for i, data in enumerate(dataset): File "/media/marcchoo/Data/marcj/Documents/VON/data/init.py", line 84, in iter for i, data in enumerate(self.dataloader): File "/home/marcchoo/anaconda3/envs/von/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 336, in next return self._process_next_batch(batch) File "/home/marcchoo/anaconda3/envs/von/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 357, in _process_next_batch raise batch.exc_type(batch.exc_msg) IndexError: Traceback (most recent call last): File "/home/marcchoo/anaconda3/envs/von/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "/home/marcchoo/anaconda3/envs/von/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 106, in samples = collate_fn([dataset[i] for i in batch_indices]) File "/media/marcchoo/Data/marcj/Documents/VON/data/concat_dataset.py", line 9, in getitem return tuple(d[i] for d in self.datasets) File "/media/marcchoo/Data/marcj/Documents/VON/data/concat_dataset.py", line 9, in return tuple(d[i] for d in self.datasets) File "/media/marcchoo/Data/marcj/Documents/VON/data/images_dataset.py", line 95, in getitem return self.get_item(index) File "/media/marcchoo/Data/marcj/Documents/VON/data/images_dataset.py", line 115, in get_item mask = im_out[3, :, :] IndexError: index 3 is out of bounds for dimension 0 with size 3

CroMocha commented 3 years ago

Ok, I see the mask in the alpha channel. Are there other modifications that I will need to make?