Stops at 0% at iteration. about shap-e

[moo-the-cow]

I had the same issue I and resolved it:
it seems there were multiple possible conflicts. I had to make sure the CUDA version is the same as suggested on
https://pytorch.org/get-started/locally/
furthermore make sure to uninstall any existing torch versions

pip uninstall torch

and re-do the local installation steps from the url before in my case I was on windows running cuda 11.8 (archive)

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

edit: a little helper.
you have to see CUDA in the output or it will keep in stuck state.
test.py

import torch

# Check if PyTorch is using the GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"PyTorch is using: {device}")

# Print PyTorch version
print(f"PyTorch version: {torch.__version__}")

# Test a simple PyTorch tensor operation on the GPU
x = torch.tensor([2.0, 3.0], device=device)
y = torch.tensor([4.0, 5.0], device=device)
result = x * y
print(f"Result of tensor operation: {result}")

[ultmedi45]

resolved.
thanks @moo-the-cow

before

test.py

PyTorch is using: cpu
PyTorch version: 2.0.0+cpu
Result of tensor operation: tensor([ 8., 15.])

What I did.

pip uninstall torch

pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117

after

test.py

PyTorch is using: cuda
PyTorch version: 2.0.0+cu117
Result of tensor operation: tensor([ 8., 15.], device='cuda:0')

[Ceterminateniya]

I have the same problem.

[DutchMaxwell]

I was able to bypass the denoising by setting use_karras=False, but now I have this:

[0xunderl0rd]

Same issue...

[blackhatma]

i was able to fix this by changing the runtime type to use a gpu on google colab, for what its worth

[DutchMaxwell]

i was able to fix this by changing the runtime type to use a gpu on google colab, for what its worth

This work fine. Yes.

[DutchMaxwell]

I had the same issue I and resolved it: it seems there were multiple possible conflicts. I had to make sure the CUDA version is the same as suggested on https://pytorch.org/get-started/locally/ furthermore make sure to uninstall any existing torch versions

pip uninstall torch

and re-do the local installation steps from the url before in my case I was on windows running cuda 11.8 (archive)

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

edit: a little helper. you have to see CUDA in the output or it will keep in stuck state. test.py

import torch

# Check if PyTorch is using the GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"PyTorch is using: {device}")

# Print PyTorch version
print(f"PyTorch version: {torch.__version__}")

# Test a simple PyTorch tensor operation on the GPU
x = torch.tensor([2.0, 3.0], device=device)
y = torch.tensor([4.0, 5.0], device=device)
result = x * y
print(f"Result of tensor operation: {result}")

No CUDA for Mac. :(

[Natotela]

PyTorch version: 2.0.0+cu117

specifically 117?

[Kabanosk]

@Natotela

by the way, any chance to run this on 8GB VRAM??

Maybe lowering the batch size will help, eg. batch_size = 1?

[moo-the-cow]

@Natotela in my case I used cu118
maybe higher versions will also work, but I wanted to stick to the documentation guide