CODEWITHSUNDEEP
pythonpytorchgpugoogle-colaboratory
Abhinav Binkar
Abhinav Binkar

Reputation: 31

Runtime error while executing code from google colab document for creating Deepfakes image animation

enter image description hereI'm getting runtime error while executing code from google colab document for creating Deepfakes image animation.

RuntimeError                              Traceback (most recent call last)

<ipython-input-5-dbd18151b569> in <module>()

  1 from demo import load_checkpoints
  2 generator, kp_detector = load_checkpoints(config_path='config/vox-256.yaml',

----> 3 checkpoint_path='/content/gdrive/My Drive/first-order-motion-model/vox-cpk.pth.tar')

10 frames

/usr/local/lib/python3.6/dist-packages/torch/cuda/__init__.py in _lazy_init()

188             raise AssertionError(

189                 "libcudart functions unavailable. It looks like you have a broken build?")

--> 190 torch._C._cuda_init()

191         # Some of the queued calls may reentrantly call _lazy_init();

192         # we need to just return without initializing in that case.

RuntimeError: cuda runtime error (100) : no CUDA-capable device is detected at /pytorch/aten/src/THC/THCGeneral.cpp:47

Upvotes: 2

Views: 5017

Answers (2)

David
David

Reputation: 331

You may be running on a colab environment that only has TPU's available and not GPU's in which case you need to utilize XLA with PyTorch. You might find this notebook and repository very helpful if this is the case:

https://colab.research.google.com/github/pytorch/xla/blob/master/contrib/colab/resnet18-training.ipynb

https://github.com/pytorch/xla

Upvotes: 1

venkat0107
venkat0107

Reputation: 254

1.check the path weather the file exists or not 2.in your screen shot there is no drive mounted try checking it once 3.if top two are done still facing problem check with the file given is correct or not

Hope this is helpfu :)

Upvotes: 0

Related Questions