CODEWITHSUNDEEP
python-2.7pytorchgoogle-colaboratorytorchvision
0101
0101

Reputation: 1096

Your session crashed after using all available RAM in Google Colab

I am trying to get this to run in google colab https://github.com/oawiles/X2Face/blob/master/UnwrapMosaic/Face2Face_UnwrapMosaic.ipynb,

I was able to get it to run and display results once but since then lately I have been getting your session crashed after using all available RAM at this cell

    BASE_MODEL = '/scratch/shared/slow/ow/eccv/2018/release_models/' # Change to your path
state_dict = torch.load(BASE_MODEL + 'x2face_model.pth')

model = UnwrappedFaceWeightedAverage(output_num_channels=2, input_num_channels=3, inner_nc=128)
model.load_state_dict(state_dict['state_dict'])
model = model.cuda()

model = model.eval()

im not sure if it is a colab issue or not

here is the logs

warn("IPython.utils.traitlets has moved to a top-level traitlets package.")
/usr/local/lib/python2.7/dist-packages/IPython/utils/traitlets.py:5: UserWarning: IPython.utils.traitlets has moved to a top-level traitlets package.

Upvotes: 2

Views: 2098

Answers (2)

Bright Chang
Bright Chang

Reputation: 311

My experience is to shift to the CPU colab version, run the codes

And then switch to the GPU colab version

The codes run smoothly after these operations.

Upvotes: 1

Hemanth Reddy
Hemanth Reddy

Reputation: 11

Try to change settings,

Go to run-time->change run-time type->hardware accelerator->select option GPU or TPU

I think this might help.

Upvotes: 1

Related Questions