Loading pretrained FastAI models in Kaggle kernels without using internet

Question

I am trying to load a densenet121 model in Kaggle kernel without switching on the internet. I have done the required steps such as adding the pre-trained weights to my input directory and moving it to '.cache/torch/checkpoints/'. It still would not work and throws a gaierror.

The following the is code SNIPPET:

!mkdir -p /tmp/.cache/torch/checkpoints
!cp ../input/fastai-pretrained-models/densenet121-a639ec97.pth /tmp/.cache/torch/checkpoints/densenet121-a639ec97.pth

learn_cd = create_cnn(data_cd, models.densenet121, metrics=[error_rate, accuracy],model_dir = Path('../kaggle/working/models'),path=Path('.'),).to_fp16()

I have been struggling with this for a long time. Any help would be immensely helpful

score 0 · Answer 1 · answered Nov 28 '20 at 20:21

so input path "../input/" in kaggle kernel is read only. create a folder in "kaggle/working" rather and copy the model weights there. Example below

if not os.path.exists('/root/.cache/torch/hub/checkpoints/'):
        os.makedirs('/root/.cache/torch/hub/checkpoints/')

!mkdir '/kaggle/working/resnet34'
!cp '/root/.cache/torch/hub/checkpoints/resnet34-333f7ec4.pth' '/kaggle/working/resnet34/resnet34.pth'

Loading pretrained FastAI models in Kaggle kernels without using internet

1 Answers1