Facing problem loading pretained architecture resnext101_64 while working with kaggle Kernels

Hello Guys,
Hope you all are doing good .
I’m facing problem loading pretrained architecture resnext101_64 while working in kaggle kernels . The code searches for weights at /opt/conda/lib/python3.6/site-packages/fastai-0.6-py3.6.egg/fastai/weights.
Its mentioned that the above location is read only , so I cannot push the downloaded weights to this location.
Anyone who has faced similar situation , I need some help.

AFAIK, you can’t use resnext with fastai in kaggle yet. Would need a code update.

I’m new to this fastai . what can I do something for that code update ? @imrandude

@z0k . did you come across this type of situation . I see that here How can I load a pretrained model on Kaggle using fastai? … Can you please suggest a suitable solution .

@z0k, I tried setting the path to current directory, but it didnt work out for me.

well that has nothing to do with resnext not working.you should give it the tmp and model paths to fix that:

TMP_PATH = “/tmp/tmp”
MODEL_PATH = “/tmp/model/”

then in convlearner,pass them as tmp and model paths:

learn = ConvLearner.pretrained(arch, data, precompute=True, tmp_name=TMP_PATH, models_name=MODEL_PATH)

but the resnext101 won’t work on kaggle,don’t know why.just use another structure.