search

insitro / ChannelViT

Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words
https://arxiv.org/abs/2309.16108
Other
46 stars 6 forks source link

Unable to locate credentials #9

Open aquorio15 opened 2 months ago

aquorio15 commented 2 months ago

I am trying to run the baseline code by I am getting the following error 'Unable to locate credentials'. I think this is most probably due to amazon s3

ctk3b commented 2 months ago

Hi there, could you share the code your invoking and the traceback?

aquorio15 commented 2 months ago

Hi I am trying to run the baseline results for channelViT without HCS. Basically, I am using the command line argument as provided in the repo. I am getting the error right after loading the test and validation set.

python channelvit/main/main_supervised.py \
    trainer.devices=8 \
    trainer.max_epochs=100 \
    meta_arch/backbone=channelvit_small \
    meta_arch.backbone.args.in_chans=8 \
    meta_arch.target='label' \
    meta_arch.num_classes=161 \
    data@train_data=jumpcp \
    data@val_data_dict=[jumpcp_val,jumpcp_test] \
    train_data.jumpcp.loader.batch_size=32 \
    transformations@train_transformations=cell \
    transformations@val_transformations=cell