Chaoran Fu

same problem and I am using my own datasets

@lrhjw did you solve it? i got same problem

same question here, I tried onnx.export(),but it is too hard, and have a lot of forward() input issue. so does any one have idea?

same question in here, backbone is EfficientNet

> > How is your config file set? > > project_name: tea_swin_t exp_name: T3000 use_wandb: True wandb_entity: dechenzhu train_root: D:\hxy\FGVC-PIM-master\dataset\data3 val_root: D:\hxy\FGVC-PIM-master\dataset\test1 data_size: 448 num_workers: 2 batch_size: 8 model_name: efficient...

ok, timm 0.4.12 works

I got issues in create_dataset and create_loader, they doesnet have "download", and "num_aug_repeats" so timm 0.4.12 is not suitable