[BUG] MLP fail to start

[fpshuang]

Describe the bug
fail to train MLP

To Reproduce
Steps to reproduce the behavior:

1. ./distributed_train.sh 2 /imagenet/ --model mixer_s32_224

Behavior
run: job 2351504 queued and waiting for resources srun: job 2351504 has been allocated resources Training with a single process on 1 GPUs. Training with a single process on 1 GPUs. Traceback (most recent call last): File "train.py", line 798, in <module> main() File "train.py", line 362, in main checkpoint_path=args.initial_checkpoint) File "/mnt/lustre/huangpengsheng/pernalEx/mlp_vit/pytorch-image-models/timm/models/factory.py", line 81, in create_model model = create_fn(pretrained=pretrained, **kwargs) File "/mnt/lustre/huangpengsheng/pernalEx/mlp_vit/pytorch-image-models/timm/models/mlp_mixer.py", line 182, in mixer_s32_224 model = _create_mixer('mixer_s32_224', pretrained=pretrained, **model_args) File "/mnt/lustre/huangpengsheng/pernalEx/mlp_vit/pytorch-image-models/timm/models/mlp_mixer.py", line 172, in _create_mixer **kwargs) File "/mnt/lustre/huangpengsheng/pernalEx/mlp_vit/pytorch-image-models/timm/models/helpers.py", line 434, in build_model_with_cfg model = model_cls(**kwargs) if model_cfg is None else model_cls(cfg=model_cfg, **kwargs) TypeError: __init__() got an unexpected keyword argument 'drop_rate' Traceback (most recent call last): File "train.py", line 798, in <module> main() File "train.py", line 362, in main checkpoint_path=args.initial_checkpoint) File "/mnt/lustre/huangpengsheng/pernalEx/mlp_vit/pytorch-image-models/timm/models/factory.py", line 81, in create_model model = create_fn(pretrained=pretrained, **kwargs) File "/mnt/lustre/huangpengsheng/pernalEx/mlp_vit/pytorch-image-models/timm/models/mlp_mixer.py", line 182, in mixer_s32_224 model = _create_mixer('mixer_s32_224', pretrained=pretrained, **model_args) File "/mnt/lustre/huangpengsheng/pernalEx/mlp_vit/pytorch-image-models/timm/models/mlp_mixer.py", line 172, in _create_mixer **kwargs) File "/mnt/lustre/huangpengsheng/pernalEx/mlp_vit/pytorch-image-models/timm/models/helpers.py", line 434, in build_model_with_cfg model = model_cls(**kwargs) if model_cfg is None else model_cls(cfg=model_cfg, **kwargs) TypeError: __init__() got an unexpected keyword argument 'drop_rate'
Screenshots
If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

• OS: [Ubuntu 16.04]