search

huggingface / pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
https://huggingface.co/docs/timm
Apache License 2.0
30.65k stars 4.63k forks source link

[BUG] Swin transformer #2201

Closed FranciscoPark closed 3 weeks ago

FranciscoPark commented 3 weeks ago

Describe the bug model = models.swin_b(pretrained=None,progress=False,stochastic_depth_prob=0.5,num_classes =100) I am getting TypeError: torchvision.models.swin_transformer._swin_transformer() got multiple values for keyword argument 'stochastic_depth_prob'

To Reproduce Steps to reproduce the behavior:

  1. model = models.swin_b(pretrained=None,progress=False,stochastic_depth_prob=0.5,num_classes =100)
  2. then run py

Expected behavior it should just run with give arguments

Desktop (please complete the following information):

rwightman commented 3 weeks ago

not timm