roatienza / deep-text-recognition-benchmark

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)
Apache License 2.0
284 stars 57 forks source link

timm==0.4.5 ModuleNotFoundError: No module named 'timm.models.layers.patch_embed' #40

Closed sh1man closed 7 months ago

sh1man commented 7 months ago

I updated the version to 0.4.9, but then there is an error AttributeError: 'GELU' object has no attribute 'approximate'

roatienza commented 7 months ago

Timm has undergone many changes. This repo was only tested on timm==0.4.5.