search

SwinTransformer / Swin-Transformer-Object-Detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.
https://arxiv.org/abs/2103.14030
Apache License 2.0
1.79k stars 378 forks source link

MaskRCNN: SwinTransformer: __init__() got an unexpected keyword argument 'embed_dim' #84

Closed 7xjerry1 closed 3 years ago

7xjerry1 commented 3 years ago

When i ran demo with python demo/image_demo.py demo/demo.jpg configs/swin/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco.py,it appears this ERROR"MaskRCNN: SwinTransformer: init() got an unexpected keyword argument 'embed_dim" Can u guys help me?thanks a lot

LL3RD commented 3 years ago

I met this problem too and i solved it by run python setup.py develop in Swin-Transformer-Object-Detection folder

7xjerry1 commented 3 years ago

thanks a lot :) i solved this problem yesterday by downloading mmdetection and running its original swinT ---原始邮件--- @.> 发送时间:2021年9月8日 星期三 下午2:1 @.> @.**@.> 主题:Re: [SwinTransformer/Swin-Transformer-Object-Detection] MaskRCNN: SwinTransformer: init() got an unexpected keyword argument 'embed_dim' (#84)

I met this problem too and i solved it by runpython setup.py developin Swin-Transformer-Object-Detection folder

— You are receiving this because you authored the thread. Reply to this email directly,view it on GitHub, orunsubscribe. Triage notifications on the go with GitHub Mobile foriOSorAndroid.

LaCandela commented 3 years ago

I met this problem too and i solved it by run python setup.py develop in Swin-Transformer-Object-Detection folder

Thanks, this solved the issue for me. I wonder how you found this solution. :)

luckychay commented 2 years ago

embed_dim --> embed_dims