Where can I find the <PRETRAIN_MODEL>? about video-swin-transformer

[hust-nj]

@wsh-nie We included pretrained model link in readme

[r-kellerm]

You can find the pretrained models in the column "model" for each dataset, under https://github.com/SwinTransformer/Video-Swin-Transformer.
E.g.

[AnupKumarGupta]

The Baidu shows incorrect credentials for the code swim.

[hayleeXinyi]

Hi, are there any mismatches occurring? I find that when I set it as below I can inference normally

config_file = '/home/haylee/Video-Swin-Transformer/mmaction2/tsn_imagenet-pretrained-r50_8xb32-1x1x8-100e_kinetics400-rgb.py'
checkpoint_file = '/home/haylee/Video-Swin-Transformer/mmaction2/tsn_imagenet-pretrained-r50_8xb32-1x1x8-100e_kinetics400-rgb_20220906-2692d16c.pth'

But setting it to the following reasoning reports an error

config_file = '/home/haylee/Video-Swin-Transformer/configs/recognition/tsn/tsn_r50_video_inference_1x1x3_100e_kinetics400_rgb.py'
checkpoint_file = '/home/haylee/Video-Swin-Transformer/checkpoints/tsn_r50_1x1x3_100e_kinetics400_rgb_20200614-e508be42.pth'

Error as below:

Exception has occurred: TypeError
class 'Normalize' in mmcv/transforms/processing.py: Normalize.__init__() got an unexpected keyword argument 'to_bgr'
TypeError: Normalize.__init__() got an unexpected keyword argument 'to_bgr'

During handling of the above exception, another exception occurred:

  File "/home/haylee/Video-Swin-Transformer/mmaction2/mmaction/apis/inference.py", line 79, in inference_recognizer
    test_pipeline = Compose(test_pipeline_cfg)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/haylee/Video-Swin-Transformer/demo/haylee_demo.py", line 12, in <module>
    pred_result = inference_recognizer(model, video_file)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: class 'Normalize' in mmcv/transforms/processing.py: Normalize.__init__() got an unexpected keyword argument 'to_bgr'