Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Where can I find the <PRETRAIN_MODEL>? #13

Closed
wsh-nie opened this issue Aug 16, 2021 · 4 comments
Closed

Where can I find the <PRETRAIN_MODEL>? #13

wsh-nie opened this issue Aug 16, 2021 · 4 comments

Comments

@wsh-nie
Copy link

wsh-nie commented Aug 16, 2021

Hi, thanks for this fascinating work!
I want to follow the instructions bash tools/dist_train.sh <CONFIG_FILE> <GPU_NUM> --cfg-options load_from=<PRETRAIN_MODEL> [model.backbone.use_checkpoint=True] [other optional arguments] to run the program, but I don't know where I can find the pretrain model.
So, I need some help, thanks all of you!

@wsh-nie wsh-nie changed the title Download Where can I find the <PRETRAIN_MODEL>? Aug 16, 2021
@r-kellerm
Copy link

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

@hust-nj
Copy link
Member

hust-nj commented Sep 7, 2021

@wsh-nie We included pretrained model link in readme
image

@hust-nj hust-nj closed this as completed Sep 7, 2021
@AnupKumarGupta
Copy link

The Baidu shows incorrect credentials for the code swim.

@hayleeXinyi
Copy link

hayleeXinyi commented Sep 29, 2023

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'

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants