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

Pretrain-model输出的cls_score_all、event_times含义 #7

Open
RyanYChen opened this issue Feb 22, 2024 · 3 comments
Open

Pretrain-model输出的cls_score_all、event_times含义 #7

RyanYChen opened this issue Feb 22, 2024 · 3 comments

Comments

@RyanYChen
Copy link

RyanYChen commented Feb 22, 2024

您好,我下载pretrain-model后,使用以下命令,跑10s视频的inference
python3.7 -B -m paddle.distributed.launch --gpus='0' --log_dir=$LOG_DIR main.py --test -c data/soccernet_inference/soccernet_pptimesformer_k400_one_file_inference.yaml -w $WEIGHT_FILE -o inference_dir=$INFERENCE_DIR -o DATASET.test.file_path=$VIDEO_CONFIG

在结果文件中, cls_score_all.shape: [5, 1, 18], event_times.shape: [5, 1, 18], 请问下这里18维对应的label顺序是什么,以及event_times代表什么含义?

@RyanYChen RyanYChen changed the title Pretrainmodel输出的cls_score_all、event_times含义 Pretrain-model输出的cls_score_all、event_times含义 Feb 22, 2024
@paulxinzhou
Copy link
Collaborator

cls_score_all 和 event_times暂时不用管,当时是为了end 2 end训练预留的,但是后来没来的及实现,所以现在暂时没什么用,feature key下面的数才有用。

@realsazzad
Copy link

Hello @paulxinzhou , What these 'features' data mean?
Sorry for asking but really getting a hard time to understand the inference result.

@paulxinzhou
Copy link
Collaborator

@realsazzad I added some explanation here. https://github.com/baidu-research/Soccernet-features/blob/develop/README.md#understanding-the-result-features

Let me know if there's still confusion.

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

3 participants