Soccernet-features icon indicating copy to clipboard operation
Soccernet-features copied to clipboard

Feature extraction and feature extractor training for Soccernet videos.

Results 6 Soccernet-features issues
Sort by recently updated
recently updated
newest added

I am trying to run this predict.py for FootBall repo section, but, it is not utilizing cuda. May I ask that what could be the reason that it is using...

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?

Hi. I have a problem with the shape of features. The Soccernet features I can download have a shape of (2700, 8576), but I do inference of a video I...

我尝试run代码的过程中会出现这样的warning, LAUNCH WARNING 2024-02-06 16:33:57,191 save gpu log failed,但是过一段时间代码会终止, LAUNCH INFO 2024-02-06 16:37:17,839 Exit code -9。没有其他的信息,我想知道该如何解决。 谢谢。

After runing about 8 batch, it returns bug Fail to perform transform [] with error: index 333 is out of bounds for axis 0 with size 327 and stack: Traceback...

在尝试利用该模型进行推理,解决Action Spotting问题的过程中,对有一些步骤感到疑惑,烦请解答。 在README中,作者写到 *“In the new feature, the feature dimension is reduced to just 768, 3489 is the number of frames.”* ,其中 *number of frames* 在中文语境下指的是什么?我在尝试的过程中发现feature.shape[0]的值和config.json中设置的 `length_secs` 有关,在 `length_secs` 较短的情况下...