search

weiguoPian / AV-CIL_ICCV2023

19 stars 1 forks source link

Training time and GPU information #2

Open yswang1717 opened 10 months ago

yswang1717 commented 10 months ago

Could you please share the required time for training in each experiment and relevant GPU information? Thanks !

yswang1717 commented 10 months ago

It would be really appreciated if you also share the required GPU memory to reproduce the paper performance.

weiguoPian commented 10 months ago

Hello, Thank you for your interest in our work. We run all the experiments on a single RTX A5000 GPU with 24GB GPU memory. With the pre-extracted features and an extire A5000 GPU, it only takes several hours to run one single experiment.

Bests,

yswang1717 commented 10 months ago

Thanks for the quick response!

Redredhorse commented 7 months ago

Hello, have you successfully reached the author's experimental results? My accuracy is only 52%

weiguoPian commented 7 months ago

Hello, have you successfully reached the author's experimental results? My accuracy is only 52%

Hello,

Do you run the experiments with our default setting?

Bests,

Redredhorse commented 7 months ago

您好，请问您成功达到作者的实验结果了吗？我的准确率只有52%

你好，

您是否使用我们的默认设置运行实验？

最好的， image

I ran train_incremental_ours.py. As shown above, here are the results of my experiment. The GPU I use is V100. Regarding audio and video feature extraction, I directly use the extracted features you shared.I refer to the settings in the paper. My experimental settings is shown below. I am very confused why the experimental result is only 52%. Hope to get your answer.Thank you so much. image

weiguoPian commented 7 months ago

您好，请问您成功达到作者的实验结果了吗？我的准确率只有52%

你好， 您是否使用我们的默认设置运行实验？ 最好的， image

I ran train_incremental_ours.py. As shown above, here are the results of my experiment. The GPU I use is V100. Regarding audio and video feature extraction, I directly use the extracted features you shared.I refer to the settings in the paper. My experimental settings is shown below. I am very confused why the experimental result is only 52%. Hope to get your answer.Thank you so much. image

Thank you for your reply.

It seems that the hyperparameters of 'instance_contrastive', 'class_contrastive', and 'attn_score_distil' are all set to False in your experiment.

You can use our provided run_incremental_ours.sh to run your experiment directly. Please refer to sh run_incremental_ours.sh 'dataset'.

Bests,