We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
作者您好,我在自己的数据集上进行训练,但是发现batch size最大只能设置为2,显卡是4090,这正常吗? 同时,训练完30个epoch后输出的日志如下:
image_to_text_mean_rank: 49.3377 image_to_text_median_rank: 46.0000 image_to_text_R@1: 0.0110 image_to_text_R@5: 0.0476 image_to_text_R@10: 0.0993 text_to_image_mean_rank: 49.0875 text_to_image_median_rank: 47.0000 text_to_image_R@1: 0.0110text_to_image_R@5: 0.0549 text_to_image_R@10: 0.1098 clip_val_loss: 0.6896 epoch: 30.0000 num_samples: 2458.0000
这是否有问题?
The text was updated successfully, but these errors were encountered:
Batch size为2应该不行。contrastive learning需要batch size越大越好,你可以测试一下呢。
Sorry, something went wrong.
但是我在24G显存上最大也只能设置为4,但我看其他人可以设置到768,这正常吗,ViT-L和ViT-B差距不会这么大吧
clip还有个text encoder,所以会比较大一些,你可以试一下vit-b32
请问image_to_text_R和 text_to_image_R只有0.1左右正常吗,图片是2400多张,但是运行evaluate.py结果还行,图片跟文本能够对应上
No branches or pull requests
作者您好,我在自己的数据集上进行训练,但是发现batch size最大只能设置为2,显卡是4090,这正常吗?
同时,训练完30个epoch后输出的日志如下:
这是否有问题?
The text was updated successfully, but these errors were encountered: