-
Notifications
You must be signed in to change notification settings - Fork 10
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
关于预训练权重 #7
Comments
我不确定你是用我的代码跑的,还是自己复现的呢? 从你说的我不太能明白问题出在哪,或许你可以多提供一些信息? |
我是使用您提供的代码在RTX3090下跑的,就改了数据集路径和权重的路径,我尝试输出了一下481.9MB的和1.1G的两个pth文件中l的key和value,然后查看了其中model部分的value.size()和value.dtype,两者都是torch.float32类型的以及层数和形状都一样。不知道为什么文件大小相差如此巨大。 |
我也不太确定为什么会这样。。 不过其实问题不大(大概) |
尊敬的大佬您好,感谢您的杰出的工作!!
我正在尝试复现您的代码,我发现您提供的在FSC147上Fine-tuned weights文件FSC147.pth大小为1.1G
我从头开始训练,在Pretrain on FSC147阶段得到的权重文件大小是1.3G,大小与您提供的pretrain.pth文件(1.3G)吻合
但是,在Finetune on FSC147阶段
选用mae_vit_base_patch16参数最后得到的pth文件大小为481.9MB
选用mae_vit_base6_patch16 = mae_vit_base_patch16_fim6参数训练后得到的权重文件大小674.5MB
这与您最终分享的权重FSC147.pth1.1G相差过大
我该如何才能够得到正确大小的权重文件
您是否能解答我的疑惑
The text was updated successfully, but these errors were encountered: