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

预训练权重 #1

Open
chiukin opened this issue Oct 26, 2023 · 2 comments
Open

预训练权重 #1

chiukin opened this issue Oct 26, 2023 · 2 comments

Comments

@chiukin
Copy link

chiukin commented Oct 26, 2023

作者你好,想问下,
在training里面:Noting: the pre_trained RGB should be saved at './checkpoints/spatial', pre_trained depth shoule be saved at './checkpoints/depth' and flow is same.
请问这三个权重是否均为resnet34的权重呢? 如果不是,那是怎么训练出来的权重呢?

@WindMirror1108
Copy link
Collaborator

并不是resnet34的权重,我们在论文的V.B这一节说明了采用预训练的策略。在code中提供了pretrain_depth.py进行分支的预训练。

@chiukin
Copy link
Author

chiukin commented Oct 27, 2023

@WindMirror1108 明白,想再问个细节,三个stream的预训练代码是一样的吧,区别是只要改下[pretrain_depth.py]里面112行,label, depth = data_batch['label'], data_batch['depth'] 可以改成‘image'或'flow'就行是吧。
另外就是train.py里面108行, # net_bone = Model(3, mode=config.mode, model_path=config.model_path),这是另一种训练策略,即不对三个stream进行预训练是吧,这性能会差点是吧?

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

2 participants