search

MrBlankness / LightM-UNet

Pytorch implementation of "LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation"
https://arxiv.org/abs/2403.05246
Apache License 2.0
279 stars 25 forks source link

How to change the batch size and the number of epochs when training? #18

Open HelloZjuLearner opened 6 months ago

HelloZjuLearner commented 6 months ago

When use nnunetV2 before, the author told us to add a new class with the number of X epochs in nnunettrainer_Xepochs, and replace the nnunettrainer with nnunettrainer_Xepochs when training,does it still work in lightMunet? When changing batchsize , i went to the nnunetPlans.json, and it looks like going well , i would appreciate it if anybody could tell me how to change these two values.

Hollycooool commented 5 months ago

Have you solved this problem? I would like to know the reason why we "add a new class with the number of X epochs in nnunettrainer_Xepochs, and replace the nnunettrainer with nnunettrainer_Xepochs when training“

HelloZjuLearner commented 5 months ago

yes,you can straight go to the file "nnUnetTrain.py"(or similar name)，and change the "self.num_epochs" to your desired number.

"add a new class with the number of X epochs in nnunettrainer_Xepochs, and replace the nnunettrainer with nnunettrainer_Xepochs when training' is the method the author of nnunetV2 told us to do when changing epoch.

-----原始邮件----- 发件人:Hollycooool @.> 发送时间:2024-05-07 16:13:12 (星期二) 收件人: MrBlankness/LightM-UNet @.> 抄送: HelloZjuLearner @.>, Author @.> 主题: Re: [MrBlankness/LightM-UNet] How to change the batch size and the number of epochs when training? (Issue #18)

Have you solved this problem? I would like to know the reason why we "add a new class with the number of X epochs in nnunettrainer_Xepochs, and replace the nnunettrainer with nnunettrainer_Xepochs when training“

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>