-
Notifications
You must be signed in to change notification settings - Fork 29
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
请问具体训练细节 #41
Comments
只试了一下ISTD;先训练FusionNet,然后训练RefineNet,具体怎么训练可以看作者的说明。因为是分阶段训练的,所以会涉及到一些模型保存和加载的步骤,建议先看一遍必要部分的代码。 |
谢谢您的回复,我再好好看看代码
…---原始邮件---
发件人: ***@***.***>
发送时间: 2022年4月20日(周三) 下午3:51
收件人: ***@***.***>;
抄送: "yufang ***@***.******@***.***>;
主题: Re: [tsingqguo/exposure-fusion-shadow-removal] 请问具体训练细节 (Issue #41)
只试了一下ISTD;先训练FusionNet,然后训练RefineNet,具体怎么训练可以看作者的说明。因为是分阶段训练的,所以会涉及到一些模型保存和加载的步骤,建议先看一遍必要部分的代码。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
可以跟您请问一下训练细节吗 |
1是的,只有c不一样
…---原始邮件---
发件人: ***@***.***>
发送时间: 2023年7月4日(周二) 晚上8:24
收件人: ***@***.***>;
抄送: "yufang ***@***.******@***.***>;
主题: Re: [tsingqguo/exposure-fusion-shadow-removal] 请问具体训练细节 (Issue #41)
1.ISTD和ISTD+是不是只有train_c不一样,其他的文件夹下放的图片都一样 2.代码的运行顺序是什么?能详细说一下吗
可以请教一下训练细节吗,我用gitbash生成的指令
python -u ./OE_train.py --loadSize 256 --randomSize --name MFusion_expo_param_b2_lr0.0001_L110_n5_ks3_vfixed5-1-loss_adam_lambda_10.0_TV0G0.0PG0.1 --dataroot D:\PycharmProjects\exposure-fusion-shadow-removal-main\data_processing\dataset\ISTD --checkpoints_dir D:/PycharmProjects/exposure-fusion-shadow-removal-main/log --fineSize 256 --model Fusion --batch_size 2 --randomSize --keep_ratio --phase train_ --gpu_ids 0 --lr 0.0001 --lambda_L1 10 --num_threads 1 --dataset_mode expo_param --mask_train D:\PycharmProjects\exposure-fusion-shadow-removal-main\data_processing\dataset\ISTD/train_NOTUSE --optimizer adam --n 5 --ks 3 --lr_policy lambda --lr_decay_iters 50 --shadow_loss 10.0 --rks 3 --tv_loss 0 --grad_loss 0.0 --pgrad_loss 0.1 --load_dir None --save_epoch_freq 100 --niter 50 --niter_decay 350,去运行OE_train.py报错:
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
大佬请问你这个模型成功跑通了吗,我在用其他数据集训练该模型时,在训练的第三十批次出现了参数问题,看了好久不知道如何解决该问题 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1.ISTD和ISTD+是不是只有train_c不一样,其他的文件夹下放的图片都一样
2.代码的运行顺序是什么?能详细说一下吗
The text was updated successfully, but these errors were encountered: