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

为什么训练时没有保存图像 #198

Open
CQxiaocaimi opened this issue Sep 28, 2023 · 1 comment
Open

为什么训练时没有保存图像 #198

CQxiaocaimi opened this issue Sep 28, 2023 · 1 comment
Assignees

Comments

@CQxiaocaimi
Copy link

训练ControlNet时,设置了 --logging_steps 5 \和--image_logging_steps 10 \,但是没有日志和图像,我没有改动过代码,为什么呢?

@JunnYu
Copy link
Member

JunnYu commented Oct 10, 2023

export FLAGS_conv_workspace_size_limit=4096
python -u train_txt2img_control_trainer.py \
    --do_train \
    --output_dir ./sd15_control \
    --per_device_train_batch_size 4 \
    --gradient_accumulation_steps 1 \
    --learning_rate 1e-5 \
    --weight_decay 0.02 \
    --lr_scheduler_type "constant" \
    --warmup_steps 0 \
    --sd_locked True \
    --max_steps 10000000 \
    --logging_steps 5 \
    --image_logging_steps 10 \
    --save_steps 2000 \
    --save_total_limit 2 \
    --seed 23 \
    --dataloader_num_workers 4 \
    --pretrained_model_name_or_path runwayml/stable-diffusion-v1-5 \
    --max_grad_norm -1 \
    --file_path ./fill50k \
    --recompute True \
    --overwrite_output_dir

你好,如果使用上面的代码运行的话,会有日志文件保存在sd15_control目录的,同时你需要确保你安装了visualdl这个工具。

# 使用这个命令查看日志
visualdl --logdir ./sd15_control 

image

image

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