When should training be stopped?

[YY-RR-ZZ]

Hello,Thank you very much for your open-source work.
I have a question regarding the visualization of the loss generated while running train_sketch.py. Below is the visualization of the validation loss. The training reached 290,000 steps and epoch 7, but the loss does not show signs of convergence. I am unsure when the training should be considered complete.
Could you please provide some guidance on this?

[Yonghao-Yu]

Where did you download the training data from?
data/LAION_6plus
data/WebDataset

[cuhkfz]

@YY-RR-ZZ
Hello, I encountered the same problem. Have you finished the training successfully?

[cuhkfz]

@YY-RR-ZZ
Hello, I encountered the same problem. Have you finished the training successfully?

[Yonghao-Yu]

@YY-RR-ZZ Hello, I encountered the same problem. Have you finished the training successfully?

hi，how you get the train data？
data/LAION_6plus
data/WebDataset

[cuhkfz]

@Yonghao-Yu Hello yonghao, I use COCO dataset, the original T2I Adapter with sd v1-4 as backbone.

[Yonghao-Yu]

@Yonghao-Yu Hello yonghao, I use COCO dataset, the original T2I Adapter with sd v1-4 as backbone.

Yes, the paper mentions using the COCO17 dataset and using pidinet to extract edges. But I don’t know the details, such as the data format, etc. Did you make the dataset yourself? Is there a tutorial I can follow? Or where can I download the dataset so that I can use it directly? Thank you very much!

[cuhkfz]

@Yonghao-Yu Hello yonghao, I use COCO dataset, the original T2I Adapter with sd v1-4 as backbone.

Yes, the paper mentions using the COCO17 dataset and using pidinet to extract edges. But I don’t know the details, such as the data format, etc. Did you make the dataset yourself? Is there a tutorial I can follow? Or where can I download the dataset so that I can use it directly? Thank you very much!

Just download the required coco dataset, and run train_sketch.py. The only pre-process I did was create train_color/val_color.

[Yonghao-Yu]

@Yonghao-Yu Hello yonghao, I use COCO dataset, the original T2I Adapter with sd v1-4 as backbone.

Yes, the paper mentions using the COCO17 dataset and using pidinet to extract edges. But I don’t know the details, such as the data format, etc. Did you make the dataset yourself? Is there a tutorial I can follow? Or where can I download the dataset so that I can use it directly? Thank you very much!

Just download the required coco dataset, and run train_sketch.py. The only pre-process I did was creating train_color/val_color. But the training does not converge.

I see, I'll try again, thanks again.

[Windrain7]

Just download the required coco dataset, and run train_sketch.py. The only pre-process I did was create train_color/val_color.

Hello, could you tell me how to set the parameters of train_sketch.py?

[Junxix]

@Yonghao-Yu Hello yonghao, I use COCO dataset, the original T2I Adapter with sd v1-4 as backbone.

Yes, the paper mentions using the COCO17 dataset and using pidinet to extract edges. But I don’t know the details, such as the data format, etc. Did you make the dataset yourself? Is there a tutorial I can follow? Or where can I download the dataset so that I can use it directly? Thank you very much!

Just download the required coco dataset, and run train_sketch.py. The only pre-process I did was create train_color/val_color.

Hello, how can I set the configuration since dataset_laion.py only describes the laion's format?

[ydniuyongjie]

Hello,Thank you very much for your open-source work. I have a question regarding the visualization of the loss generated while running train_sketch.py. Below is the visualization of the validation loss. The training reached 290,000 steps and epoch 7, but the loss does not show signs of convergence. I am unsure when the training should be considered complete. Could you please provide some guidance on this?
What is your batch size? You've iterated 290,000 steps, and the epoch is already at 7. How many GPUs are you using?