linfengWen98 / CAP-VSTNet

[CVPR 2023] CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer
MIT License
120 stars 8 forks source link

Fine-tune instructions. #12

Open yong3yuan3yong4 opened 10 months ago

yong3yuan3yong4 commented 10 months ago

Thank you for your excellent work. Could you provide instructions on how to fine-tune your pretrained model using my own dataset? I'd appreciate it."

linfengWen98 commented 10 months ago

You can insert the following code into line 83 of train.py

ckpoint = 'xxx.pt'  # checkpoints/photo_image.pt , checkpoints/art_image.pt
state_dict = torch.load(ckpoint)
RevNetwork.load_state_dict(state_dict['state_dict'])
linfengWen98 commented 9 months ago

Sorry, I find an error in the fine-tuning. Please update the code!