jiangsutx/SRN-Deblur

Using own image post-training

Closed this issue · 1 comments

jpds commented

Quick question: after one has trained the model on the go-pro dataset - how can I then input a random blurry picture into the model to have it generate a non-blurred image?

You can put your trained model inside checkpoints\ folder, then test images in the same way as using our pre-trained models.