search

zhangmozhe / Deep-Exemplar-based-Video-Colorization

The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".
https://arxiv.org/abs/1906.09909
MIT License
341 stars 76 forks source link

Train the model #12

Open Zonobia-A opened 3 years ago

Zonobia-A commented 3 years ago

I have no idea to train a new model on my dataset, if the author can provide a tiny dataset sample.

rleaver152 commented 3 years ago

I'd like that too - a simple 'how to' walkthrough assuming knowledge of Python :-)

sciart17 commented 2 years ago

I hope so too. Thanks a lot!

songyn95 commented 2 years ago

@Zonobia-A @rleaver152 @sciart17 @zhangmozhe Can you train normally? I am currently troubled by this problem. If you solve it, can you provide a detailed description，Thank you very much

ndhieunguyen commented 1 year ago

Is there anyone who has the dataset? It's very nice if I am shared in order to train the model. Thank you very much

AsserOssama commented 1 year ago

@ndhieunguyen did u know the structure of the dataset to train the model? Thank you very much

yyang181 commented 8 months ago

I wrote a dataloader purposed to manage the training process. Kindly examine an exemplar below which shows the dataloader at: https://github.com/yyang181/NTIRE23-VIDEO-COLORIZATION/blob/main/BiSTNet-NTIRE2023/lib/videoloader_woAugImg.py#L1332C1-L1454C31.

Note that the computation of the optical flow between two sequential frames—specifically, flow_forward and flow_backward—might pose some complexities. A strategy I highly recommend to navigate this issue involves the prior computation of the optical flow. It is vitally important to ensure that it is coherently loaded in conjunction with the input images and references.

Please be aware that the authors also offer a script dedicated to the calculation of the optical flow. This valuable resource can be accessed via the following link: https://github.com/zhangmozhe/Deep-Exemplar-based-Video-Colorization/blob/main/lib/videoloader_imagenet.py#L199C13-L215C14.

Hope this helps.