Junlin Han

Hi, You need 1: install pytorch fid pip install pytorch-fid 2: Use this command python -m pytorch_fid A B where A, B are the path of two folders

> Hi，can you provide me with trained SIMDCL models? Hi, Unfortunately, I currently do not have a copy of pretrained SimDCL models... (the HPC I'm using has a quota limit...

> May I ask if the comparison experiment was retrained by you? This looks like a lot of work. Sure. We only retrain some of them (CUT FASTCUT CYCLEGAN MUNIT),...

> Are the comparison experiments copied from previous papers (e.g. horse to zebra images) obtained by running the pre-trained model? If we retrained the model, the result is based on...

> Thank you very much for replying to so many of my questions. I trained the code you provided (the dataset is horse to zebra) and got a FID of...

> Thank you very much for replying to so many of my questions. I trained the code you provided (the dataset is horse to zebra) and got a FID of...

> The batchsize should be 1 for unsupervised image-to-image translation methods. (This has been studied in previous work like CycleGAN). For almost all computer vision tasks, changing the total batchsize...

Hi, thanks for your interest in our work! We didn't try using YOCO for detection tasks directly. You might try applying YOCO to photometric transformations, such as color jitter. I...

Hello, You might need to change the name during training. (But even you didn't change it, you can manually change the checkpoint folder name). The name of checkpoint folder is...

Hello NONI, Thanks for your suggestions! Unfortunately I'm not very faimiliar with how to design a colab notebook version... I guess this colab version of CycleGan might be helpful: https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/generative/cyclegan.ipynb