sunshineatnoon
commented
4 years ago Hi, we target at the task of arbitrary style transfer, where we transfer style from a single style image to a single content image. In the training code, I have a two dataloaders for the content images and style images respectively, each time a random pair of (content, style) is used for training.
After training, you can transfer styles from multiple images onto a single content image by feature interpolation. But during training, we only use a random pair of style image and content image each time.
Hello, how about style migration (without GAN), in the training process, can you use multiple pictures to train multiple pictures? The following is an example:
Suppose there are 3 pictures in category A and 3 pictures in category B. In the network training process, the first batch: A1 A2 corresponds to B1 training; the second batch A1 A2 corresponds to B2 training; the third batch A2 A3 corresponds to B3 Training, is this ok?
I checked your code and can only train multiple pictures for one picture. Maybe I understand the wrong code. Please feel free to answer my questions. Thank you very much.
您好，请问风格迁移(不使用GAN)，在训练过程中，可以使用多张图片对应多张图片训练么？如下是一个例子：
假设A类有3张图片，B类也有3张图片，在网络训练过程中，第一批次：A1 A2 对应B1训练；第二批次A1 A2对应B2训练；第三批次A2 A3对应B3训练，这样可以么？
我查阅了您的代码，只能多张图片对应一张图片进行训练，也许是我理解错了您的代码，请您在闲暇之余，能解答一下我的疑问，十分感谢。