Hi @pbaylies, sorry to ask such naive question. But I'm a little confused about the policy to train an encoder network. Here are my detailed questions.
Can the encoder be trained in minibatch? or it should be optimized for each image?
--- Because I found it I set batchsize=8, the generated images seems crashed. So I wonder if the encoder should be optimized for every single image?
The pretrained resnet provided by you is trained on imagenet or other datasets? Could you simply explain the training details, such as trained on which dataset, and which losses you adopt?
Hi @pbaylies, sorry to ask such naive question. But I'm a little confused about the policy to train an encoder network. Here are my detailed questions.
Can the encoder be trained in minibatch? or it should be optimized for each image? --- Because I found it I set batchsize=8, the generated images seems crashed. So I wonder if the encoder should be optimized for every single image?
The pretrained resnet provided by you is trained on imagenet or other datasets? Could you simply explain the training details, such as trained on which dataset, and which losses you adopt?