Open Huang9495 opened 6 years ago
Hi, (1) yes, sometimes we will reconstruct the generated image.
(2) In the paper, after finish training on 300wLP and Multi-PIE dataset, we will train 10 more epochs with CelebA dataset. Currently we are preparing another paper, and the modified codes will be updated later.
You can improve the generation performance by training with more datasets, as long as you can generate view labels for them.
(3) The text files are generated from 300wLP's mat files, their mat files contain pose information, and I use them to create view labels for 300wLP data.
Thanks you! @bluer555 Looking forward to your update.
@bluer555 Thanks for your answer, and I want to know the detail that how to achieve creating view labels for 300wLP data. Can you provide me with code of this transform or tell me where to download the code of this transform?
@Huang9495 did you find out the code for finding out view labels for 300wLP?
Sorry to interrupt, @bluer555 , and I am still wondering that have you updated the new version of the code? Because my master degree's paper is based on your paper. I'm struggling with some of the details of your released code. In this case , hope it doesn't bother you to update the code at your convenience and I am looking forward to your helpful reply. Thank you.
Thank you for @bluer555 provice this code of your paper for me. Three issues in the code of your paper that confuse me. So, I want to ask you for help.
(1) In the code:in the train.py ,you init the variable tmp with random.uniform(0,1) and tmp decide to the reconstruction, after tmp = torch.LongTensor(idexs), the content of tmp is about the angle of image. So I want to know what the tmp represent and the reconstruction is random?
(2) In your paper and code: In the 4.1 section of your paper, It shows that we train 10 more epochs in self-supervised learning. But I don't know where the epoch of self-supervised learning in your code except the 25 epochs in supervised learning?
(3) In the dataset, the dataset named crop0907 resize image of 300W_LP, and I want to know how to genera the txt of 300w_LP_size_128?
Thanks for your help! @bluer555