GL Li comments

Results 12 comments of


                                            GL Li

AttGAN RuntimeERROR:Sizes of tensors must match except in dimension 1

CUDA_VISIBLE_DEVICES=0 \ python train.py \ --data CelebA-HQ \ --img_size 128

AttGAN RuntimeERROR:Sizes of tensors must match except in dimension 1

I did not change any of your code. And I train STGAN and STARGAN on this dataset without any error. It seems like a new layer named Generator-40 is created...

I am puzzled by the results presented in your paper.

@prouff I used your code and did an 8:2 split on the training set during training to use as a validation set. But I found that your model I used...

I am puzzled by the results presented in your paper.

I have not made any changes to your test scripts. As far as the training process of the model is concerned, the patchsize of the convolutional network has been modified...

I am puzzled by the results presented in your paper.

[ASCAD.zip](https://github.com/ANSSI-FR/ASCAD/files/2319036/ASCAD.zip)

I am puzzled by the results presented in your paper.

Sorry, I can't agree with you. I used the same partitioning and the same training script to train my model and used the same test script to test the model's...

I am puzzled by the results presented in your paper.

I am just saying that the lack of overfitting mentioned in the paper is somewhat inconsistent with the results I observed in the experiment. I hope you can test the...

I am puzzled by the results presented in your paper.

yes，of course

I am puzzled by the results presented in your paper.

Thx,I got it.However, I still can't understand why the model will have better results in the test set if the validation set has been degraded. This is very different from...

[Feature Support] For Multi-Batch Data Inference Support

After some tests, the maximum batch size can be 20 for 4 RTX 3090. But the total inference time increases as well. Specifically, using 4 RTX 3090 to generate descriptions...