roomo7time

The AgeDB cropper provided in the [code](https://github.com/JDAI-CV/FaceX-Zoo/blob/main/test_protocol/lfw/face_cropper/crop_agedb_by_arcface.py) does not work because of the landmark size error. The cropper and dependent utilites in this library work only for 5-point, 25-point, and...

This line is too slow

1

https://github.com/openai/weightnorm/blob/dff0cd132e9c6e0a31b76cb243d47a07e0c453cc/tensorflow/nn.py#L188 I've been re-implementing ImprovedGAN for semi-supervised learning for cifar10 using nn.py. This line is defining a variable by initializing it by a tensor from the build-up graph. Initializing a...

EMA update on CosineCodebook

7

The original VIT-VQGAN paper does not seem to use EMA update for codebook learning since their codebook is unit-normalized vectors. Particularly, to my understanding, EMA update does not quite make...

usage of 'range' in 'reduce_max' and 'reduce_sum' needs to be debugged

3

https://github.com/takerum/vat_tf/blob/c5125d267531ce0f10b2238cf95604d287de63c8/vat.py#L34 In tensorflow (1.8>) with python 3, this line does not seem to work. It seems range needs to be wrapped by 'list'.

https://github.com/yaohungt/Barlow-Twins-HSIC/blob/a30baba4d2d3dcdf85a4ccebe57902f0d827c1ed/model.py#L31 Hi, your code is very helpful and I want to firstly appreciate the code share. I have a question on whether this feature normalization is necessary (to make the...

Hi, I'd like to ask you some questions on the baseline model that you used for the comparison. In README.md, the reported baseline gives a simialr performace to that of...