Mingyuan Luo

The output of Cutout is mask

1


[BUG] Type hint broken for type when using ABCMeta

5

**Describe the bug & To Reproduce** My code: ```python # _mytype.py import abc class M(metaclass=abc.ABCMeta): def __init__(self): print(self) def cmp(cls1: type, cls2: type): print(cls1.__name__, cls2.__name__) ``` ```python # mytype.py from...

Training did not converge

2

I got loss as follows ``` ... 2018-10-27 Saturday 02:21:32 : Train Epoch: 1 [213/284 (75%)] loss_G: 13.778452 loss_G_identity: 4.409110 loss_G_GAN: 0.245768 loss_G_cycle: 9.123573 loss_D: 1.171054 2018-10-27 Saturday 02:21:33 :...

clGetPlatformIDs() gets error

3

Hi, I build and run your code on my MI5 (Qualcomm 820, Adreno 530) with eclipse. The process of build is ok but I get some errors as follows when...

When ``isprecise=True``, the ``q`` returned by ``quaternion_from_matrix`` has the possibility of appearing ``q[0] < 0``. transformations version: 2021.6.6 numpy version: 1.21.4 ```python3 import transformations import numpy as np m =...

In [wgan_div_celeba.py#L129](https://github.com/bojone/gan/blob/master/keras/wgan_div_celeba.py#L129), there is `d_train_model.add_loss(d_loss + grad_loss)` and `d_loss` is defined by `K.mean(x_real_score - x_fake_score)`. Should it be `d_train_model.add_loss(d_loss - grad_loss)` ?