wangherr

The original function "stackImages(imgArray, scale, lables=[]):" is inconvenient to rectify "imageArray" when testing repeatedly. Based on "stackImages(imgArray, scale, lables=[]):" , I write a new function, which need a list as...

~~~ # [vae](https://github.com/bojone/vae)/vae_vmf_keras.py def sampling(mu): """vMF分布重参数操作 """ dims = K.int_shape(mu)[-1] # 预先计算一批w epsilon = 1e-7 x = np.arange(-1 + epsilon, 1, epsilon) y = kappa * x + np.log(1 -...

why multiply 100 in "anomaly_map = (100.0 * patch_tokens[layer] @ text_features)"?

1

Is it chosen based on empirical observations?

why there is no intermediate fine-tuning for one-class ImageNet-30?

1

In my view, there is no difference between one-class ImageNet-30 and one-class cifar10. why intermediate fine-tuning is ok for one-class cifar10, but is not ok for one-class ImageNet-30?

Error when setting num_single_layers=0 while training flux-controlnet on a multi-GPU server using a single GPU

6

### Describe the bug While training flux-controlnet on a multi-GPU server and restricting the training to a single GPU, setting **_num_single_layers=0_** leads to an error: [rank0]: Parameter indices which did...