keras-io

keras-io copied to clipboard

CycleGan save error

1

Hi, I'm running the Colab of CycleGan as is ([https://colab.research.google.com/github/keras-team/keras-io/blob/master/examples/generative/ipynb/cyclegan.ipynb](https://colab.research.google.com/github/keras-team/keras-io/blob/master/examples/generative/ipynb/cyclegan.ipynb)) and have the following error: > ValueError Traceback (most recent call last) > in () > 42 tf.data.Dataset.zip((train_horses, train_zebras)), >...

antoine-l

Code Example on DropBlock2D Layer and its Regularization Impacts in Training ConvNets

2

Hello, I would like to make a code example on KerasCV DropBlock2D Layer and its regularization impact in training convolutional neural networks. If this would be a nice thing to...

Nyandwi

A bug causing gradient to NaN in WGAN-gp example

1

Hi, I want to report a bug and corresponding fix to your team. I believe this fix could help others who use WGAN-gp algorithm to train GANs. ## Bug and...

Sneaker001333

Add MobileNetV3 performance to https://keras.io/api/applications/

2

Not sure who contributed MobileNetV3 to `keras.applications`. Couldn't figure it out from https://github.com/keras-team/keras/commits/v2.9.0/keras/applications/mobilenet_v3.py either. The purpose of this thread is to just request the contributor of the model to add...

sayakpaul

Add ResNet-RS performance to https://keras.io/api/applications/

1

The purpose of this thread is to just request the contributor (@spatil6) of the model to add the following details and contribute a PR to https://keras.io/api/applications/: * Size * Top-1...

sayakpaul

Make Fixed Sidebar in `keras.io` website!

2

I found it very unpleasant when navigating the [`keras.io`](https://keras.io/api/) site. The sidebar should be fixed (something we see in the official [`tensorflow.org`](https://www.tensorflow.org/api_docs/python/tf).). Ref. [Fixed Sidebar ](https://www.w3schools.com/howto/howto_css_fixed_sidebar.asp) 

innat

Problem: Face image generation with StyleGAN generates darker and darker output.

6

Problem: Face image generation with StyleGAN generates darker and darker output. I am running the stylegan.py example, doing a training, and the more steps_per_epochs i use, the darker the output...

notnot

I want to create a call function like this but I am unable to call a list object in my `call()` defined in `__init__` `def call(self, images):` augmented_images = self.data_augmentation(images)...

Zah-Ram

Hi! I've a minimal example for diffusion model that would train within few minutes along with equations from the paper and some visualizations: https://github.com/InFoCusp/diffusion_models Would it be a good fit...

falaktheoptimist

why keras.layers.MultiHeadAttention q-dim don't / heads?

1

zhanlie2008