keras-io icon indicating copy to clipboard operation
keras-io copied to clipboard

Keras documentation, hosted live at keras.io

Results 302 keras-io issues
Sort by recently updated
recently updated
newest added
trafficstars

The VAE class in the example for VAE shows `total_loss = reconstruction_loss + kl_loss`, but this is not the case when adding these values in the `fit` output. I ran...

stat:awaiting keras-eng

Hi there, I read the ViT code. However, I havent find any code relevant "Class Token". Could you give me some hint?

@fchollet, to help our contributors sort the imports in a nice manner, should we start using `isort`? If so, I can prepare a PR that does all the changes necessary...

There were some training and inference bugs in siamese network with triplet loss example, the bugs were the following: 1. In `train_step` we should pass `training=True`. 2. In the `test_step`...

Hello, I would like to make a code example on Denoising Diffusion probabilistic models. Do you think it is needed on keras.io ? Here is what it would like on...

I'm following this example: https://github.com/keras-team/keras-io/blob/master/examples/vision/depth_estimation.py However, I'm confused as to why the model is compiled with the cross-entropy loss when a custom loss function is being used for optimization?

Hello, why is the decoder not used in [this](https://github.com/keras-team/keras-io/blob/a9b0bc50ca2b60621eb6da84c051183380d5e272/examples/timeseries/timeseries_classification_transformer.py) sample code from the transformer network? Isn't the decoder part of the transformer network?

![eRY9s](https://user-images.githubusercontent.com/91024790/177130764-bcd4a8bf-6ecc-4fc8-b709-e4231866a6f8.png) I’m trying to implement this network. My dataset is composed by images and masks of left ventricle and I'm performing binary segmentation. I used TimeDistributedImageDataGenerator in order to create...

I am ruinning my own dataset, after all pre-processing the below code generates error, which is location in `Class DualEncoder`. `def create_example(image_path, caption):` ` feature = {` `"caption": bytes_feature(caption.str.encode()),` `"raw_image":...

As part of the HuggingFace Keras sprint, I have added the HF links in the CCT and the Timeseries classification from scratch examples.