keras-io

keras-io copied to clipboard

Hello I get the following error: "SystemError: Negative size passed to PyUnicode_New" when I run the following program: https://github.com/keras-team/keras-io/blob/master/examples/generative/ddim.py Please advise. Thanks.

deicool

ViT cannot detect multiple objects in one image

4

The Object Detections with Vision Transformers can only detect one object per image. I tried to run the model prediction on an image containing many same objects, only 1 big...

galax-count

Add explanation : pip install tensorflow-addons

1

I have seen colab link on documents. After I executed the code, colab needs installation of tensorflow-addons. For consistency, I copied install message in another example file. It's not serious,...

lazybuttrying

In the Keras tutorial "Next-Frame Video Prediction with Convolutional LSTMs" (https://keras.io/examples/vision/conv_lstm/) I've noticed that there seems to be a data leakage problem. Namely, the 3D convolution has direct access to...

lugi7

https://github.com/keras-team/keras-io/blob/c300386a5989a99f1508a068e62436083c48797c/examples/nlp/neural_machine_translation_with_transformer.py#L156 ## Inputs For Transformers #### 1. Encoder Inputs - The encoder of Transformer takes in vectorized source sentences the way they are. #### 2. Decoder Inputs - The decoder...

aryan7781

gadagashwini

I am training hybrid vision transformer model with Dense121 model in custom dataset which contains 25 classes. The model get overfit from the start, the validation loss remains constant doesn't...

Badal-Shrestha

The tutorial [Image classification via fine-tuning with EfficientNet](https://keras.io/examples/vision/image_classification_efficientnet_fine_tuning/#image-classification-via-finetuning-with-efficientnet) demonstrates how EfficientNet can be fine tuned to improve classification accuracy. In this example, the last 20 layers are unfrozen and tuned....

TylerADavis

The model proposed in [ddim.py](https://github.com/keras-team/keras-io/tree/master/examples/generative/ddim.py) does not converge at all. It stays stable in a state that estimates the noise to be ~0 with an error of 0.7979 forever. My...

Bejro

Error in keras example - Speaker Recognition using cnn colab file

3

As a part of the hugging face sprint, I was trying to add the hf space & model link for this [Keras example](https://keras.io/examples/audio/speaker_recognition_using_cnn/) but got an error while executing the...

robotjellyzone