keras-io
keras-io copied to clipboard
Keras documentation, hosted live at keras.io
I have implemented the GradCAM algorithm with an SSD model and I was able to generate the heatmap only for few layers. The convolutional layers towards the end of the...
Fix 'utf-8' codec can't decode byte 0xe9 in position 3114: invalid continuation byte
As a teacher in ML I find there are clear problem spots in [timeseries_weather_forecasting.py](https://github.com/keras-team/keras-io/blob/master/examples/timeseries/timeseries_weather_forecasting.py) First, the Data Preprocessing is not sufficient, compare this code to the TensorFlow tutorial on [Time...
Almost all of keras-io's workflows run with safe permissions. However, `continuous_integration.yml` is currently running with the default write-all token. This issue can be solved in two ways: - add top-level...
Keras.io example: https://keras.io/examples/nlp/data_parallel_training_with_keras_nlp/ Merged PR: https://github.com/keras-team/keras-io/pull/1395 This example is good on the whole but it would be much better with proper batch size and learning rate scaling. Without this, using...
Hello, I have been looking for information but I still am unclear about how to save and load the models obtained through the [object detection guide ](https://keras.io/guides/keras_cv/object_detection_keras_cv/#train-a-custom-object-detection-model). I am running...
Hi, Can you please guide me on how I can feed the data to the network using timeseries_dataset_from_array? In fact, I want to use the sliding windows technique and timeseries_dataset_from_array...
https://github.com/keras-team/keras-io/blob/6270df3d8a7f853160d05ee196404f2ccc4298eb/examples/nlp/text_classification_with_switch_transformer.py#L189
I implemented an example of adversarial sample generation using the keras framework. And I carefully read the documentation required to contribute, passed the relevant tests. Hopefully it will be adopted...
The example provided in timeseries_anomaly_detection.py is not working in practice, and the final result shows only the portion of the output with the expected behaviour, but it skips the part...