jsaladich

Hi guys, I found myself in the need of installing some modules with the argument `--no-binary`, when I realized about a potential issue / bug of pipenv ### Issue description...

Hi! I have been tracking your amazing library, which seems pretty cool. Yet, I have some problems with the Corine Land Cover geotiff ([link to download](https://land.copernicus.eu/pan-european/corine-land-cover/clc2018?tab=download)) As they say, the...

Unexpected Symbolic tensor in Tensorflow Probability tensor_coercible object (mixture layer)

1

Complex interpretation of Tensorflow Probability tensor_coercible object I have a tensorflow model (keras sequential) that ends with a Tensorflow Probability (TFP) mixture layer. My goal is to fit this network...

Saving a Keras model that includes a mixture layer (e.g. MixtureNormal) might be unsafe

1

Hi Team, I am trying to save the weights of a Keras model that end with a MixtureNormal layer. And I get the following warning: ``` .../keras/src/saving/serialization_lib.py:(line) 159: UserWarning:The object...

Tuner's Oracle paratemer "run_times" differs from user input "executions_per_trial"

10

Hi KerasTuner team! **Describe the bug** I ran an experiment with `keras_tuner.BayesianOptimization` in which `executions_per_trial=3`. When I check the file `./oracle.json` I realize that the field `run_times` is always equal...