Sachin Prasad comments

Results 317 comments of


                                            Sachin Prasad

Cannot load back model with no-op Concatenate layer

For functional API you should use concatenate instead of Concatenate, please find the gist [here](https://colab.research.google.com/gist/sachinprasadhs/7083046f47862f0859e2e2b231b341ff/52968.ipynb) for the same with multiple inputs in concat layer and in your case there is...

Instantiating a `tf.keras.applications` Model Nullifies Augmentation Layers

By default keras layers augmentation works only during training. Augmentation layers which you are using such as `RandomRotation`, `RandomFlip`, `RandomZoom`, `RandomHeight`, `RandomWidth` by default does augmentation only during training and...

Enable NNAPI Crash

Is there any way you could include the select ops as well in your converter and check the outcome. ``` converter.target_spec.supported_ops = [ tf.lite.OpsSet.TFLITE_BUILTINS, # enable TensorFlow Lite ops. tf.lite.OpsSet.SELECT_TF_OPS...

Shifted/reordered YOLO output layers when converting with TfLite 2.8 or higher

Hi @misterBart , Could you please try using `ExportArchive` https://www.tensorflow.org/api_docs/python/tf/keras/export/ExportArchive which could solve the issue of retain output name in the Keras model. The other way to make it work...

Better error message for Unexpected result of `train_function` (Empty logs). Please use `Model.compile(..., run_eagerly=True)`, or `tf.config.run_functions_eagerly(True)` for more information of where went wrong, or file a issue/bug to `tf.keras`

@pwernette , There is a PR created for this issue here https://github.com/keras-team/keras/pull/16216, but there is no update from the author.

Updated timeseries_dataset_from_array

Hello, Thank you for submitting a pull request. We're currently in the process of migrating the new `Keras 3 code base` from `keras-team/keras-core` to `keras-team/keras`. Consequently, merging this PR is...

Keras 3 SpectralNormalization()

I was able to replicate the issue in PyTorch and Jax as well, below is the error message and Gist attached. Pytorch: ``` RuntimeError: Exception encountered when calling SpectralNormalization.call(). Boolean...

Typo in Weights-only saving

Thanks for reporting the issue. I have linked the PR here with correction.

migrate keras2 code to keras3.0 with pytorch backend, got inplace error

Hi, Thanks for reporting the issue, I was trying to reproduce the error, I could not find the `q_loss` defined in the code, please find the attached Gist [here](https://colab.sandbox.google.com/gist/sachinprasadhs/87fc4c0b22332bcf1a16e1d4f3a81894/18895.ipynb) and...

migrate keras2 code to keras3.0 with pytorch backend, got inplace error

I was able to run the code without any error in Keras 3.0.2, please find the below Gist and let us know if there is anything I'm missing. https://colab.sandbox.google.com/gist/sachinprasadhs/6329e51aa49fa697c09185f912b5049e/18895.ipynb