-
Is it correct that there is no support for 'vanilla' RNN layers, e.g. that of torch.nn.RNN? Is the reason for this something like 'GRU or LSTM is better anyway, just use that'?
-
Hey!
I'm working on a model that uses custom capsule layers. I used custom_operations to convert it to onnx but not achieved. Anyone here converted multiple custom layers of keras to onnx? If so how?…
-
In torch, one typically writes layer `__call__` methods by overriding the `forward` method. Under keras, we instead use the `call` method.
I would not expect overriding `forward` to have any effect…
-
### Describe the bug
### Steps/Code to reproduce the bug
:
```
import tensorflow as tf
import numpy as np
data_x=np.random.random((64,10)…
-
After the redesign in #2500, here is a list of potential improvements for recurrent layers and recurrent cells
- [ ] add an option in constructors to have trainable initial state
- [ ] use cuDNN
…
-
To add a loss and metrics to a model, I can add them to `model.compile(loss=..., metrics=...)`, provided that they have the signature `fn(y_true, y_pred)`, see the [docs](https://keras.io/api/models/m…
-
#### Issue Description
I have created and trained a TensorFlow Keras model in Python and saved it as _trained_model.h5:_
```
model = tf.keras.Sequential([hub.KerasLayer("https://tfhub.dev/googl…
-
Dot, as found here https://keras.io/layers/merge/#dot, and for legacy purposes "cos" merge mode in `Merge` layer.
-
While running demo.ipynb i get the below error:
Tensorflow version = 1.15.0
---------------------------------------------------------------------------
AttributeError T…