-
Please go to TF Forum for help and support:
https://discuss.tensorflow.org/tag/keras
If you open a GitHub issue, here is our policy:
It must be a bug, a feature request, or a significant prob…
-
### Issue Type
Bug
### Source
binary
### Keras Version
2.16.0
### Custom Code
No
### OS Platform and Distribution
_No response_
### Python version
3.11
### GPU model and memory
_No respon…
-
Hi all,
My Keras is using Theano backend. Encountered the following error:
`
theano.gradient.DisconnectedInputError: grad method was asked to compute the gradient with respect to a variable tha…
-
Hi all,
The following code runs fine for a standard neural network, but not for a Bayesian neural network. In the latter case, calling the function `fit`leads R to abort, not before saying that ten…
-
**Describe the bug**
Literally the title
```python
import numpy as np
import tensorflow as tf
from gpflux.helpers import (
construct_basic_inducing_variables,
construct_basic_kernel,
…
-
**Describe the bug**
When using `prune_low_magnitude()`, my model is not pruned if the batch size is low.
**System information**
TensorFlow version (installed from source or binary): 2.8.0 inst…
-
what should I do now? I am getting this error, I have resolved the earlier errors by degrading the python from 3.8.1 to 3.7.6, and using keras version 2.0.1. This seems like dead end to me.
File "…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
No
### Source
binary
### TensorFlow version
2.14.0
### Custom code
Yes
### OS platform and distribution
Linux
##…
-
### 🚀 The feature, motivation and pitch
I would Like a layer that maps string features into integer indices and can be packaged within pytorch binary/onnx to use it on production serving.
I'm work…
-
For the Keras model with `PReLU` layer, It can be converted to RelayIR but crashes when compiling it and throw "**Incompatible broadcast type TensorType([4, 2, 3], float32) and TensorType([1, 2, 3, 4]…