-
/kind bug
Should we allow an option for the model load to be done per Tornado worker? At present it's done once:
https://github.com/kubeflow/kfserving/blob/34809b91c57a9f7dfb27592f1f4ad895bc074e…
-
solution is probably just global search and replace things like this:
```python
LeakyReLU(alpha=0.2)
```
with:
```python
LeakyReLU(negative_slope=0.2)
```
just a note.
-
Hi all. I've recently trained a keras implementation of ssd-keras. I've managed to run QAT training on the model and got desired the accuracy. I wanted to get the quantised weights from the QAT model …
-
**Describe the bug**
When doing quantization of the model in order to run on Edge_TPU an error message is presented.
**System information**
TensorFlow installed from (source or binary): binary
…
-
Instantiated metrics are not pickleable, as `__init__` instantiates tf variables, which cannot be pickled.
This means that keras models trained with one of the metrics, and then saved, cannot be op…
-
I'm trying to load the saved model . The model saves ok but when I try to load it with the code:
```
custom_objects={"BilinearUpsampling":BilinearUpsampling}
keras.models.load_model(model_f…
-
# Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [ √] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
- [ √] I am reporti…
-
Hi, would you be interested in adding GTR to Hugging Face? The Hub offers free hosting, and it would make your work more accessible and visible to the rest of the ML community.
Example from other o…
AK391 updated
2 years ago
-
Thank you for submitting an issue. Please refer to our [issue policy](https://www.github.com/mlflow/mlflow/blob/master/ISSUE_POLICY.md) for additional information about bug reports. For help with debu…
-
Here is a simple keras neural network using a `Dot` layer:
```python
from keras.layers import Input, Dense, Dot, Reshape, Flatten
from keras.models import Model
model_in = Input((10,), name='inp…