-
## Description
`KeyError: 'dense_1/Sigmoid:01'` when using `onnx2mx` to import an LSTM model that was originally trained via keras and converted to ONNX format via `keras2onnx`.
## Environment inf…
-
**Describe the bug**
AdamW implementation (see [here](https://github.com/NVIDIA/apex/blob/a7de60e57f0534266841e1733262601ad76aaa74/csrc/multi_tensor_adam.cu#L333)) does not truly decouple the weight…
-
## Description
(A clear and concise description of what the bug is.)
I was using one derivation of the AlexNet model to do model inference using MXNet as the Keras's backend. I used the `keras-mxnet…
-
It would be great to be able to switch between deep learning backends, so users aren't tied to mxnet. The three that come to mind are mxnet, tensorflow, and knet. This could also simplify model buildi…
-
@smilesun Incremental learning with neural networks in R is very slow.
I made some benchmarking experiments, `mxnet `is twice as fast as `keras `but still very slow.
Not sure what we can do about …
-
# Summary
Unable to use batchnormalization with MXNet backend when using multiple GPUs. After debugging the issue, I found that there is a mismatch in the shape of batchnorm param in KVStore. in mxne…
-
# Variables and Placeholders
- [ ] Support for constraints in Keras variables and Placeholders
# Update Operators
- [ ] update
- [ ] update_add
- [ ] update_sub
# Graph Manipulations
- [ ] …
-
- [x] xgboost
- [x] ranger
- [x] rpart
- [ ] a neural net package (maybe mxnet or keras)?
- [ ] svm from e1071
- [x] naiveBayes from e1071
- [ ] kknn (knn from class and fnn do not s…
-
This code uses a Lambda layer to select a subset of the input (data format is `channels_first`):
```python
import keras
NSTEPS=100
NFEATURES=10
NGROUPS=3
a = keras.layers.Input((NFEATURES,NGRO…
-
**Describe the bug**
A clear and concise description of what the bug is.
**To Reproduce**
Steps to reproduce the behavior:
1. Go to 'adversarial_action_recognition.ipynb'
2. Click on 'adv_sampl…