-
Hello! Our static bug checker has found a performance issue in lime/scripts/lipo_gru/ht_lipo_gru.py: [`init`](https://github.com/choderalab/gimlet/blob/9082431d8b664699a898c1e2fa490a18737d6e2d/lime/s…
-
### Describe the issue
When running inference session ONLY with OpenVino EP and ORT > 1.13.1 any results except first are incorrect. There are no issues with ORT == 1.13.1 or CPU/CUDA/XNNPACK on an…
-
I want to use my model to decompression and compression.But It maybe needs to know the content of these files ?
-
**Describe the issue**:
**Environment**:
- NNI version:2.9
- Training service (local|remote|pai|aml|etc):colab
- Client OS: linux(colab)
- Server OS (for remote mode only): colab
- Python …
-
I run into InvalidArgumentError when my notebook gets to the GRU section.
```
InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'CudnnRNN' with these attrs. R…
-
Hi,
are there any plans to add cuDNN-accelerated versions of LSTM and GRU to the PyTorch backend? Without cuDNN acceleration, the LSTM and GRU are considerably (several times) slower, even when run…
foxik updated
3 months ago
-
## 🐛 Bug
It is advertised, that forward pass of JITed RNNs (e.g. GRU) is as fast as cuDNN implementation.
But it is not the case.
## To Reproduce
Steps to reproduce the behavior:
See here…
-
@sirius-ai Thank you very much for implementing **LPRNet**. During the training process, adding **residual connection** to SmallBasicBlock using ResNet can further improve performance (**LPRNet ->LPR…
-
**This Error occurred when try to execute even on example png file included in examples folder:-**
Traceback (most recent call last):
File "convert_single_image.py", line 53, in
main()
…
-
### 🚀 The feature, motivation and pitch
I was trying to vmap a GRUCell and got the following:
```
There is a performance drop because we have not yet implemented the batching rule for aten::gru_c…