-
[copied from CUNY-CL/abstractness/issues/123]
There are lot of pure Python loops in the transducer implementation and many can be replaced with PyTorch functions.
-
Your work is outstanding, and I admire the efficiency achieved in your mamba implementation.
However, I’m concerned about its accessibility and broader adoption in comparison to transformer-based …
-
In Python, `Tensor.detach()` does not copy the tensor storage. In-place value changes update the original tensor.
See doc, https://pytorch.org/docs/stable/autograd.html#torch.Tensor.detach.
```p…
-
### 🐛 Describe the bug
Hi all, I am a little confused about the implementation of GPSC…
-
The reason to rewrite the 'class LayerNorm(nn.Module)' is that you think the layer normal provided by PyTorch only supports 'channels_last' format (batch_size, height, width, channels), so you rewrite…
-
Hello, I'd like to try to use your implementation of Mish in our repo: https://github.com/ultralytics/yolov3
I'm not sure exactly how to implement Mish-CUDA. I haven't done any CUDA programming, I …
-
See keras-team/keras#512 and the [main Keras issue](https://github.com/keras-team/tf-keras/issues/183) for some previous discussion on this topic.
`AdaptivePool` is a pooling layer in PyTorch that …
-
Hi there,
I spent a week working on your code, and contributing to it! But, all I got is the blank prediction maps after convergences! I just found that you've had the same problem with your imple…
-
## 📚 Documentation
Hi all,
I found the LPPool2d & LPPool1d in the pytorch implementation, but there is no reference provided in the documents. And I didn't find the related paper explain…
-
After running the fold.py script for 3 hours, the process is in sleeping status with status D reported by shell command Top.
I am not sure the really cause of the bug, but here is an assumption.
I…