-
My suggestions for 1.0 of the package, specifically for learning:
NB: if ticked, it means either it is complete or there is a good reason (which is provided) why this cannot go in for 1.0
- [x] …
-
hi~ I have done some modification on your model architecture, But when i train, WER and CER are both 100...
Could you tell me how can i get the text of model output? I wanna find the reason!
By the …
-
I am a beginner of GNN, and I take the liberty to ask a question, please bear with me.
My question is based on this sentence from the paper 4.1: The graph partitions are generated such that the train…
-
We'd like to be able to backtrace the gradient of interp for implementing a toy model. Is anybody working on this?
If not we will file a PR. (cc: @energy)
-
### Describe the bug
using the train_dreambooth.py script, when I add flags for enabling xformers and set_grads_to_none, the following error happened: train_dreambooth.py: error: unrecognized argum…
-
I'm titling this with "Workflow needed:" as this doesn't necessarily refer to a specific feature, but we should track whether the need described here has a reasonably straightforward workflow using Co…
-
Investigate training on unipen on multiple passes via loading iterative passes' weights at init of new pass, e.g. training on 5* 20% of dataset, as dataset itself (Close to 1M signals when cut) is too…
-
Hi,
Thanks for the PyTorch implementation. It is really good. However, I've ran into some issues. While exporting using torch.onnx, I am getting an error. The code is as follows:
```
model = Effi…
-
Currently the app only supports search in documents. Expecting OCR support for images.
-
Thank you for providing the code necessary for my research.
I have a question about PTv3 + PPT training.
I checked config file which you provided in Modelzoo(ScanNet validation on PTv3 + PPT).
…