-
Description says you collect feedback, but not specifies how it should be provided, so I should open an issue ... I guess?
First, nice job @zdevito ! torchdim looks very promising, in particular in…
-
I tried to run `notebooks/TS_dataset_generation_benchmarking1.ipynb` notebook However when calling cell
```python
num_classes = y_train_binary.shape[1]
models = modelgen.generate_models(np.swap…
-
Hello can you provide a Python Notebook for "How to do forecasting using Mamba?"
How to use Mamba to forecast and compare with LSTM, RNN also.
-
## 🚀 Feature
Support for a new device in DGL - Intel GPU. The POC of Intel GPU support in DGL for GraphSAGE model is available here: https://github.com/RafLit/dgl/tree/xpu_poc.
## Motivation
Intel …
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### Ultralytics YOLO Component
…
-
### 📚 The doc issue
We need to specify that we could not use `torch.compile` in official Pytorch runtime docker images.
For CPU images `g++` is missing and for GPU flavour it cannot find `libcu…
bhack updated
1 month ago
-
To the point: Why does higher need to deep copy the parameters of the base model (usually the initialization params)?
-----
# More expanded question
I noticed this line of code:
https://gith…
-
## 📚 Documentation
In deep metric learning we usually have to compute a pairwise similarity/distance matrix. For example, the cosine distance matrix `pdist` is computed as:
```python
x = th.rand(…
-
In SharpLearning, the F64Matrix class, which is part of the [Learner interfaces](https://github.com/mdabros/SharpLearning/tree/master/src/SharpLearning.Common.Interfaces), is mostly used as a containe…
-
## Description
The problem is when I train a PSPNet using GluonCV semantic segmentation library on the Cityscapes dataset, the training will stuck (hang) right after it started. Checking the GPU stat…