-
Hi,
I'm trying to use your code to a chatbot and your work is very valuable to me. However, I found that you only published the statement of function `Train` and `TrainIters` without an example of …
-
The defacto only reliable reference (https://pytorch.org/tutorials/advanced/cpp_extension.html) for C++ and CUDA extension is not using device guards, which makes the resulting extension broken for no…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
Updates from:
- https://github.com/jacobhilton/deep_learning_curriculum (focus on transformers)
- Raschka book
1. Math prerequisites
Taking a derivative to find a point of minimum or maxim…
-
Hello!
I am benchmarking attention implementations, and trying to use flash attention for my variable length data and for some reason var length is much much slower than any other implementation, i a…
-
Proposal for adding support for Kolmogorov-Arnold Networks (KANs) in PyTorch. KANs are a promising alternative to traditional Multi-Layer Perceptrons (MLPs) and offer potential advantages in terms of …
-
joram updated
4 years ago
-
https://github.com/OdingdongO/pytorch_classification/blob/master/dataset/AL_defect_dataset.py
-
Full stacktrace:
```
/pytorch/aten/src/THC/THCTensorScatterGather.cu:188: void THCudaTensor_scatterFillKernel(TensorInfo, TensorInfo, Real, int, IndexType) [with IndexType = unsigned int, Real = lo…
-
Hi,
How can I retrain the yolov5 pre-trained models and run them using VectorBlox?
I tried the following:
- Tried using the ONNX model file provided in the VectorBlox tutorials with the [ultral…