-
Overview
In the final lesson of Practical Deep Learning for Coders we'll study one of the most important techniques in modern architectures: the skip connection. This is most famously used in the res…
-
Get mobilenet working end-to-end with whatever hacks needed!
So far, this involves
- Making Relay operators opaque, see #65
- No longer trying to have Glenside find a blocking scheme; instead, re…
-
##### System information (version)
- OpenCV => 4.2.0
##### Detailed description
The CUDA backend can support mixed-precision inference with various types: FP32, FP16, INT32, (U)INT8 and possibl…
-
Hi, I was a bit surprised by the difference in speed between backpropogating through ODEs vs SDEs but couldn't find any discussion in the documentation about the time complexity of either. With a quic…
-
Hi,
I'd like to run KataGo on my M1 macbook with native support for CoreML but sadly, I don't know the framework plus I have no experience with macOS development.
Hence I'd like to create this i…
-
@pjreddie @lilohuang @tjluyao The model size which i trained for the custom dataset is around 63.5Mb for 6 class , i need to reduce the model size as much as possible . Can you suggest a way where i…
-
Could we get an in place `conv!` function?
Looking at [the code](https://github.com/JuliaDSP/DSP.jl/blob/9a2f5d63d65cc225bfaa481e76f274e0a933c36e/src/dspbase.jl#L674), it seems like you'd only need…
-
### Describe the issue
I have a model that I'd like to run using onnxruntime to decrease the install size. Here's a table comparing the total time of ONNX and pytorch when running different amount …
-
Hi everyone,
Thanks for the awesome work. I've been trying to export the pytorch model to ONNX for inference with `torch.onnx.export` but it yields this error : `OnnxExporterError: Unsupported: ON…
-
## 🚀 Feature
Add a lowering for `unfold`.
## Motivation
I want to run Longformer ([model code on HF repo](https://github.com/huggingface/transformers/blob/master/src/transformers/modeling_long…