Guocheng
Guocheng
In the README.md introduction: >Finally, we compute the AP as the **area under this curve** (shown in light blue) by numerical integration. No approximation is involved since the curve is...
darknet.py line 94 still don't get it, I googled a lot, at yolov3.cfg where padding always equal to 1, some say padding is constant( [links](https://github.com/pjreddie/darknet/issues/950)), and i tried padding =...
Why sort bbox with objectness score (Pobj) rather than individual class score (Pc) util.py line 149 `conf_sort_index = torch.sort(image_pred_class[:,4], descending = True )[1]` I searched NMS sort bbox with Pc...
I'm trying to parse a arg that is a list of dict use the comand line tool: The yaml: ```yaml # part of the config.yaml model: augmentations: - a: random_crop...
## 🚀 Feature request Use Argument linking to link `init_args` to `dict_kwargs` ### Motivation I try to link `data.input_width` to `model.dict_kwargs.input_width` because transformer models need input image shape for model...
Hi! I would like to contribute my [repo](https://github.com/bot66/MNISTDiffusion) to this awesome curated list. In this [repo](https://github.com/bot66/MNISTDiffusion) I implemented a denoising diffusion model from scratch with merely PyTorch.The model is surprisingly...
In your [blog](https://lilianweng.github.io/posts/2021-07-11-diffusion-models/#forward-diffusion-process): > f(t)=cos( (t/T+s)/(1+s) * pi * 0.5 ) But from the [paper](https://arxiv.org/pdf/2102.09672.pdf) your blog reference: > f(t)=cos( (t/T+s)/(1+s) * pi * 0.5 )**2
Add markdown code block type hint.
```bash #python=3.10.14 pip install "langserve[all]" pip install -U langchain-cli #log ... Installing collected packages: uvicorn, typer, tomlkit, smmap, libcst, colorama, gitdb, gitpython, fastapi, langchain-cli Attempting uninstall: uvicorn Found existing installation:...