Pinned Repositories
agent
qwen ai agent
bypy
Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端
centernet-pytorch
这是一个centernet-pytorch的源码，可以用于训练自己的模型。
cocoapi
COCO API - Dataset @ http://cocodataset.org/
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
darknet
YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
DBNet.pytorch
A pytorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization
Dipoorlet
Offline Quantization Tools for Deploy.
NART
NART = NART is not A RunTime, a deep learning inference framework.
OcrTool
Tool
Wq-dd's Repositories
Wq-dd/Dipoorlet
Offline Quantization Tools for Deploy.
Wq-dd/NART
NART = NART is not A RunTime, a deep learning inference framework.
Wq-dd/agent
qwen ai agent
Wq-dd/bypy
Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端
Wq-dd/centernet-pytorch
这是一个centernet-pytorch的源码，可以用于训练自己的模型。
Wq-dd/cocoapi
COCO API - Dataset @ http://cocodataset.org/
Wq-dd/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Wq-dd/darknet
YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
Wq-dd/DeepLabV3Plus-Pytorch
Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes
Wq-dd/MobileNetv2-YOLOV3
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
Wq-dd/my_yolof
Wq-dd/EasyLLM
Built upon Megatron-Deepspeed and HuggingFace Trainer, EasyLLM has reorganized the code logic with a focus on usability. While enhancing usability, it also ensures training efficiency.
Wq-dd/Langchain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain
Wq-dd/lightllm
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
Wq-dd/llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
Wq-dd/onnx
Open standard for machine learning interoperability
Wq-dd/onnx2X
ONNX2Pytorch
Wq-dd/ppq
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Wq-dd/pybind11_practice
Wq-dd/python
Wq-dd/quickrun
瑞芯微芯片的rknn推理框架部署(yolo模型)
Wq-dd/rag-retrieval
RAG向量召回示例
Wq-dd/RepDistiller
[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods
Wq-dd/rk3588_yolov5_bytetrack
Wq-dd/Server
PanDownload的个人维护版本
Wq-dd/STDC-Seg
Source Code of our CVPR2021 paper "Rethinking BiSeNet For Real-time Semantic Segmentation"
Wq-dd/SuperGluePretrainedNetwork
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
Wq-dd/swift
Use PEFT or Full-parameter to train LLMs or MLLMs
Wq-dd/the-gan-zoo
A list of all named GANs!
Wq-dd/yolov5_prune
yolov5 prune，Support V2, V3, V4 and V6 versions of yolov5