zcl912's repositories
AI-Competition-Collections
AI比赛经验帖子 & 训练和测试技巧帖子 集锦（收集整理各种人工智能比赛经验帖）
awesome-ChatGPT
ChatGPT相关资源汇总
Awesome-LLM-Large-Language-Models-Notes
What can I do with a LLM model?
blazepose_openvino
BlazePose model test program for Intel Distribution of OpenVINO toolkit
BlazePose_torch
pytorch implement of google blazePose
ChatGLM3
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
ClothFormer
code and demo for our CVPR2022 paper "ClothFormer: Taming Video Virtual Try-on in All Module"
efficientdet-pytorch
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
JSON2YOLO
Convert JSON annotations into YOLO format.
mdistiller
A Knowledge Distillation Toolbox. The official implementation of https://arxiv.org/abs/2203.08679
mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练、有监督微调、RLHF(奖励建模、强化学习训练)和DPO(直接偏好优化)。
openvino_movenet
MoveNet Single Pose on OpenVINO
paddleOCR_cpp_tensorrt
The version of cpp tensorrt for paddleOCR.
ppq
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
pytorch-openai-transformer-lm
🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
pytorch-receptive-field
Compute CNN receptive field size in pytorch in one line
receptive_field
Compute receptive fields of your favorite convnets
RepVGG
RepVGG: Making VGG-style ConvNets Great Again
SummerTTS
SummerTTS 是一个基于C++的独立编译的中文和英文语音合成项目，可以本地运行不需要网络，而且没有额外的依赖，一键编译完成即可用于中文和英文的语音合成。SummerTTS is a standalone Chinese and English speech synthesis(TTS) project that has almost no dependency and could be easily used for Chinese TTS with just one key build out
Test_Net_Size
calculate params and FLOPs
tflite2tensorflow
Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite, ONNX, OpenVINO, Myriad Inference Engine blob and .pb from .tflite. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support.
TraDeS
Track to Detect and Segment: An Online Multi-Object Tracker (CVPR 2021)
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
ultralytics
YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite