amtf1683

albumentations

Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

BackgroundMattingV2

Real-Time High-Resolution Background Matting

deeplearning-models

A collection of various deep learning architectures, models, and tips

DifficultProblem

Image-Downloader

Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.

micronet

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

pytorch-YOLOv4

PyTorch ,ONNX and TensorRT implementation of YOLOv4

Tengine

Tengine is a lite, high performance, modular inference engine for embedded device

TimeSformer-pytorch

Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification

YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

amtf1683/buddhist

佛学资料收集

amtf1683/CppTemplateTutorial

中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)

amtf1683/DeepLearningSystem

Deep Learning System core principles introduction.

amtf1683/examples

Example code and applications for machine learning on Graphcore IPUs

amtf1683/faguquanji

法鼓全集 聖嚴法師 電子書 圣严法师 电子书 (EPub Mobi PDF)

amtf1683/gslcl

Getting Started with LLVM Core Libraries （中文版），翻译：潘立丰

amtf1683/ISP-pipeline-hdrplus

Denoise,HDR,Isppipeline,Image-processing(图形处理),camera, Isp ,HDRplus

amtf1683/ISPLab

An open-source image signal processing (ISP) pipeline implemented by C++

amtf1683/KsanaLLM

amtf1683/leetcode-1

LeetCode Problems' Solutions

amtf1683/llama2.c

Inference Llama 2 in one file of pure C

amtf1683/llm.c

LLM training in simple, raw C/CUDA

amtf1683/llvm

A specific version of llvm that matches mlir

amtf1683/Megatron-LM

Ongoing research training transformer models at scale

amtf1683/mlir-hlo

amtf1683/naked_llama

build llama inference compute from scrath, only using torch/numpy base ops

amtf1683/popart

Poplar Advanced Runtime for the IPU

amtf1683/poplibs

Poplar libraries

amtf1683/relax

amtf1683/tensorflow-internals

It is open source ebook about TensorFlow kernel and implementation mechanism.

amtf1683/tpu-mlir

Machine learning compiler based on MLIR for Sophgo TPU.

amtf1683/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

amtf1683/triton

Development repository for the Triton language and compiler

amtf1683/tutorials

Training material for IPU users: tutorials, feature examples, simple applications

amtf1683/tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

amtf1683/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

amtf1683/xla_tutorial

This is a set of tutorial to learn the TensorFlow XLA (Accelerated Linear Algebra) compiler infrastructure.

amtf1683/yuqianyi1001.github.io

我的学佛记录，文章等

amtf1683/zju-icicles

浙江大学课程攻略共享计划

amtf1683/zynqmp_cam_isp_demo

ISP-Lite, VIP, MIPI-RX IP实现，测试平台为KV260+AR1335 3MP@30fps