Pinned Repositories
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's Repositories
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/DIOPI
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/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
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/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