haojunyong Goto Github PK

accelerating-cnn-with-fpga

This project accelerates CNN computation with the help of FPGA, for more than 50x speed-up compared with CPU.

act

Source code for the paper 'Audio Captioning Transformer'

awesome-pruning

A curated list of neural network pruning resources.

awesome-quantization-and-fixed-point-training

Neural Network Quantization & Low-Bit Fixed Point Training For Hardware-Friendly Algorithm Design

awesome-semi-supervised-learning

😎 An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.

bert

使用BERT做文本相似度

brevitas

Brevitas: quantization-aware training in PyTorch

c-cpp_mobilenetv2_inference

MobileNetV2 inference C++ implement

c-ml-kws-for-mcu

cpjku_dcase20

CP-JKU submission to DCASE 20

cpjku_dcase22

dcase20_task4

Baseline of DCASE 2020 task 4

dcase_task4

DCASE2019_task4 DA-CRNN

deep-occ-using-ics

Deep One-Class Classification using Intra-Class Splitting

deeplearningdeployment

Examples and tools for deep learning deployment

deepvac

PyTorch Project Specification.

dsq

pytorch implementation of "Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks"

effectivemoderncppchinese

《Effective Modern C++》翻译 - 已完成

fastspeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

fastspeech2-1

Multi-Speaker Pytorch FastSpeech2: Fast and High-Quality End-to-End Text to Speech :fist:

gpurir

Python library for Room Impulse Response (RIR) simulation with GPU acceleration

int8inferenceengine

An inference engine for 8-bit quantized neural network

kdconv

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation

libtorch-yolov3

A Libtorch implementation of the YOLO v3 object detection algorithm

libtorchdetection

C++ trainable detection library based on libtorch (or pytorch c++). Yolov4 tiny provided now.

lightweight-facial-expression-recognition

Face detection, expression recognition, model compression, terminal deployment

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

mdistiller

A Knowledge Distillation Toolbox. The official implementation of https://arxiv.org/abs/2203.08679

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

ml-kws-for-mcu

Keyword spotting on Arm Cortex-M Microcontrollers