XiangqianMa's Projects
Code of HuaWeiCloud AI competition: classification.
剑指Offer中的算法问题
本仓库为深蓝学院-语音识别从入门到精通课程的作业仓库,仓库将随着课程的推进而更新。
This is a deep learning framework for cnn which using xnor method to accelerate calculating convolution layer on cpu.
Captcha recognition.
Object detection, 3D detection, and pose estimation using center point detection:
Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
Mataining some scripts which can be used in the computer vision mission.
Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices
YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )
PyTorch implementation of 'Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding' by Song Han, Huizi Mao, William J. Dally
在我很多项目中用到的CV算法推理框架应用。
A faster pytorch implementation of faster r-cnn
FCOS: Fully Convolutional One-Stage Object Detection
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)
《GitHub实践入门》实验用仓库
my gittalk.
The winning submission for NIPS 2017: Defense Against Adversarial Attack of team TSAIL
The code of Kaggle competition Pheumothorax Segmentation.
Code of kaggle semantic segmentation competition: Steel Defect Detection.
A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.
Open MMLab Detection Toolbox with PyTorch 1.0
Pretrain neural network.
Pytorch implementation of Octave convolution
Python - 100天从新手到大师
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Some custom dataset examples for PyTorch
DeepLab v3+ model in PyTorch. Support different backbones.
Count the FLOPs of your PyTorch model.