Name: ML.Designer
Type: User
Company: Guangxi University
Bio: Artificial intelligence related research, involving Machine learning, Deep learning and Computer vision
Location: College of Computer and Electronic Information, Guangxi University, Nanning, China
Blog: www.learncv.cn
ML.Designer's Projects
Nipype-N4BiasFieldCorrection-Bin, The files has made in bin
Implementation of C++ Boost Python Examples, With python3.5+ support
An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations.
基于深度学习高性能中文车牌识别 High Performance Chinese License Plate Recognition Framework.
Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials. 《Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs》
Implementation based on the paper Li et al., “A Convolutional Neural Network Cascade for Face Detection, ” 2015 CVPR
https://www.sohu.com/a/193020221_798050
Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices
深度学习教程整理 | 干货
Set up Alexnet to perform gender recognition and gesture prediction based on face,AlexNet: ImageNet Classification with Deep Convolutional Neural Networks
This is a repository containing code to Paper 3D Dense-Unet for MRI brain tissue segmentation (that hopefully will be) published on TSP 2018 conference.
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Keras community contributions (eg:common normalization, crf ...... )
deeplab v3+: Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
3D Deformable Convolution Network
DenseNet implementation in Keras
DropBlock:A regularization method for convolutional networks
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation, web:https://blog.csdn.net/u011974639/article/details/78956380
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Fully Convolutional Networks for Semantic Segmentation
Focal Loss for Dense Object Detection
inceptionV4: Inception-ResNet and the Impact of Residual Connections on Learning,Keras Implementation of Google's Inception-V4 Architecture (includes Keras compatible pre-trained weights)
GoogleNet: Going Deeper with Convolutions
Implementation of Segnet, FCN, UNet and other models in Keras.
Pyramid Scene Parsing Network
Rich feature hierarchies for accurate object detection and semantic segmentation
ResNet: Deep Residual Learning for Image Recognition,Residual networks implementation using Keras-1.0 functional API
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Differentiable Learning-to-Normalize via Switchable Normalization
Conditional Random Fields as Recurrent Neural Networks (Tensorflow)