smartfour Goto Github PK

aestheticsperception

Deep CNN for image aesthetic perception

caffe-fcn

Run Long and Shelhamer's FCN image segmentation network using Caffe

caffe_rtpose

Realtime C++ code for multi-person pose estimation

deepface

Face analysis mainly based on Caffe. At this time, face analysis tasks like detection, alignment and recognition have been done.

dilatedfcnsegmentation

A dilated version of FCN with Stride 2 for Efficient Semantic Segmentation

eco-efficient-video-understanding

Code and models of paper " ECO: Efficient Convolutional Network for Online Video Understanding"

enet

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

face-landmark

caffe 68 points face-landmark

face-landmark-localization

cnn network predict face landmarks (68 points) and head pose (3d pose, yaw,roll,pitch).

face_recognition

使用webface人脸数据集以及DeepID网络，通过Caffe训练出模型参数，得到LFW二分类的人脸识别准确率。

faceboxes

FaceBoxes: A CPU Real-time Face Detector with High Accuracy

faciallandmark_caffe

Facial Landmark Detection with Caffe CNN. Face alignment avaiable.

fcn.berkeleyvision.org

Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.

goturn

Source code for paper: Learning to Track at 100 FPS with Deep Regression Networks, Held, et al. ECCV 2016

goturn-example

GOTURN tracker example using Caffe & OpenCV

idn-caffe

Caffe implementation of "Fast and Accurate Single Image Super-Resolution via Information Distillation Network" (CVPR 2018)

mask-rcnn

Implementation of Mask-RCNN in Caffe https://arxiv.org/pdf/1703.06870.pdf

mobilenet-caffe

Caffe Implementation of Google's MobileNets (v1 and v2)

ordinalregression

Caffe Loss Layer for Ordinal Regression with Multiple Output CNN for Age Estimation.

realtime_multi-person_pose_estimation

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

resnet-cifar10-caffe

ResNet 20 32 44 56 110 for CIFAR10 with caffe

resnet-on-cifar10

Reimplementation ResNet on cifar10 with caffe

segnet-tutorial

Files for a tutorial to train SegNet for road scenes using the CamVid dataset

shufflenet

This is a fast caffe implementation of ShuffleNet.

squeezenet-deep-compression

ssh

SSH: Single Stage Headless Face Detector

ssh-windows

Windows version for Single Stage Headless Face Detector

vmaf

Perceptual video quality assessment based on multi-method fusion.