egrass Goto Github PK

-

ab-lstm

AB-LSTM: Attention-Based Bidirectional LSTM Model for Scene Text Detection

acfpedestriandetection

基于ACF行人检测框架，引入EdgeBox特征和Salient特征，使用real adaboost算法，显著提高行人检测算法的准确率和泛化能力。

ar-ped

awesome-crowd-counting

Awesome Crowd Counting

awesome-multi-label-image-recognition

Awesome Multi-label Image Recognition Paper List

bbox-label-tool

A simple tool for labeling object bounding boxes in images

caffe

Caffe fork that supports SPP_net or faster R-CNN

caffe-fast-rcnn

Caffe fork that supports Fast R-CNN

caffe-model

Caffe models (imagenet pretrain) and prototxt generator scripts for inception_v3 \ inception_v4 \ inception_resnet \ fractalnet \ resnext

caffe-rfcn

Caffe branch for R-FCN

caffe-rpn_bf

caffe-segmentation

Train/eval code for DilatedConv [Yu, ICLR'16], DeepLab-v2 [Chen, Arxiv'16], PSPNet [Zhao, CVPR'17]

caffe-weighted_softmax_loss_layer

Source files of a weighted_softmax_with_loss layer for latest version of caffe. Allow wild cards to be accepted as a bottom

caffe-yolo

Caffe for YOLO

caffe_densenet_focal_loss

Add focal loss to caffe

caffe_mod

latest caffe official release + transpose layer

cameracalibration

Fisheye or Normal Camera Intrinsic and Extrinsic Calibration. Surround Camera Bird Eye View Generator.

crowdcount-cascaded-mtl

Single Image Crowd Counting (CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting)

crowdcount-mcnn

Single Image Crowd Counting via MCNN (Unofficial Implementation)

cvc09_matlab

imageset annovations convert to bbGet

da-svms

Various SVM based methods for domain adaptation

dan

Code release of "Learning Transferable Features with Deep Adaptation Networks" (ICML 2015)

danet

Dual Attention Network for Scene Segmentation (CVPR2019)

darknet

The yolo for pedestrian detection task.

datatool

SCUT FIR Pedestrian Dataset data toolbox

ddc-transfer-learning

A simple implementation of Deep Domain Confusion: Maximizing for Domain Invariance

deep-crowd-counting_crowdnet

An independent implementation of "CrowdNet: A Deep Convolutional Network for Dense Crowd Counting"

deep_scene

deeplearning