chuanqi305

MobileNet-SSD. Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

MobileNetv2-SSDLite. Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

FocalLoss. Caffe implementation of FAIR paper "Focal Loss for Dense Object Detection" for SSD.

SqueezeNet-SSD. SSD detection network of SqueezeNet, with pretrained weights on VOC0712 and mAP=0.643

rscnn. A cnn framework on Android platform, implemented with RenderScript and java, support MobileNet-SSD and faster-rcnn. No JNI/C++ or thirdparty dependencies.

KCF. python implementation of "high-speed tracking with kernelized correlation filters"

ssd. Caffe: a fast open framework for deep learning.

LeNet5. Pure numpy implementation of LeNet5, to help you understand how CNN works.

caffe-model. Caffe models (includimg classification, detection and segmentation) and deploy files for famouse networks

myshell. myshell