YOLOv3: Training and inference in PyTorch

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. https://arxiv.org/abs/1812.00332

Implementation of YOLOv3 in PyTorch

Caffe: a fast open framework for deep learning.

This convert tools is base on TensorRT Int8 calibration tools,which use the KL algorithm to find the suitable threshold to quantize the activions from Float32 to Int8(-128 - 127).

Convolutional Neural Networks

A caffe implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.

caffe pretrained models and prototxt

Versatile Deep Learning Toolbox

A PyTorch implementation of MobileNet V2 architecture and pretrained model.

convert between pytorch, caffe prototxt/weights and darknet cfg/weights

SqueezeNet Generator

Deformable Convolutional Networks on caffe

DSOD: Learning Deeply Supervised Object Detectors from Scratch. In ICCV 2017.

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

YOLO object detector for Movidius Neural Compute Stick (NCS)

A personal depthwise convolution layer implementation on caffe by liuhao.(only GPU)

Breakout game for Android devices