canteen-man Goto Github PK

arm_neon_conv_3-3

3*3 conv by arm neon

bnn-pynq

caffe-int8-convert-tools

This convert tools is base on TensorRT 2.0 Int8 calibration tools,which use the KL algorithm to find the suitable threshold to quantize the activions from Float32 to Int8(-128 - 127).

caffe-segmentation

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

caffe-yolo

Caffe for YOLO

caffe-yolo-1

YOLO (Real-Time Object Detection) in caffe

cnn_fpga_zynq_pynq

hls code zynq 7020 pynq z2 CNN

cuda-program

CUDA Program：CUDA image rgb to gray；CUDA KLT

darknet

Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores is used)

ds-600-final-project

DS-600-Final-project, housing price, feature selection and prediction

fcn.berkeleyvision.org

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

fcn_caffe_cpp_forward

fcn_caffe_cpp_forward

gaitset

A flexible, effective and fast cross-view gait recognition network

gpu-efficient-networks

mmdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

mobilenet-ssd-focal-loss

MobileNet-SSD-Focal-loss

pynq

Python Productivity for ZYNQ

pytorch-pruning

PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference

squeezenet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters