cassiaaaaaa Goto Github PK

activitynet-video-downloader

This simple script is for downloading videos of ActivityNet dataset by parsing URLs from given .json file.

attention-module

Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"

attention_branch_network

Attention Branch Network (CIFAR100, ImageNet models)

awesome_cnn

A collection of CNN structures, contains PyTorch Implementation and Netscope Visualization.

caffe

Caffe on both Linux and Windows

caffe-model

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

caffe_lightweightnet

This is a caffe project for Lightweight Network

caffelstm-ocr

基于caffe的LSTM OCR案例，能够利用该案例完成序列的识别，包括验证码、车牌、身份证号码、地址等长序列动长的内容识别

changed_endian_filename

the storation of characters includes big-endian and small-endian according to the different CPU ways. this code shows the change of endians in the filename.

changedmodels

cjk_symbol

to seperate CJK characters with symbols by Unicode.

cntk

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

computervisionpractice

Reviewing CV in Python

cvpr2019_pyramid-feature-attention-network-for-saliency-detection

code and model of Pyramid Feature Selective Network for Saliency detection

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

find_different_move

accodring to the .txt list, to find the difference of two folers( one is included by another one), and to move the anti-intersection into some other folder.

handwritten-sequence-tensorflow

Tensorflow implementation of handwritten sequence of small letters recognition.

hccr-googlenet

This project is about directional feature extraction and HCCR-GoogLeNet CNN architecture definition for Caffe platform.

hccr-resnet

incubator-mxnet

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

label_smoothing

Corrupted labels and label smoothing

layrub

Layrub is a runtime data placement strategy for extreme-scale net training. It is developed on BVLC Caffe, and achieves memory savings more than 50% over BVLC Caffe.

lovaszsoftmax

Code for the Lovász-Softmax loss (CVPR 2018)

lstm_ctc_ocr

Use CTC + tensorflow to OCR

manchutensorflow

mdlstm+ctc

mdlstm

Multi-Dimensional Recurrent Neural Networks Tensorflow 1.0

mmdetection

OpenMMLab Detection Toolbox and Benchmark

mmdetection-mini

mmdetection最小学习版

mobilenet-caffe

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

mobilenet-v2-mxnet

the symbol description of mobilenet v2