Pre-trained Deep Learning models and samples (high quality and extremely fast)

MOT tracking using deepsort and yolov3 with pytorch

FaceRank - Rank Face by CNN Model based on TensorFlow (add keras version). FaceRank-人脸打分基于 TensorFlow (新增 Keras 版本) 的 CNN 模型（QQ群：167122861）。技术支持：http://tensorflow123.com

CNNs for Sentence Classification in PyTorch

Optical Character Recognition in Swift for iOS&macOS. 银行卡、身份证、门牌号光学识别

In PyTorch Learing Neural Networks Likes CNN(Convolutional Neural Networks for Sentence Classification (Y.Kim, EMNLP 2014) 、LSTM、BiLSTM、DeepCNN 、CLSTM、CNN and LSTM

Image Captcha Solving Using TensorFlow and CNN Model. Accuracy 90%+

ImageNet pre-trained models with batch normalization for the Caffe framework

Keras implementation of a ResNet-CAM model

基于深度学习的12306验证码识别

Deep Learning models for network traffic classification

To classify video into various classes using keras library with tensorflow as back-end.

Style transfer using deep convolutional neural nets

A simple Spatial Pyramid Pooling layer which could be added in CNN

Implementation of ShuffleNetV2 for pytorch

Openpose implementation using darknet

Object classification with CIFAR-10 using transfer learning

IPython Notebook for training a word-level Convolutional Neural Network model for sentiment classification task on Yelp-Challenge-2016 review dataset.

Train and deploy a cat vs dog image recognition model using TensorFlow

all kinds of demos of tensorflow code

CNN for heartbeat classification

Compare six baseline deep learning models on TrecQA

An Image classifier to identify whether the given image is Batman or Superman using a CNN with high accuracy. (From getting images from google to saving our trained model for reuse.)

Lviv Data Science Summer School 2016 project

Highway Networks implement in pytorch

Speaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2 speakers (on separate channels).

The source code and dataset are used to demonstrate the DF model, and reproduce the results of the ACM CCS2018 paper

A CNN model in numpy for gesture recognition

Using keras to implement VDCNN model