220 Open source projects that are alternatives of or similar to Daps

Deep Reinforcement Learning for Keras.

A course in reinforcement learning in the wild

Theano implementation of XNOR-Net

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

A collection of recent video understanding datasets, under construction!

使用Theano实现的一些RNN代码，包括最基本的RNN，LSTM，以及部分Attention模型，如论文MLSTM等

Gluon CV Toolkit

Training Toolbox for Caffe

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

Hierarchical Co-occurrence Network with Prototype Loss for Few-shot Learning (PyTorch)

Setup and customize deep learning environment in seconds.

Implementation of a hierarchical CNN based model to detect Big Five personality traits

Collection of iris classifcation program for teaching purpose

RNN-based generative models for speech.

Generating proportional fonts with deep learning

Keras package for region-based convolutional neural networks (RCNNs)

Video classification tools using 3D ResNet

A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text

EPIC-KITCHENS-55 baselines for Action Recognition

PyTorch implementation of two-stream networks for video action recognition

3-day dive into deep learning at csc

GemPy is an open-source, Python-based 3-D structural geological modeling software, which allows the implicit (i.e. automatic) creation of complex geological models from interface and orientation data. It also offers support for stochastic modeling to adress parameter and model uncertainties.

Detects Chinese traffic police commanding poses 检测中国交警指挥手势

Action recognition using soft attention based deep recurrent neural networks

An implementation of RNN-RBM & GBRBM.

💻 Make machines learn so that you don't have to struggle to program them; The ultimate list

Implementation of Dynamic memory networks by Kumar et al. http://arxiv.org/abs/1506.07285

Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection

中文 Python 笔记

A deep generative model library in Theano and Lasagne

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

temporal action detection with SSN

This is now the official location of the Merlin project.

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is coupled with the Kaldi decoder.

GPU-accelerated Deep Learning on Windows 10 native

several basic neural networks[mlp, autoencoder, CNNs, recurrentNN, recursiveNN] implements under several NN frameworks[ tensorflow, pytorch, theano, keras]

Neural Machine Translation with Keras

An implementation of the RoiAlign operation for Theano

A deep neural network for face alignment

As a part of the HAKE project, includes the reproduced SOTA models and the corresponding HAKE-enhanced versions (CVPR2020).

Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.

Sets up a VM with Keras, TensorFlow, TFLearn and Theano installed

Deep Convolutional Neural Networks for Musical Source Separation

ResGCN: an efficient baseline for skeleton-based human action recognition.

Text Classification Library in Keras

Temporal Segment Networks (TSN) in PyTorch

Lightweight library to build and train neural networks in Theano

Real time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition

Skeleton-based Action Recognition

Action recognition.基于C3D的视频动作识别

Reimplementation of DRAW

This toolbox is support material for the book on CNN (http://www.convolution.network).

Keras implementation of BERT with pre-trained weights

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

Materials for the course of machine learning at Imperial College organized by Yandex SDA

AIOpen是一个按人工智能三要素（数据、算法、算力）进行AI开源项目分类的汇集项目，项目致力于跟踪目前人工智能（AI）的深度学习（DL）开源项目，并尽可能地罗列目前的开源项目，同时加入了一些曾经研究过的代码。通过这些开源项目，使初次接触AI的人们对人工智能（深度学习）有更清晰和更全面的了解。

DL course co-developed by YSDA, HSE and Skoltech

Gesture recognition via CNN. Implemented in Keras + Tensorflow/Theano + OpenCV