vikingee's repositories
alpha-zero
AlphaZero implementation for Othello, Connect-Four and Tic-Tac-Toe based on "Mastering the game of Go without human knowledge" and "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm" by DeepMind.
Deep-Learning-21-Examples
《21个项目玩转深度学习———基于TensorFlow的实践详解》配套代码
DeepReinforcementLearning
A replica of the AlphaZero methodology for deep reinforcement learning in Python
drl_binpacking
3D bin packing is a classical and challenging combinatorial optimization problem in logistics and production systems. An effective bin packing algorithm means the reduction of total packing cost and increase in utilization of resources. Because the cost of packing materials, which is mainly determined by their surface area, occupies the most part of packing cost, and in many real business scenarios there is no bin with fixed size, so AI Department of Cainiao proposed a new type of 3D bin packing problem. The objective of this new type of 3D bin packing problem is to pack all items into a bin with minimized surface area. And a DRL method based on the sequence-to-sequence model is proposed to solve the problem. This is the research paper link: https://arxiv.org/abs/1708.05930. Source code of this method can be found in the project.
face_classification
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
HandDetector
Hand and Fingertip Detecot with OpenCV
keras-yolo3
A Keras implementation of YOLOv3 (Tensorflow backend)
neural_image_captioning
Neural image captioning (NIC) implementation with Keras 2.
reinforcement-learning-an-introduction
Python Implementation of Reinforcement Learning: An Introduction
Reinforcement_Learning-101-demo
A self-contained laboratory session, of a Reinforcement Learning model (A3C) playing Atari Space Invaders.
ReinforcementLearning-AtariGame
Pytorch LSTM RNN for reinforcement learning to play Atari games from OpenAI Universe. We also use Google Deep Mind's Asynchronous Advantage Actor-Critic (A3C) Algorithm. This is much superior and efficient than DQN and obsoletes it. Can play on many games
RL-solitaire
Solving the game of peg solitaire with a Reinforcement Learning Algorithm.
ssd_keras
A Keras port of Single Shot MultiBox Detector
TensorFlow-Tutorials
TensorFlow Tutorials with YouTube Videos