FDDB数据集的图片来自于美联社和路透社新闻报道图片，并删除了重复图片。数据集包含2845张图片，共有5171个人脸作为测试集。测试集范围包括：不同姿势、不同分辨率、旋转和遮挡等图片，同时包括灰度图和彩色图，标准的人脸标注区域为椭圆形。
标签：图像识别
Imagenet数据集是目前深度学习图像领域应用得非常多的一个领域，可用于图像分类、定位、检测等研究工作。数据集有1400多万幅图片，涵盖2万多个类别，其中有超过百万的图片有明确的类别标注和图像中物体位置的标注。
COCO数据集由微软赞助，其对于图像的标注信息不仅有类别、位置信息，还有对图像的语义文本描述，COCO数据集在图像分割语义理解取得了巨大的进展。
Deep Learning API and Server in C++11 with Python bindings and support for Caffe, Tensorflow, XGBoost and TSNE
Tensorflow port of Image-to-Image Translation with Conditional Adversarial Nets https://phillipi.github.io/pix2pix/
subpixel: A subpixel convnet for super resolution with Tensorflow
Image-to-image translation with conditional adversarial nets
Face recognition with deep neural networks.
Neural style in TensorFlow!
Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to anoth...
Multi-Person Pose Estimation System
deepgazeComputer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Netwo...
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
Automatic License Plate Recognition library
Keras implementation of 'LipNet: End-to-End Sentence-level Lipreading'
Face recognition using Tensorflow
An MXNet implementation of Mask R-CNN
The world's simplest facial recognition api for Python and the command line
High Performance Chinese License Plate Recognition Framework.
Deep Residual Learning for Image Recognition