Python codes in Machine Learning, NLP, Deep Learning and Reinforcement Learning with Keras and Theano

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

StyleGAN Encoder - converts real images to latent space

Keras implementation of a ResNet-CAM model

An easy implementation of Faster R-CNN (https://arxiv.org/pdf/1506.01497.pdf) in PyTorch.

A one stop shop for all of your activity recognition needs.

CoreML.framework Demo App

A Multiclass Weed Species Image Dataset for Deep Learning

Learning Fine-grained Image Similarity with Deep Ranking is a novel application of neural networks, where the authors use a new multi scale architecture combined with a triplet loss to create a neural network that is able to perform image search. This repository is a simplified implementation of the same

code for ICCV19 paper "Deep Meta Metric Learning"

CP and Tucker decomposition for Convolutional Neural Networks

Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification (AAAI2019)

No reference image quality assessment based Semantic Feature Aggregation, published in ACM MM 2017, TMM 2019

resnetが料理の材料をあてます

Image classification of wildflowers using deep residual learning and convolutional neural nets

Visualizing where the Convolution Network is looking through CAM.

IntelliP (Intelligent Photos) is a Windows photo gallery that intelligently organizes the pictures in your computer into 12 unique and related categories.

An easy implementation of FPN (https://arxiv.org/pdf/1612.03144.pdf) in PyTorch.

Computer Vision - Impemented algorithms - Hybrid image, Corner detection, Scale space blob detection, Scene classifiers, Vanishing point detection, Finding height of an object, Image stitching.

This is an experimental code to train a ResNet-50 made entirely in Tensorflow on Dogs-vs-Cats-Redux

🌮 Classify Food Images from the Food-101 Dataset Using Transfer Learning (ResNet50).

A tutorial on Residual Networks which was originally proposed by Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun from Microsoft Research Team.

Keras Implementation of major CNN architectures

Deep-learning seismic facies on state-of-the-art CNN architectures

A project developed and maintained as part of the aim at bringing current capabilities in machine learning and artificial intelligence into practical use for non-programmers and average computer users.

Deep CNN-LSTM for Generating Image Descriptions :smiling_imp:

A web application + neural net to distinguish baby boys and girls

This is an implementation of ResNet-50/101/152.

Image recognition iOS app with Apple’s CoreML and Vision APIs

Classifying the type of property given Real Estate, satellite and Street view Images