Natsuda's repositories
C3D
C3D is a modified version of BVLC caffe to support 3D ConvNets.
caffe
Caffe: a fast open framework for deep learning.
chatbot-retrieval
Dual LSTM Encoder for Dialog Response Generation
DCGAN-tensorflow
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
deep-learning
Repo for the Deep Learning Nanodegree Foundations program.
densecap
Dense image captioning in Torch
Detectron
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
facenet
Face recognition using Tensorflow
fastText
Library for fast text representation and classification.
GCPArchitectureChallenge
This is a public repo
improved_wgan_training
Code for reproducing experiments in "Improved Training of Wasserstein GANs"
keras
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.
NeuroNER
Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results.
pandas
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
pythai
A collection of tools for working with the Thai language in Python
pythia
A modular framework for Visual Question Answering research by the FAIR A-STAR team
pytorch-seq2seq
pytorch-seq2seq is a framework for sequence-to-sequence (seq2seq) models in PyTorch.
scikit-multilearn
A scikit-learn based module for multi-label et. al. classification
seq2seq_temporal_attention
Generating Video Description using Sequence-to-sequence Model with Temporal Attention
tensorflow
Computation using data flow graphs for scalable machine learning
tensorflow-template
Template for train/predict/test in Tensorflow
tilse
Timeline summarization and evaluation.
wordvectors
Pre-trained word vectors of 30+ languages
youtube-8m
Starter code for working with the YouTube-8M dataset.