research

TensorFlow Research Models

This directory contains code implementations and pre-trained models of published research papers.

The research models are maintained by their respective authors.

Table of Contents

• Modeling Libraries and Models
• Models and Implementations
  • Computer Vision
  • Natural Language Processing
  • Audio and Speech
  • Reinforcement Learning
  • Others
• Archived Models and Implementations (:no_entry_sign: No longer maintained)

Modeling Libraries and Models

Directory	Name	Description	Maintainer(s)
object_detection	TensorFlow Object Detection API	A framework that makes it easy to construct, train and deploy object detection models A collection of object detection models pre-trained on the COCO dataset, the Kitti dataset, the Open Images dataset, the AVA v2.1 dataset, and the iNaturalist Species Detection Dataset	@jch1, @tombstone, @pkulzc
slim	TensorFlow-Slim Image Classification Model Library	A lightweight high-level API of TensorFlow for defining, training and evaluating image classification models • Inception V1/V2/V3/V4 • Inception-ResNet-v2 • ResNet V1/V2 • VGG 16/19 • MobileNet V1/V2/V3 • NASNet-A_Mobile/Large • PNASNet-5_Large/Mobile	@sguada, @marksandler2

Models and Implementations

Computer Vision

Directory	Referenece (Paper)	Maintainer(s)
attention_ocr	Attention-based Extraction of Structured Information from Street View Imagery	xavigibert
autoaugment	[1] AutoAugment [2] Wide Residual Networks [3] Shake-Shake regularization [4] ShakeDrop Regularization for Deep Residual Learning	barretzoph
deeplab	[1] DeepLabv1 [2] DeepLabv2 [3] DeepLabv3 [4] DeepLabv3+	aquariusjay, yknzhu
delf	[1] DELF (DEep Local Features): Large-Scale Image Retrieval with Attentive Deep Local Features [2] Detect-to-Retrieve	andrefaraujo
lstm_object_detection	Mobile Video Object Detection with Temporally-Aware Feature Maps	yinxiaoli, yongzhe2160, lzyuan
marco	Classification of crystallization outcomes using deep convolutional neural networks	vincentvanhoucke
vid2depth	Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints	rezama

Natural Language Processing

Directory	Referenece (Paper)	Maintainer(s)
adversarial_text	[1] Adversarial Training Methods for Semi-Supervised Text Classification [2] Semi-supervised Sequence Learning	rsepassi, a-dai
cvt_text	Semi-supervised sequence learning with cross-view training	clarkkev, lmthang

Audio and Speech

Directory	Referenece (Paper)	Maintainer(s)
audioset	[1] AudioSet: A Large Scale Dataset of Audio Events [2] CNN Architectures for Large-Scale Audio Classification	plakal, dpwe

Reinforcement Learning

Directory	Referenece (Paper)	Maintainer(s)
efficient-hrl	[1] Data-Efficient Hierarchical Reinforcement Learning [2] Near-Optimal Representation Learning for Hierarchical Reinforcement Learning	ofirnachum
pcl_rl	[1] Improving Policy Gradient by Exploring Under-appreciated Rewards [2] Bridging the Gap Between Value and Policy Based Reinforcement Learning [3] Trust-PCL: An Off-Policy Trust Region Method for Continuous Control	ofirnachum

Others

Directory	Referenece (Paper)	Maintainer(s)
lfads	LFADS - Latent Factor Analysis via Dynamical Systems	jazcollins, sussillo
rebar	REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models	gjtucker

---

⚠️ Archived Models and Implementations

The following research models are no longer maintained.

Note: We will remove archived models from the master branch in June, 2020. After removal, you will still be able to access archived models in the archive branch.

Directory	Referenece (Paper)	Maintainer(s)
adv_imagenet_models	[1] Adversarial Machine Learning at Scale [2] Ensemble Adversarial Training: Attacks and Defenses	alexeykurakin
adversarial_crypto	Learning to Protect Communications with Adversarial Neural Cryptography	dave-andersen
adversarial_logit_pairing	Adversarial Logit Pairing	alexeykurakin
autoencoder	Various autoencoders	snurkabill
brain_coder	Neural Program Synthesis with Priority Queue Training	danabo, mnorouzi
cognitive_mapping_and_planning	Cognitive Mapping and Planning for Visual Navigation	s-gupta
compression	Full Resolution Image Compression with Recurrent Neural Networks	nmjohn
deep_contextual_bandits	Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling	rikel
deep_speech	Deep Speech 2	yhliang2018
domain_adaptation	[1] Domain Separation Networks [2] Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks	bousmalis, dmrd
feelvos	FEELVOS	pvoigtlaender, yuningchai, aquariusjay
fivo	Filtering variational objectives for training generative sequence models	dieterichlawson
global_objectives	Scalable Learning of Non-Decomposable Objectives	mackeya-google
im2txt	Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge	cshallue
inception	Rethinking the Inception Architecture for Computer Vision	shlens, vincentvanhoucke
keypointnet	KeypointNet	mnorouzi
learned_optimizer	Learned Optimizers that Scale and Generalize	olganw, nirum
learning_to_remember_rare_events	Learning to Remember Rare Events	lukaszkaiser, ofirnachum
learning_unsupervised_learning	Meta-Learning Update Rules for Unsupervised Representation Learning	lukemetz, nirum
lexnet_nc	Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model	vered1986, waterson
lm_1b	Exploring the Limits of Language Modeling	oriolvinyals, panyx0718
lm_commonsense	A Simple Method for Commonsense Reasoning	thtrieu
maskgan	MaskGAN: Better Text Generation via Filling in the______	liamb315, a-dai
namignizer	Namignizer	knathanieltucker
neural_gpu	Neural GPUs Learn Algorithms	lukaszkaiser
neural_programmer	Learning a Natural Language Interface with Neural Programmer	arvind2505
next_frame_prediction	Visual Dynamics	panyx0718
ptn	Perspective Transformer Nets	xcyan, arkanath, hellojas, honglaklee
qa_kg	Learning to Reason	yuyuz
real_nvp	Density estimation using Real NVP	laurent-dinh
sentiment_analysis	Effective Use of Word Order for Text Categorization with Convolutional Neural Networks	sculd
seq2species	Seq2Species: A deep learning approach to pattern recognition for short DNA sequences	apbusia, depristo
skip_thoughts	Skip-Thought Vectors	cshallue
steve	Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion	buckman-google
street	End-to-End Interpretation of the French Street Name Signs Dataset	theraysmith
struct2depth	Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos	aneliaangelova
swivel	Swivel: Improving Embeddings by Noticing What's Missing	waterson
tcn	Time-Contrastive Networks: Self-Supervised Learning from Video	coreylynch, sermanet
textsum	A Neural Attention Model for Abstractive Sentence Summarization	panyx0718, peterjliu
transformer	Spatial Transformer Network	daviddao
video_prediction	Unsupervised Learning for Physical Interaction through Video Prediction	cbfinn

---

Contributions

If you want to contribute, please review the contribution guidelines.