GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

Abstract

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. The Apache 2.0 license has been adopted by GluonCV and GluonNLP to allow for software distribution, modification, and usage.

References in corpus (6)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Caffe: Convolutional Architecture for Fast Feature Embedding
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Theano: new features and speed improvements
• Learning to Diagnose with LSTM Recurrent Neural Networks
• SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering

Cited by in corpus (22)

• Assessing bikeability with street view imagery and computer vision
• Revisiting Few-sample BERT Fine-tuning
• Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
• MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
• LEEP: A New Measure to Evaluate Transferability of Learned Representations
• Serving DNNs like Clockwork: Performance Predictability from the Bottom Up
• Attention-guided Chained Context Aggregation for Semantic Segmentation
• Deep Interest Highlight Network for Click-Through Rate Prediction in Trigger-Induced Recommendation
• BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language Recognition
• LOTR: Face Landmark Localization Using Localization Transformer
• LaProp: Separating Momentum and Adaptivity in Adam
• BoolNet: Minimizing The Energy Consumption of Binary Neural Networks
• Geolocated Social Media Posts are Happier: Understanding the Characteristics of Check-in Posts on Twitter
• Face Detection with Feature Pyramids and Landmarks
• Secure Watermark for Deep Neural Networks with Multi-task Learning
• Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances
• CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
• Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition
• GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning
• Improving Non-autoregressive Neural Machine Translation with Monolingual Data
• PyTorchVideo: A Deep Learning Library for Video Understanding
• Robustness-aware 2-bit quantization with real-time performance for neural network