PocketFlow - An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications

•    Python

---

PocketFlow is an open-source framework for compressing and accelerating deep learning models with minimal human effort. Deep learning is widely used in various areas, such as computer vision, speech recognition, and natural language translation. However, deep learning models are often computational expensive, which limits further applications on mobile devices with limited computational resources. PocketFlow aims at providing an easy-to-use toolkit for developers to improve the inference efficiency with little or no performance degradation. Developers only needs to specify the desired compression and/or acceleration ratios and then PocketFlow will automatically choose proper hyper-parameters to generate a highly efficient compressed model for deployment.

deep-learning model-compression mobile-app automl computer-vision

NeuronBlocks - NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego

•    Python

---

NeuronBlocks is a NLP deep learning modeling toolkit that helps engineers/researchers to build end-to-end pipelines for neural network model training for NLP tasks. The main goal of this toolkit is to minimize developing cost for NLP deep neural network model building, including both training and inference stages. NeuronBlocks consists of two major components: Block Zoo and Model Zoo.

question-answering deep-learning pytorch natural-language-processing text-classification artificial-intelligence dnn qna text-matching knowledge-distillation model-compression

channel-pruning - Channel Pruning for Accelerating Very Deep Neural Networks

•    Python

---

Please have a look at AMC: AutoML for Model Compression and Acceleration on Mobile Devices ECCV'18, which combines channel pruning and reinforcement learning to further accelerate CNN.

image-recognition model-compression acceleration object-detection image-classification channel-pruning deep-neural-networks

mobile-id - Deep Face Model Compression

•    Matlab

---

Further information please contact Ziwei Liu. Note that there are no identity overlapping between CelebA Dataset and LFW Dataset.

computer-vision deep-learning face-recognition model-compression efficient-inference