Feng Wang's starred repositories
google-research
Google Research
DeepLearningExamples
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
FasterTransformer
Transformer related optimization, including BERT, GPT
x-deeplearning
An industrial deep learning framework for high-dimension sparse data
tensorflow-internals
It is open source ebook about TensorFlow kernel and implementation mechanism.
micronet
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
Distributed-TensorFlow-Guide
Distributed TensorFlow basics and examples of training algorithms
Taylor_pruning
Pruning Neural Networks with Taylor criterion in Pytorch
sparsehash-c11
Experimental C++11 version of sparsehash
Co-Action-Network
Implementation of CAN: Revisiting Feature Co-Action for Click-Through RatePrediction
bigcomputing
bigcomputing
awd-lstm-tensorflow
AWD-LSTM from "Regularizing and Optimizing LSTM Language Models" with training-award quantization support for tensorflow.