Stars
Submit stacked diffs to GitHub on the command line
Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS
LightSeq: A High Performance Library for Sequence Processing and Generation
CaoE / lightseq
Forked from bytedance/lightseqLightSeq: A High Performance Library for Sequence Processing and Generation
Tools to run and parse MKL verbose mode
Counting Float/Int operation in a C/C++ function using a numeric C++ class OR parsing the generated assembler code for ARM
Feedforward style transfer
Torch implementation for the paper "Artistic style transfer for videos"
mingfeima / AdaIN-style
Forked from xunhuang1995/AdaIN-styleArbitrary Style Transfer in Real-time with Adaptive Instance Normalization
Speech Recognition using DeepSpeech2 network and the CTC activation function.
mingfeima / warp-ctc
Forked from baidu-research/warp-ctcFast parallel CTC.
Benchmark omp threshold for pytorch.
A PyTorch implementation of MobileNet V2 architecture and pretrained model.
mingfeima / audio
Forked from pytorch/audiosimple audio I/O for pytorch
Speech Recognition using DeepSpeech2.
PyTorch wheel installation file with performance optimization on CPU
mingfeima / wavenet_vocoder
Forked from r9y9/wavenet_vocoderWaveNet vocoder
Easy benchmarking of all publicly accessible implementations of convnets with pytorch support
mingfeima / crnn.pytorch
Forked from meijieru/crnn.pytorchConvolutional recurrent network in pytorch
mingfeima / OpenNMT-py
Forked from OpenNMT/OpenNMT-pyOpen-Source Neural Machine Translation in PyTorch http://opennmt.net/ with multi node support
mingfeima / horovod
Forked from horovod/horovodDistributed training framework for TensorFlow, Keras, and PyTorch.
mingfeima / examples
Forked from pytorch/examplesA set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
parser script to process pytorch autograd profiler result, convert json file to excel.
RNN Performance benchmark on PyTorch
mingfeima / XNNPACK
Forked from google/XNNPACKHigh-efficiency floating-point neural network inference operators for mobile, server, and Web