desklee's starred repositories
simple-onnx-processing-tools
A set of simple tools for splitting, merging, OP deletion, size compression, rewriting attributes and constants, OP generation, change opset, change to the specified input order, addition of OP, RGB to BGR conversion, change batch size, batch rename of OP, and JSON convertion for ONNX models.
channel_v3_daily
每天定时更新channel_v3.json，解决 Sublime Text 3 拓展包源无法访问问题，fix the problem that can not access packagecontrol.io
EEG-BayesianCNN
This is an EEG Signals Classification based on Bayesian Convolutional Neural Network (Bayesian CNNs) via Variational Inference.
EEG_classification
EEG Sleep stage classification using CNN with Keras
CompressiveSensingDictionaryLearning
Compressive Sensing using Sparse Dictionary Learning
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
PyTorch-Static-Quantization
PyTorch Static Quantization Example
pytorch-OpCounter
Count the MACs / FLOPs of your PyTorch model.
flops-counter.pytorch
Flops counter for convolutional networks in pytorch framework
nn_dataflow
Explore the energy-efficient dataflow scheduling for neural networks.
NeuralPower
The code for paper: Neuralpower: Predict and deploy energy-efficient convolutional neural networks
hyperpower
Hardware-aware Neural Network (Keras+TensorFlow) Hyper-parameter Optimization (Bayesian optimization)
nas_rnn_cpu
nas for cnn rnn
single-path-nas
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
enas_pytorch
PyTorch port of "Efficient Neural Architecture Search via Parameters Sharing"
compression-framework-pytorch
Reproducing An End-to-End Compression Framework Based on Convolutional Neural Network in PyTorch
Quantized-ENAS-ConvNets
Quantized (half-precision) CNNs via Efficient Neural Architecture Search (ENAS)
auto-sklearn
Automated Machine Learning with scikit-learn
ENAS-pytorch
PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"