Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
awesome-quantization-and-fixed-point-training
Neural Network Quantization & Low-Bit Fixed Point Training For Hardware-Friendly Algorithm Design
https://github.com/A-suozhang/awesome-quantization-and-fixed-point-training
Last synced: 6 days ago
JSON representation
-
Quantize-Aware Training
-
Fixed-Point Training
-
Binary
-
-
A. Post-Training Quantization
- 1510-Deep Compression
- 1702-Incremental Quantization
- 1511-Fixed Point Quantization of Deep Convolutional Network
- 1611-Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning
- 1711-NISP: Pruning Networks using Neuron Importance Score Propagation
- 1805-Retraining-Based Iterative Weight Quantization for Deep Neural Networks
- 1906-Data-Free Quantization through weiht equailization & Bias Correction
- 1810-Post training 4-bit quantization of convolutional networks for rapid-deployment(NIPS 2019)
- Entropy Constraint Scalar Quantization
- 1802-Model compression via distillation and quantization
- 1907-And the Bit Goes Down: Revisiting the Quantization of Neural Networks
-
B. Quantize-Aware-Training
- 1603-XNORNet
- 1802-Mixed Precision Training Of ConvNets Using Integer Operations-ICLR2018
- 1805-Accurate & Efficient 2-bit QNN
- 1905-hawq: hessian aware quantization of neuralnetworks with mixed-precision
- 1911-V2
- 1901-Improving Neural Network Quantization with Retraining Outlier Channel Splitting
- 1606-DoReFa
- 1802-WAGE - Training & Inference with Integers in DNN
- 1705-TernGrad
- 1905-mixed precision training with 8-bit floating point
- 1709-Flexible Network Binarization with Layer-wise Priority
- 1711-ReBNet: Residual Binarized Neural Network
- 1804-Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving
- 1902-Self-Binarizing Networks
- 1906-Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
- 2001-Least squares binary quantization of neural networks
- 2002-Widening and Squeezing: Towards Accurate and Efficient QNNs
- 1808-Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
- 1812-Training Competitive Binary Neural Networks from Scratch
- 1909-XNORNet++
- 2001-MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
- 1909-IRNet-Forward and Backward Information Retention for Accurate Binary Neural Networks
- Code at - Implemented with Distiller Library
- 1903-Training Quantized Network with Auxiliary Gradient Module
- 1808-Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss
- 1805-PACT
- 1711-Towards Accurate Binary Convolutional Neural Network
- 1805-Scalable Methods for 8-bit Training of Neural Networks
- 1602-Binarized Neural Networks
- 1901-Accumulation bit-width Scaling
- 1606-DoReFa
- 1812-Training Deep Neural Networks with 8-bit Floating Point Numbers
- 1511-BinaryConnect
- 1605-Ternary Weighted Network
- 1712-Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
- 1802-Mixed Precision Training Of ConvNets Using Integer Operations-ICLR2018
- 1905-hawq: hessian aware quantization of neuralnetworks with mixed-precision
- 1911-V2
- 1901-Improving Neural Network Quantization with Retraining Outlier Channel Splitting
- Towards Unified INT8 Training for Convolutional Neural Network
- 1909-IRNet-Forward and Backward Information Retention for Accurate Binary Neural Networks
-
量化方法（低比特）
-
理论分析
-
~~奇技淫巧~~
-
BN Related
- ernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
- Analysis Of Quantized MOdels-ICLR2019
- ReLeQ: An Automatic Reinforcement Learning Approach for Deep Quantization of Neural Networks
- Deep Learning with Low Precision by Half-wave Gaussian Quantization
- Learning low-precision neural networks without Straight-Through Estimator (STE)
- SWALP: Stochastic Weight Averaging in Low-Precision Training
- Ternary MobileNets via Per-Layer Hybrid Filter Banks
- Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations
- MoBiNet: A Mobile Binary Network for Image Classification
- Multi-Precision Quantized Neural Networks via Encoding Decomposition of -1 and +1
-
-
Tensorflow Lite
-
BN Related
-
-
PyTorch
-
Binary及其延申(极低比特)
-
Others
Programming Languages
Categories
Sub Categories