wxwang0104 / Quantized_ResNet
This repo is an implementation of quantized CNN for both weights (1-bit compression) and feature maps (2-bit compression).
☆18Updated 6 years ago
Related projects ⓘ
Alternatives and complementary repositories for Quantized_ResNet
- Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression☆47Updated last year
- Codes for AAAI2019 paper: Deep Neural Network Quantization via Layer-Wise Optimization using Limited Training Data☆41Updated 5 years ago
- Implement Towards Effective Low-bitwidth Convolutional Neural Networks☆42Updated 6 years ago
- PyTorch implementation for GAL.☆55Updated 4 years ago
- ☆25Updated 5 years ago
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers https://arxiv.org/abs/1802.00124☆71Updated 6 years ago
- ☆49Updated 5 years ago
- resnet_cifar10_cifar100_imagenet☆13Updated 6 years ago
- implementation of Iterative Pruning for Deep neural network [Han2015].☆40Updated 6 years ago
- Unofficial Pytorch implementation of Deep Compression in CIFAR10☆34Updated 3 years ago
- Two-Step Quantization on AlexNet☆13Updated 6 years ago
- Global Sparse Momentum SGD for pruning very deep neural networks☆43Updated 2 years ago
- Code repositoy for "AOWS: Adaptive and optimal network width search with latency constraints", CVPR 2020☆36Updated 4 years ago
- ☆38Updated 6 years ago
- Caffe implementation of ICCV 2017 & TPAMI 2018 paper - ThiNet☆46Updated 6 years ago
- HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs simply implement