matthew-mcateer / Keras_pruningLinks
A walkthrough of how to prune keras models, using both weight-pruning and unit/neuron-pruning.
☆30Updated 6 years ago
Alternatives and similar repositories for Keras_pruning
Users that are interested in Keras_pruning are comparing it to the libraries listed below
Sorting:
- Repository to track the progress in model compression and acceleration☆106Updated 4 years ago
- Post-training static quantization using ResNet18 architecture☆37Updated 5 years ago
- On-the-fly Structured Pruning for PyTorch models. This library implements several attributions metrics and structured pruning utils for n…☆167Updated 5 years ago
- PyTorch Static Quantization Example☆38Updated 4 years ago
- Yolov3 (+tiny) pythonic pytorch implementation.☆34Updated 7 years ago
- PyTorch Pruning Example☆50Updated 2 years ago
- Demonstrates knowledge distillation for image-based models in Keras.☆54Updated 4 years ago
- Tutorials on Quantized Neural Network using Tensorflow Lite☆87Updated 6 years ago
- Code for training Keras ImageNet (ILSVRC2012) image classification models from scratch☆71Updated 3 years ago
- FLOPs and other statistics COunter for tf.keras neural networks☆30Updated 3 years ago
- A Numpy implementation of a Convolutional Neural Network: slow & fast (im2col/col2im).☆58Updated 2 years ago
- Unofficial Pytorch implementation of Deep Compression in CIFAR10☆35Updated 4 years ago
- Train ResNet on ImageNet in Tensorflow 2.0; ResNet 在ImageNet上完整训练代码☆84Updated 5 years ago
- Summary & Implementation of Deep Learning research paper in Tensorflow/Pytorch.☆39Updated 5 years ago
- papers about model compression☆165Updated 2 years ago
- Guide for quantization, conversation of the tensorflow model to tensorflow lite☆20Updated 2 years ago
- PyTorch Quantization Aware Training Example☆140Updated last year
- FLOPs calculator with tf.profiler for neural network architecture written in tensorflow 2.2+ (tf.keras)☆55Updated last year
- This is a function for estimating the floating point operations (FLOPS) of deep learning models developed with keras.