BenWhetton / keras-surgeon
Pruning and other network surgery for trained Keras models.
☆405Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for keras-surgeon
- A machine learning experiment☆182Updated 7 years ago
- SqueezeNet implementation with Keras Framework☆404Updated last year
- PyTorch Implementation of [1611.06440] Pruning Convolutional Neural Networks for Resource Efficient Inference☆875Updated 5 years ago
- Convert trained PyTorch models to Keras, and the other way around☆226Updated 5 years ago
- CondenseNet: Light weighted CNN for mobile devices☆694Updated 5 years ago
- PyTorch to Keras model convertor☆858Updated last year
- Implementation of ResNeXt models from the paper Aggregated Residual Transformations for Deep Neural Networks in Keras 2.0+.☆224Updated 3 years ago
- Implementation of One-Cycle Learning rate policy (adapted from Fast.ai lib)☆285Updated 4 years ago
- The Inception-ResNet v2 model using Keras (with weight files)☆180Updated 3 years ago
- Keras model convolutional filter pruning package☆44Updated 5 years ago
- Keras package for deep residual networks☆300Updated last year
- Compress neural network with pruning and quantization using TensorFlow.☆105Updated 5 years ago
- A Pytorch implementation of Neural Network Compression (pruning, deep compression, channel pruning)☆153Updated 4 months ago
- Keras Implementation of EfficientNets☆187Updated 4 years ago
- Implementation of model compression with knowledge distilling method.☆346Updated 7 years ago
- ☆240Updated 6 years ago
- Implementation of Squeeze and Excitation Networks in Keras☆400Updated 4 years ago
- Model Compression CLI Tool for Keras.☆157Updated 5 years ago
- ☆302Updated 3 years ago
- Quantized Neural Networks - networks trained for inference at arbitrary low precision.☆146Updated 6 years ago
- RAdam implemented in Keras & TensorFlow☆325Updated 2 years ago
- Keras implementation of Efficient Neural Architecture Search☆90Updated 6 years ago
- Code for: "And the bit goes down: Revisiting the quantization of neural networks"☆636Updated 4 years ago
- A Simply Example to show how to use Keras model in multiple processes to do the prediction☆111Updated 6 years ago
- a list of awesome papers on deep model ompression and acceleration☆349Updated 3 years ago
- Memory consumption and FLOP count estimates for convnets☆919Updated 5 years ago
- "NASNet" models in Keras 2.0+ with weights☆199Updated 6 years ago
- Papers for deep neural network compression and acceleration☆396Updated 3 years ago
- Code for https://arxiv.org/abs/1810.04622☆139Updated 5 years ago