Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)
-
Updated
Jun 7, 2020 - Python
#
network-pruning
Here are 21 public repositories matching this topic...
Efficient Sparse-Winograd Convolutional Neural Networks (ICLR 2018)
-
Updated
May 7, 2019 - Python
This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" by Jonathan Frankle and Michael Carbin that can be easily adapted to any model/dataset.
python
deep-learning
pytorch
pruning
lottery
network-pruning
pytorch-implementation
iclr2019
lottery-ticket-hypothesis
winning-ticket
-
Updated
Nov 3, 2019 - Python
Code for "EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis" https://arxiv.org/abs/1905.05934
-
Updated
Mar 3, 2020 - Python
SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY
-
Updated
Jun 26, 2019 - Python
Tensorflow codes for "Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers"
-
Updated
Oct 14, 2019 - Python
CAE-ADMM: Implicit Bitrate Optimization via ADMM-Based Pruning in Compressive Autoencoders
pytorch
model-architecture
image-compression
admm
autoencoders
network-pruning
lossy-image-compression
-
Updated
May 20, 2019 - Python
A pytorch pruning toolkit for structured neural network pruning and layer dependency maintaining.
-
Updated
Mar 21, 2020 - Python
-
Updated
Nov 21, 2017
Implementation of Autoslim using Tensorflow2
-
Updated
Jun 5, 2020 - Python
-
Updated
May 28, 2020 - Python
Gifts from Iterative Network Pruning
deep-learning
pytorch
convolutional-neural-networks
network-pruning
weight-pruning
image-net
filter-pruning
structured-pruning
unstructured-pruning
iterative-pruning
-
Updated
Jun 25, 2020 - Jupyter Notebook
Cheng-Hao Tu, Jia-Hong Lee, Yi-Ming Chan and Chu-Song Chen, "Pruning Depthwise Separable Convolutions for MobileNet Compression," International Joint Conference on Neural Networks, IJCNN 2020, July 2020.
deep-neural-networks
pytorch
model-compression
mobilenet
efficient-inference
channel-pruning
network-pruning
depthwise-separable-convolutions
filter-pruning
-
Updated
Apr 7, 2020
Channel-Prioritized Convolutional Neural Networks for Sparsity and Multi-fidelity
-
Updated
Feb 23, 2018 - Python
Improved Implementation of Single Shot MultiBox Detector, RefineDet and Network Optimization in Pytorch 07/2018
-
Updated
Aug 17, 2018 - Python
Reducing the computational overhead of Deep CNNs through parameter pruning and tensor decomposition.
-
Updated
May 28, 2020 - Python
Pruning neural networks directly with back-propagation
-
Updated
Jun 26, 2020 - Python
collection of works aiming at reducing model sizes or the ASIC/FPGA accelerator for machine learning
-
Updated
Jul 8, 2018
Network acceleration methods
-
Updated
Sep 23, 2018
This repository contains a Pytorch implementation of the article "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" and an application of this hypothesis to reinforcement learning
-
Updated
May 29, 2020 - Python
Improve this page
Add a description, image, and links to the network-pruning topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the network-pruning topic, visit your repo's landing page and select "manage topics."
In the code, it seems that you use the model stored in ema to do the validation and get the final result.Here i have two questions:
1.Why do you use the ema model to do the validation, but do not use the model_wrapper which is directely preuned?
2.Is it supposed that ema model will get better result than model_wrapper?And why?
Thanks very much for your reply!