alecwangcq / Grasp
Licence: mit
Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH
Stars: ✭ 58
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Grasp
Awesome Ml Model Compression
Awesome machine learning model compression research papers, tools, and learning material.
Stars: ✭ 166 (+186.21%)
Mutual labels: neural-networks, pruning
Meme Generator
MemeGen is a web application where the user gives an image as input and our tool generates a meme at one click for the user.
Stars: ✭ 57 (-1.72%)
Mutual labels: neural-networks
Tensorflow Seq2seq Dialogs
Build conversation Seq2Seq models with TensorFlow
Stars: ✭ 43 (-25.86%)
Mutual labels: neural-networks
Deepbrain
Deep Learning tools for brain medical images
Stars: ✭ 51 (-12.07%)
Mutual labels: neural-networks
Ml In Tf
Get started with Machine Learning in TensorFlow with a selection of good reads and implemented examples!
Stars: ✭ 45 (-22.41%)
Mutual labels: neural-networks
Tensoranfis
A Tensorflow implementation of the Adaptive Neuro-Based Fuzzy Inference System (ANFIS)
Stars: ✭ 53 (-8.62%)
Mutual labels: neural-networks
Machine Learning From Scratch
Succinct Machine Learning algorithm implementations from scratch in Python, solving real-world problems (Notebooks and Book). Examples of Logistic Regression, Linear Regression, Decision Trees, K-means clustering, Sentiment Analysis, Recommender Systems, Neural Networks and Reinforcement Learning.
Stars: ✭ 42 (-27.59%)
Mutual labels: neural-networks
Applying eanns
A 2D Unity simulation in which cars learn to navigate themselves through different courses. The cars are steered by a feedforward neural network. The weights of the network are trained using a modified genetic algorithm.
Stars: ✭ 1,093 (+1784.48%)
Mutual labels: neural-networks
Genann
simple neural network library in ANSI C
Stars: ✭ 1,088 (+1775.86%)
Mutual labels: neural-networks
Mckinsey Smartcities Traffic Prediction
Adventure into using multi attention recurrent neural networks for time-series (city traffic) for the 2017-11-18 McKinsey IronMan (24h non-stop) prediction challenge
Stars: ✭ 49 (-15.52%)
Mutual labels: neural-networks
Delve
PyTorch and Keras model training and layer saturation monitor
Stars: ✭ 49 (-15.52%)
Mutual labels: pruning
Mujocounity
Reproducing MuJoCo benchmarks in a modern, commercial game /physics engine (Unity + PhysX).
Stars: ✭ 47 (-18.97%)
Mutual labels: neural-networks
Awesome Pruning
A curated list of neural network pruning resources.
Stars: ✭ 1,017 (+1653.45%)
Mutual labels: pruning
Convisualize nb
Visualisations for Convolutional Neural Networks in Pytorch
Stars: ✭ 57 (-1.72%)
Mutual labels: neural-networks
Advis.js
[Tensorflow.js] AdVis: Exploring real-time Adversarial Attacks in the browser with Fast Gradient Sign Method.
Stars: ✭ 42 (-27.59%)
Mutual labels: neural-networks
Pytorch highway networks
Highway networks implemented in PyTorch.
Stars: ✭ 51 (-12.07%)
Mutual labels: neural-networks
Lstm Context Embeddings
Augmenting word embeddings with their surrounding context using bidirectional RNN
Stars: ✭ 57 (-1.72%)
Mutual labels: neural-networks
Picking Winning Tickets Before Training by Preserving Gradient Flow
This repo contains the official implementations of Picking Winning Tickets Before Training by Preserving Gradient Flow.
- The config file for the experiments are under the directory of
configs/
.
Requirements
python3.6
pip install https://download.pytorch.org/whl/cu90/torch-0.4.1-cp36-cp36m-linux_x86_64.whl
pip install torchvision
pip install tqdm
pip install tensorflow
pip install tensorboardX
pip install easydict
Dataset
-
Download tiny imagenet from "https://tiny-imagenet.herokuapp.com", and place it in ../data/tiny_imagenet. Please make sure there will be two folders,
train
andval
, under the directory of../data/tiny_imagenet
. In eithertrain
orval
, there will be 200 folders storing the images of each category. Or You can also download the processed data from here. -
For cifar datasets, it will be automatically downloaded.
How to run?
# CIFAR-100, VGG19, Pruning ratio = 98%
$ python main_prune_non_imagenet.py --config configs/cifar100/vgg19/GraSP_98.json
# CIFAR-10, VGG19, Pruning ratio = 98%
$ python main_prune_non_imagenet.py --config configs/cifar10/vgg19/GraSP_98.json
# For all the experiments, please refer to the folder configs.
Citation
To cite this work, please use
@inproceedings{
Wang2020Picking,
title={Picking Winning Tickets Before Training by Preserving Gradient Flow},
author={Chaoqi Wang and Guodong Zhang and Roger Grosse},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=SkgsACVKPH}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].