Generalizing-Lottery-Tickets
This repository contains code to replicate the experiments given in NeurIPS 2019 paper "One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers" (by varungohil)
ImageNetV2
A new test set for ImageNet (by modestyachts)
Generalizing-Lottery-Tickets | ImageNetV2 | |
---|---|---|
1 | 1 | |
50 | 225 | |
- | 0.9% | |
0.0 | 2.1 | |
almost 2 years ago | about 1 year ago | |
Jupyter Notebook | Jupyter Notebook | |
MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Generalizing-Lottery-Tickets
Posts with mentions or reviews of Generalizing-Lottery-Tickets.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-03-29.
-
Avoid vver fitting in iterative pruning [D]
Code for https://arxiv.org/abs/1906.02773 found: https://github.com/varungohil/Generalizing-Lottery-Tickets
ImageNetV2
Posts with mentions or reviews of ImageNetV2.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Assignment 2 Part C.3 - Which Dataset?
Part C.3 seems to expect us the use the ImageNet dataset, but ImageNet is not publicly available anymore - it can only be downloaded from here: http://image-net.org/download-images, and you need to sign up for it. What dataset are we expected to use for the question then - would using ImageNetV2 (https://github.com/modestyachts/ImageNetV2) be fine? Would it be okay to split this up into a train set and test set (with the test set having a length of 128 as requested in the question), and use the test set for evaluation and the train set for retraining our modified AlexNet model?
What are some alternatives?
When comparing Generalizing-Lottery-Tickets and ImageNetV2 you can also consider the following projects:
Lottery-Ticket-Hypothesis-for-DNNs - This repo aims to provide an easy-to-use interface for searching the lottery ticket of a DNN structure.
GRAN - Efficient Graph Generation with Graph Recurrent Attention Networks, Deep Generative Model of Graphs, Graph Neural Networks, NeurIPS 2019
distiller - Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
deconstructing-lottery-tickets