for-ai / Targeted Dropout
Complementary code for the Targeted Dropout paper
Stars: ✭ 251
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Targeted Dropout
Variance Networks
Variance Networks: When Expectation Does Not Meet Your Expectations, ICLR 2019
Stars: ✭ 38 (-84.86%)
Mutual labels: dropout
Lstms.pth
PyTorch implementations of LSTM Variants (Dropout + Layer Norm)
Stars: ✭ 111 (-55.78%)
Mutual labels: dropout
dropclass speaker
DropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020
Stars: ✭ 20 (-92.03%)
Mutual labels: dropout
Dropblock
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
Stars: ✭ 466 (+85.66%)
Mutual labels: dropout
Cplxmodule
Complex-valued neural networks for pytorch and Variational Dropout for real and complex layers.
Stars: ✭ 51 (-79.68%)
Mutual labels: dropout
NIPS-Global-Paper-Implementation-Challenge
Selective Classification For Deep Neural Networks.
Stars: ✭ 11 (-95.62%)
Mutual labels: dropout
Tensorflow Mnist Cnn
MNIST classification using Convolutional NeuralNetwork. Various techniques such as data augmentation, dropout, batchnormalization, etc are implemented.
Stars: ✭ 182 (-27.49%)
Mutual labels: dropout
Satania.moe
Satania IS the BEST waifu, no really, she is, if you don't believe me, this website will convince you
Stars: ✭ 486 (+93.63%)
Mutual labels: dropout
Sdr Densenet Pytorch
Stochastic Delta Rule implemented in Pytorch on DenseNet
Stars: ✭ 102 (-59.36%)
Mutual labels: dropout
Deepnet
Implementation of CNNs, RNNs, and many deep learning techniques in plain Numpy.
Stars: ✭ 285 (+13.55%)
Mutual labels: dropout
Tensorflow Tutorial
Tensorflow tutorial from basic to hard, 莫烦Python 中文AI教学
Stars: ✭ 4,122 (+1542.23%)
Mutual labels: dropout
Deep Learning 101
The tools and syntax you need to code neural networks from day one.
Stars: ✭ 59 (-76.49%)
Mutual labels: dropout
CS231n
My solutions for Assignments of CS231n: Convolutional Neural Networks for Visual Recognition
Stars: ✭ 30 (-88.05%)
Mutual labels: dropout
Daguan 2019 rank9
datagrand 2019 information extraction competition rank9
Stars: ✭ 121 (-51.79%)
Mutual labels: dropout
Machine-Learning-in-Python-Workshop
My workshop on machine learning using python language to implement different algorithms
Stars: ✭ 89 (-64.54%)
Mutual labels: dropout
Svhn Cnn
Google Street View House Number(SVHN) Dataset, and classifying them through CNN
Stars: ✭ 44 (-82.47%)
Mutual labels: dropout
Densenet Sdr
repo that holds code for improving on dropout using Stochastic Delta Rule
Stars: ✭ 148 (-41.04%)
Mutual labels: dropout
Icellr
Single (i) Cell R package (iCellR) is an interactive R package to work with high-throughput single cell sequencing technologies (i.e scRNA-seq, scVDJ-seq, ST and CITE-seq).
Stars: ✭ 80 (-68.13%)
Mutual labels: dropout
Targeted Dropout
Aidan N. Gomez, Ivan Zhang, Kevin Swersky, Yarin Gal, and Geoffrey E. Hinton
Table of Contents
Requirements
- Python 3
- Tensorflow 1.8
Quick Start
- Train a model:
python -m TD.train --hparams=resnet_default - Prune that model:
python -m TD.scripts.prune.eval --hparams=resnet_default --prune_percent 0.0,0.25,0.5,0.75,0.95
Flags
-
--env: one oflocal,gcp(GPU instances), ortpu(TPU instances). Feel free to add more if necessary. -
--hparams: the hparam set you want to run. -
--hparam_override: manually specify hparams to be overridden (e.g--hparam_override 'drop_rate=0.66')
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].