GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → yasunorikudo → chainer-ResDrop

yasunorikudo / chainer-ResDrop

Licence: other
Deep Networks with Stochastic Depth implementation by Chainer

Programming Languages

python
139335 projects - #7 most used programming language

Labels

chainerresdrop

Projects that are alternatives of or similar to chainer-ResDrop

Fcn
Chainer Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)
Stars: ✭ 211 (+427.5%)
Mutual labels:  chainer
chainer2pytorch
Converts Chainer modules to PyTorch, parameters included.
Stars: ✭ 36 (-10%)
Mutual labels:  chainer
chainer-param-monitor
Monitor parameter and gradient statistics during neural network training with Chainer
Stars: ✭ 13 (-67.5%)
Mutual labels:  chainer
kawaii creator
Photo to illustration converter
Stars: ✭ 79 (+97.5%)
Mutual labels:  chainer
ChainerPruner
ChainerPruner: Channel Pruning framework for Chainer
Stars: ✭ 21 (-47.5%)
Mutual labels:  chainer
BMI219-2017-ProteinFolding
UCSF BMI219 Deep Learning (2017), Coding example (Prediction of protein folding with RNN and CNN)
Stars: ✭ 14 (-65%)
Mutual labels:  chainer
Alpha Zero General
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
Stars: ✭ 2,617 (+6442.5%)
Mutual labels:  chainer
chainer-graph-cnn
Chainer implementation of 'Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering' (https://arxiv.org/abs/1606.09375)
Stars: ✭ 67 (+67.5%)
Mutual labels:  chainer
Visual-Attention-Model
Chainer implementation of Deepmind's Visual Attention Model paper
Stars: ✭ 27 (-32.5%)
Mutual labels:  chainer
chainer-fcis
[This project has moved to ChainerCV] Chainer Implementation of Fully Convolutional Instance-aware Semantic Segmentation
Stars: ✭ 45 (+12.5%)
Mutual labels:  chainer
pyner
🌈 Implementation of Neural Network based Named Entity Recognizer (Lample+, 2016) using Chainer.
Stars: ✭ 45 (+12.5%)
Mutual labels:  chainer
3dgan-chainer
📦 A Chainer implementation of 3D Generative Adversarial Network.
Stars: ✭ 25 (-37.5%)
Mutual labels:  chainer
deep-learning-tutorial-with-chainer
Deep learning tutorial with Chainer
Stars: ✭ 25 (-37.5%)
Mutual labels:  chainer
Einops
Deep learning operations reinvented (for pytorch, tensorflow, jax and others)
Stars: ✭ 4,022 (+9955%)
Mutual labels:  chainer
rocgan
Chainer implementation of the paper Robust Conditional Generative Adversarial Networks
Stars: ✭ 15 (-62.5%)
Mutual labels:  chainer
Bert Chainer
Chainer implementation of "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding"
Stars: ✭ 205 (+412.5%)
Mutual labels:  chainer
chainer-pix2pix
Chainer implementation for Image-to-Image Translation Using Conditional Adversarial Networks
Stars: ✭ 40 (+0%)
Mutual labels:  chainer
superresolution gan
Chainer implementation of Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 50 (+25%)
Mutual labels:  chainer
chainer-sort
Simple, Online, Realtime Tracking of Multiple Objects (SORT) implementation for Chainer and ChainerCV.
Stars: ✭ 20 (-50%)
Mutual labels:  chainer
convolutional seq2seq
fairseq: Convolutional Sequence to Sequence Learning (Gehring et al. 2017) by Chainer
Stars: ✭ 63 (+57.5%)
Mutual labels:  chainer
View All Similar Projects ➔

Deep Networks with Stochastic Depth implementation by Chainer

Implementation by Chainer. Original paper is Deep Networks with Stochastic Depth.

This repository includes network definition scripts only.

If you want to train ResDrop from scratch, see chainer sample code.

Requirements

Usage

In python script, write:

from ResDrop152 import ResNet
model = ResNet()

Traning speed

About 25% faster per iteration than ResNet with no layer drop.

Sample result

I trained ResNet101 with layer drop and ResNet101 with no layer drop for PASCAL VOC Action dataset. ResNet with layer drop improved the accuracy of test results about 4%.

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].