All Projects → 4uiiurz1 → pytorch-ricap

4uiiurz1 / pytorch-ricap

Licence: MIT License
PyTorch implementation of RICAP (Random Image Cropping And Patching)

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to pytorch-ricap

Pba
Efficient Learning of Augmentation Policy Schedules
Stars: ✭ 461 (+1052.5%)
Mutual labels:  image-classification, data-augmentation
Wb color augmenter
WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].
Stars: ✭ 89 (+122.5%)
Mutual labels:  image-classification, data-augmentation
Random Erasing
Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST
Stars: ✭ 511 (+1177.5%)
Mutual labels:  image-classification, data-augmentation
bird species classification
Supervised Classification of bird species 🐦 in high resolution images, especially for, Himalayan birds, having diverse species with fairly low amount of labelled data
Stars: ✭ 59 (+47.5%)
Mutual labels:  image-classification, data-augmentation
Paddleclas
A treasure chest for image classification powered by PaddlePaddle
Stars: ✭ 625 (+1462.5%)
Mutual labels:  image-classification, data-augmentation
general backbone
No description or website provided.
Stars: ✭ 37 (-7.5%)
Mutual labels:  image-classification, data-augmentation
Personalised-aesthetic-assessment-using-residual-adapters
Jupyter notebooks used as supporting material for an msc thesis about personalised aesthetic assessment using residual adapters.
Stars: ✭ 19 (-52.5%)
Mutual labels:  image-classification
ML2017FALL
Machine Learning (EE 5184) in NTU
Stars: ✭ 66 (+65%)
Mutual labels:  image-classification
image classifier
Image classifier in Elixir
Stars: ✭ 12 (-70%)
Mutual labels:  image-classification
SketchRecognition
Model and Android app for sketch recognition using Google's quickdraw dataset
Stars: ✭ 28 (-30%)
Mutual labels:  image-classification
thermography
Automatic detection of defected solar panel modules
Stars: ✭ 59 (+47.5%)
Mutual labels:  image-classification
EmotionalConversionStarGAN
This repository contains code to replicate results from the ICASSP 2020 paper "StarGAN for Emotional Speech Conversion: Validated by Data Augmentation of End-to-End Emotion Recognition".
Stars: ✭ 92 (+130%)
Mutual labels:  data-augmentation
car-crash-accident
Car Crash Accident Project
Stars: ✭ 14 (-65%)
Mutual labels:  image-classification
HugsVision
HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
Stars: ✭ 154 (+285%)
Mutual labels:  image-classification
sparsify
Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint
Stars: ✭ 138 (+245%)
Mutual labels:  image-classification
TensorPy
Easy Image Classification with TensorFlow
Stars: ✭ 44 (+10%)
Mutual labels:  image-classification
CrowdLayer
A neural network layer that enables training of deep neural networks directly from crowdsourced labels (e.g. from Amazon Mechanical Turk) or, more generally, labels from multiple annotators with different biases and levels of expertise.
Stars: ✭ 45 (+12.5%)
Mutual labels:  image-classification
work with stagesepx
about how to use stagesepx in production
Stars: ✭ 41 (+2.5%)
Mutual labels:  image-classification
DeepSentiPers
Repository for the experiments described in the paper named "DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus"
Stars: ✭ 17 (-57.5%)
Mutual labels:  data-augmentation
convolutedPredictions Cdiscount
2nd place solution to Kaggle's Cdiscount image classification challange.
Stars: ✭ 17 (-57.5%)
Mutual labels:  image-classification

A PyTorch implementation of RICAP

This repository contains code for a data augmentation method RICAP (Random Image Cropping And Patching) based on Data Augmentation using Random Image Cropping and Patching for Deep CNNs implemented in PyTorch.

example

Requirements

  • Python 3.6
  • PyTorch 0.4 or 1.0

Training

CIFAR-10

WideResNet28-10 baseline on CIFAR-10:

python train.py --dataset cifar10

WideResNet28-10 +RICAP on CIFAR-10:

python train.py --dataset cifar10 --ricap True

WideResNet28-10 +Random Erasing on CIFAR-10:

python train.py --dataset cifar10 --random-erase True

WideResNet28-10 +Mixup on CIFAR-10:

python train.py --dataset cifar10 --mixup True

Results

Model Error rate Loss Error rate (paper)
WideResNet28-10 baseline 3.82 0.158 3.89
WideResNet28-10 +RICAP 2.82 0.141 2.85
WideResNet28-10 +Random Erasing 3.18 0.114 4.65
WideResNet28-10 +Mixup 3.02 0.158 3.02

Learning curves of loss and accuracy.

loss

acc

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].