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 → rohanchopra → cifar10

rohanchopra / cifar10

Licence: MIT License
Predict CIFAR-10 labels with 88% accuracy using keras.

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

tensorflowkerasjupyter-notebookcifar10cifar-10

Projects that are alternatives of or similar to cifar10

DenseNet-Cifar10
Train DenseNet on Cifar-10 based on Keras
Stars: ✭ 39 (+21.88%)
Mutual labels:  cifar10, cifar-10
srVAE
VAE with RealNVP prior and Super-Resolution VAE in PyTorch. Code release for https://arxiv.org/abs/2006.05218.
Stars: ✭ 56 (+75%)
Mutual labels:  cifar10, cifar-10
pcdarts-tf2
PC-DARTS (PC-DARTS: Partial Channel Connections for Memory-Efficient Differentiable Architecture Search, published in ICLR 2020) implemented in Tensorflow 2.0+. This is an unofficial implementation.
Stars: ✭ 25 (-21.87%)
Mutual labels:  cifar10, cifar-10
numpy-cnn
A numpy based CNN implementation for classifying images
Stars: ✭ 47 (+46.88%)
Mutual labels:  cifar10, cifar-10
gans-2.0
Generative Adversarial Networks in TensorFlow 2.0
Stars: ✭ 76 (+137.5%)
Mutual labels:  cifar10, cifar-10
BottleneckTransformers
Bottleneck Transformers for Visual Recognition
Stars: ✭ 231 (+621.88%)
Mutual labels:  cifar10
deeplearning-mpo
Replace FC2, LeNet-5, VGG, Resnet, Densenet's full-connected layers with MPO
Stars: ✭ 26 (-18.75%)
Mutual labels:  cifar10
DCGAN-CIFAR10
A implementation of DCGAN (Deep Convolutional Generative Adversarial Networks) for CIFAR10 image
Stars: ✭ 18 (-43.75%)
Mutual labels:  cifar10
ReZero-ResNet
Unofficial pytorch implementation of ReZero in ResNet
Stars: ✭ 23 (-28.12%)
Mutual labels:  cifar10
ocsvm-anomaly-detection
anomaly detection by one-class SVM
Stars: ✭ 66 (+106.25%)
Mutual labels:  cifar10
Classification Nets
Implement popular models by different DL framework. Such as tensorflow and caffe
Stars: ✭ 17 (-46.87%)
Mutual labels:  cifar10
NIPS-Global-Paper-Implementation-Challenge
Selective Classification For Deep Neural Networks.
Stars: ✭ 11 (-65.62%)
Mutual labels:  cifar-10
Pruning filters for efficient convnets
PyTorch implementation of "Pruning Filters For Efficient ConvNets"
Stars: ✭ 96 (+200%)
Mutual labels:  cifar10
AlexNet
AlexNet model from ILSVRC 2012
Stars: ✭ 35 (+9.38%)
Mutual labels:  cifar-10
cifar-tensorflow
No description or website provided.
Stars: ✭ 18 (-43.75%)
Mutual labels:  cifar-10
PFL-Non-IID
The origin of the Non-IID phenomenon is the personalization of users, who generate the Non-IID data. With Non-IID (Not Independent and Identically Distributed) issues existing in the federated learning setting, a myriad of approaches has been proposed to crack this hard nut. In contrast, the personalized federated learning may take the advantage…
Stars: ✭ 58 (+81.25%)
Mutual labels:  cifar10
resnet-cifar10
ResNet for Cifar10
Stars: ✭ 21 (-34.37%)
Mutual labels:  cifar10
image-defect-detection-based-on-CNN
TensorBasicModel
Stars: ✭ 17 (-46.87%)
Mutual labels:  cifar10
Federated-Learning-Mini-Framework
Federated Learning mini-framework with Keras
Stars: ✭ 38 (+18.75%)
Mutual labels:  cifar10
Keras-CIFAR10
practice on CIFAR10 with Keras
Stars: ✭ 25 (-21.87%)
Mutual labels:  cifar10
View All Similar Projects ➔

CIFAR-10 using CNNs

This project aims to predict the labels of the CIFAR-10 datset. This project uses Keras to implement deep learning. Almost all the code is in the form of IPython notebooks. Final accuracy - 87.94%

Mis-classifications

Mis-classified outputs

Metric graphs

Metrics

Dependencies

  • Jupyter
  • Keras
  • Tensorflow
  • Matplotlib
  • Pickle

Contents

  1. Helper - Helper functions which decode and fetch the data to the IPython notebooks
  2. Basic - IPython notebook to test helper functions and list images in the dataset
  3. Simple CNN - IPython notebook with a simple implementation of CNN taken from the Keras examples
  4. Improved CNN - IPython notebook which uses a pure CNN network with image augmentations to implove the accuracy of the model
  5. Model files (.h5) - Different saved models

Getting started

The quickest way to run these on a fresh Linux machine is to follow this tutorial: Kerai-Labs

Then clone this repo and start Jupyter Notebook:

git clone https://github.com/09rohanchopra/cifar10.git
cd cifar10
jupyter notebook

Tutorial

Kerai-Labs

Feedback

If you have ideas or find mistakes please leave a note.

License

MIT

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].