https://github.com/muhammedbuyukkinaci/tensorflow-multiclass-image-classification-using-cnn-s

Balanced Multiclass Image Classification with TensorFlow on Python.
https://github.com/muhammedbuyukkinaci/tensorflow-multiclass-image-classification-using-cnn-s

gpu gpu-options image-classification image-processing image-recognition low-level low-level-programming multiclass-classification multiclass-image-classification python tensorflow tensorflow-api tensorflow-experiments tensorflow-gpu tensorflow-models tensorflow-tutorials

Last synced: 3 days ago
JSON representation

Balanced Multiclass Image Classification with TensorFlow on Python.

• Host: GitHub
• URL: https://github.com/muhammedbuyukkinaci/tensorflow-multiclass-image-classification-using-cnn-s
• Owner: MuhammedBuyukkinaci
• Created: 2018-03-24T06:49:39.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2022-11-19T15:56:11.000Z (almost 2 years ago)
• Last Synced: 2024-11-12T17:03:00.284Z (3 days ago)
• Topics: gpu, gpu-options, image-classification, image-processing, image-recognition, low-level, low-level-programming, multiclass-classification, multiclass-image-classification, python, tensorflow, tensorflow-api, tensorflow-experiments, tensorflow-gpu, tensorflow-models, tensorflow-tutorials
• Language: Python
• Homepage:
• Size: 144 MB
• Stars: 68
• Watchers: 8
• Forks: 38
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# TensorFlow-Multiclass-Image-Classification-using-CNN-s

This is a multiclass image classification project using Convolutional Neural Networks and PyTorch. If you want to have Tensorflow 1.0 version, take a look at **tensorflow1.0** branch.

It is a ready-to-run code.

## Folder Tree

![folder_tree](folder_tree.png)

## Installing Dependencies & Running

```run.sh

python3 -m venv venv

source venv/bin/activate

pip install -r requirements.txt

python main.py

```

## Data

No MNIST or CIFAR-10. 

This is a repository containing datasets of 5200 training images of 4 classes and 1267 testing images.No problematic image.

Just extract files from multiclass_datasets.rar.

train_data_bi.npy is containing 5200 training photos with labels.

test_data_bi.npy is containing 1267 testing photos with labels.

Classes are chair & kitchen & knife & saucepan. Classes are equal(1300 glass - 1300 kitchen - 1300 knife- 1300 saucepan) on training data. 

Download pure data from [here](https://www.kaggle.com/mbkinaci/chair-kitchen-knife-saucepan). Warning 962 MB.

## Architecture

AlexNet is used as architecture. 5 convolution layers and 3 Fully Connected Layers with 0.5 Dropout Ratio. 60 million Parameters.

![alt text](https://github.com/MuhammedBuyukkinaci/TensorFlow-Image-Classification-Convolutional-Neural-Networks/blob/master/alexnet_architecture.png) 

## Results

Accuracy score reached 87% on CV after just 5 epochs.

![alt text](https://github.com/MuhammedBuyukkinaci/TensorFlow-Multiclass-Image-Classification-using-CNN-s/blob/master/mc_results.png)

![folder_tree](mc_results.png)

## Predictions

Predictions for first 64 testing images are below. Titles are  the predictions of our Model.

![folder_tree](mc_preds.png)