https://github.com/anyesh/ballot_paper_classification

Ballot paper classification using deep learning
https://github.com/anyesh/ballot_paper_classification

cnn deep-learning image-classification image-processing

Last synced: about 2 months ago
JSON representation

Ballot paper classification using deep learning

• Host: GitHub
• URL: https://github.com/anyesh/ballot_paper_classification
• Owner: Anyesh
• Created: 2020-05-21T07:09:14.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-05-02T08:49:15.000Z (over 2 years ago)
• Last Synced: 2023-02-27T23:56:08.410Z (almost 2 years ago)
• Topics: cnn, deep-learning, image-classification, image-processing
• Language: Python
• Homepage:
• Size: 2.01 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Ballot Paper Classification - Computer Vision Project

## Demo







## Model

The model is trained on ResNet50 architecture.

Model and encoder can be downloaded from the following link:

https://www.floydhub.com/cruzaan/datasets/ballot-model/1/

Store the `model`and `encoder` in artifacts directory.







## Prepare the data for Evaluation

Prepare your dataset to proceed with the model. Your data folder structure should be on following format:

```

│

├── data             <- Root data folder

|   |── 0             <- Sub data folder with it's associated label

|       |── img1.jpeg   <- Image file with same filename as on csv file

|   |── 1

│

```

To structure data this way, while running `evaluate.py` make sure to change `process_data` param to `True`

## Evaluate data

The `evaluate.py` function will evaluate the provided data and returns the evaluation report as an output.

```

python evaluate.py

```

# Flask App

To run the flask app, use the following command.

```

python app.py

```