https://github.com/pacospace/predict-movies-genre-from-posters

Predict Movies genre from posters - Multi Label Image Classification
https://github.com/pacospace/predict-movies-genre-from-posters

Last synced: about 1 month ago
JSON representation

Predict Movies genre from posters - Multi Label Image Classification

• Host: GitHub
• URL: https://github.com/pacospace/predict-movies-genre-from-posters
• Owner: pacospace
• License: other
• Created: 2021-12-18T12:09:23.000Z (about 3 years ago)
• Default Branch: master
• Last Pushed: 2021-12-23T11:13:14.000Z (about 3 years ago)
• Last Synced: 2024-11-07T17:59:44.822Z (3 months ago)
• Language: Python
• Size: 93.8 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Codeowners: .github/CODEOWNERS

Awesome Lists containing this project

README

        
Predict movies genre from posters images

=========================================

Goal

----

The aim is to predict the genre of a movie using just its poster image. It is a multi-label image classification problem: A movie can belong to more than one genre. It doesn’t just have to belong to one category, like action or comedy. The movie can be a combination of two or more genres.

Dataset

-------

The dataset for Movie Genre Classification based on Poster Images with Deep Neural Networks is available [here](https://www.cs.ccu.edu.tw/~wtchu/projects/MoviePoster/index.html).

The dataset in zip files contains the poster images of several multi-genre movies. It is in a structured format, i.e. a folder containing the images and a .csv file for true labels.

Visualize

---------

In order to visualize annotation dataset and model architecture.

```

pipenv run python3 src/cli.py visualize

```

Training

-------

In order to train the model:

```

pipenv run python3 src/cli.py train

```

In order to see tensorboard results created, you have to run the following command from another terminal:

```

pipenv run tensorboard --logdir models/logs/scalars

```

Inference

-------

In order to make prediction with a model:

```

pipenv run python3 src/cli.py predict --model-name  --image-name 

```

MODEL_NAME: Name of the model to be loaded. Model needs to be available in `models/` folder.

IMAGE_NAME: Name of the image used for predictions. Image needs to be available in `data/external/` folder.