README.md

metadata

title: Generative Augmented Classifiers
emoji: 💻
colorFrom: gray
colorTo: indigo
sdk: gradio
sdk_version: 4.36.1
app_file: app.py
pinned: false

Generative Augmented Classifiers

Main GitHub Repo: Generative Data Augmentation | Image Classification Demo: Generative Augmented Classifiers.

This demo showcases the performance of image classifiers trained on various datasets as part of the project `Improving Fine-Grained Image Classification Using Diffusion-Based Generated Synthetic Images' dissertation.

Demo Usage Instructions

1. Select the dataset, the model architecture, training methods, type of training dataset to evaluate the classifier on.
2. Upload an image, or click Sample Random Image to select a random image from the validation dataset.
3. Click Classify to classify the image using the selected classifier.
4. To download the classifier, click Download Model: <model_name>.

The top 5 predicted labels and their corresponding probabilities are displayed.

Configuration

git clone https://huggingface.co/spaces/czl/generative-augmented-classifiers
cd generative-data-augmentation-demo
# Setup the data directory structure as shown above
conda create --name $env_name python=3.11.* # Replace $env_name with your environment name
conda activate $env_name
# Visit PyTorch website https://pytorch.org/get-started/previous-versions/#v212 for PyTorch installation instructions.
pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url # Obtain the correct URL from the PyTorch website
pip install -r requirements.txt
python app.py