A Convolutional Neural Network based image classification model to disease in tomato plant leaves.
- Model is developed over AlexNet architecture. Refer: ImageNet classification with deep convolutional neural networks | Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1 (acm.org)
- This model is trained on tomato disease images taken from PlantVillage dataset.
- plant_disease.ipynb contains the code to develop and train the model.
- model folder contains the saved model.
- Install git, anaconda or miniconda.
- Run
git clone https://github.com/sudoshivam/plant-disease-DL.gitin cmd or terminal to clone the project or you can simply download the folder and unzip it. - create an anaconda environment with python3.6. Refer this link for tutorial.
- Activate conda anvironment and run the commands given in dependencies.txt file to install required libraries.
- Open new anaconda prompt in project folder and run following command
flask run - Now the app should be running in anaconda prompt. Open the given url in a web browser to use the app.
Choose an image file and click on Upload or paste link to an image in the URL box and click on Proceed.
Model will predict the disease in leaf. It also shows which disease has highest probability.
