This repository is about an end to end implemetation of deep learning cotton plant disease classification web application using flask.

The dataset is downloaded from Kaggle.

• total size - 152 MB.
• train - 1951 images
• validation - 253 images
• test - 160 images

• diseased cotton plant (Fusarium Wilt)
• diseased cotton leaf (Leaf Curl Disease)
• fresh cotton plant (Healthy Plant)
• fresh cotton leaf (Healthy Leaf).

Image resolution - 694x694 pixels
Image format - JPG format

Pretrained DenseNet121 model on ImageNet dataset is used. With the help of transfer learning, the last 8 layers of the model are tuned to solve the problem. The model is trained for 20 epoches and the accuracy is 97% on test data.

pip install -r requirements.txt

For model implementation and training, run

densenet121cottondisease.ipynb

Download model weight - DenseNet121.h5 and store inside /model folder.

For running Flask app,run:

python app.py

To build docker image, run:

docker build -t cotton .

To run docker image, run:

docker run --name cotton-app cotton

To stop docker:

docker stop cotton-app

• Sakshi (@GitHub Sakshi053)
• Prachi Gupta (@GitHub Prachigupta0305)