A Tomato leaf disease detection model using CNN and Keras
The dataset used for this project is taken from Kaggle. It contains 10 classes of tomato leaf diseases. The dataset is divided into 3 folders: train, test and valid. Each folder contains 10 subfolders, each corresponding to a class of tomatoes. The dataset contains 18,440 images in total. The dataset is divided into 3 folders: train, test and valid. Each folder contains 10 subfolders, each corresponding to a class of tomatoes. The dataset contains 18,440 images in total. The dataset is divided into 3 folders: train, test and valid. Each folder contains 10 subfolders, each corresponding to a class of tomatoes. The dataset contains 18,440 images in total. The dataset is divided into 3 folders: train, test and valid. Each folder contains 10 subfolders, each corresponding to a class of tomatoes. The dataset contains 18,440 images in total. The dataset is divided into 3 folders: train, test and valid. Each folder contains 10 subfolders, each corresponding to a class of tomatoes. The dataset contains 18,440 images in total.
The model is a simple CNN model with 3 convolutional layers and 2 fully connected layers. The model is trained for 50 epochs with a batch size of 32. The model is trained on a GPU with 8GB of VRAM.