CNN-Image-Classifier-Project

Convolutional Neural Network (CNN) project to identify the class of input image. In this project the input images are divided into one of two classes which are Dogs and Cats, and the model is trained and tested over 300 unique images.

The link to the dataset used: https://www.kaggle.com/datasets/samuelcortinhas/cats-and-dogs-image-classification/data

The dataset is divided into two folders, one for each class. The dataset is further divided into training and testing data. The training data is used to train the model and the testing data is used to test the model.

The model is trained using the training data and then tested using the testing data. The model is trained using a Convolutional Neural Network (CNN) and the accuracy of the model is calculated using the testing data.

The model is trained using the following layers:

1. Convolutional Layer
2. Max Pooling Layer
3. Flatten Layer
4. Dense Layer
5. Output Layer

The model is trained using the following parameters:

1. Loss Function: Binary Cross Entropy
2. Optimizer: Adam
3. Metrics: Accuracy

The model is trained using the following hyperparameters:

1. Epochs: 25
2. Batch Size: 32

The model is trained using the following image preprocessing techniques:

1. Image Data Generator
2. Flow From Directory
3. Image Resizing
4. Image Normalization

The model is trained using the following steps:

1. Data Preprocessing
2. Data Augmentation
3. Model Building
4. Model Compilation
5. Model Training
6. Model Evaluation
7. Model Visualization

The model is trained using the following results:

1. Training Accuracy: 0.9933
2. Testing Accuracy: 0.9667
3. Training Loss: 0.0273
4. Testing Loss: 0.1063

The model is trained using the following conclusions:

1. The model is trained using a Convolutional Neural Network (CNN).
2. The model is trained using the training data and then tested using the testing data.
3. The model is trained using a Binary Cross Entropy loss function, Adam optimizer, and Accuracy metrics.
4. The model is trained using 25 epochs and a batch size of 32.
5. The model is trained using a data augmentation and image preprocessing techniques.
6. The model is trained using a Confusion Matrix, Classification Report, Accuracy Score, and Loss Score.
7. The model is trained using a visualization techniques.

Screenshots