This project implements an Image Sentiment Classifier using Convolutional Neural Networks (CNNs). The model is designed to analyze images and classify their sentiment (e.g., positive, negative, neutral). It leverages deep learning techniques to extract meaningful features and predict sentiment with high accuracy.
Dataset Preprocessing: Image augmentation, resizing, and normalization. CNN Model Architecture: Built using TensorFlow/Keras for efficient feature extraction. Model Training & Evaluation: Performance analysis using accuracy, loss, and confusion matrix. Real-time Prediction: Test the model on new images.
The dataset consists of labeled images categorized into different sentiment classes. Images are preprocessed before training.
The CNN model achieves high accuracy in classifying image sentiment. Visualizations of training loss, accuracy, and sample predictions included.