flower-classification-using-tensorflow

Tech used: Machine Learning,Python,TensorFlow,Keras,Matplotlib,PIL (Python Imaging Library),Gradio,Convolutional Neural Network (CNN) •Developed a Convolutional Neural Network based flower classification model using TensorFlow, achieving an accuracy of 85.46%. •Implemented dropout regularization with a rate of 0.2 to prevent overfitting by randomly dropping 20% of neurons during training. •Created a user-friendly interface using Gradio to allow users to interactively classify flower images using the trained model. Users can upload images or use their webcam for real-time classification.