Waste-Image-Classification-Using-CNN

Problem statement:

Implement an algorithm to classify whether the image is recycle or organic type.

Dataset:

The total number of images available for training the model is 22,564 and 2513 images for testing.
_• Dataset Link: https://www.kaggle.com/techsash/waste-classification-data

Dependencies:

• Keras
• Tensorflow - 2.2.0
• Python - 3.6
• Scikit-Learn
• Pandas
• Numpy
• Matplotlib
• Seaborn

Data Augmentation

Using some Data Augmentation techniques for more data and Better results.

• Random zoom
• Horizontal flips
• Vertical flips
• Rotation

Network Parameter:

• Rectifier Linear Unit (ReLU) - Hidden Layers
• Sigmoid - Output Layer
• RMSprop optimizer
• Loss: Binary CrossEntropy