layers

tensorflow layers attention sequential flatten dense relu sequential-models relu-layer conv2d relu-activation maxpooling2d noisy-regularization globalmaxpooling1d

• Updated Dec 30, 2022
• Jupyter Notebook

Keras Convolutianl Networks

tensorflow ipython dropout matplotlib sequential activation flatten l2 dense conv2d batchnormalization maxpooling2d to-categorical keras-convolutianl-networks glorot-uniform

• Updated Jan 4, 2023
• Jupyter Notebook

Utilized CNN models to classify images of mountains and forests, treating mountains as the positive class and forests as the negative class. We compare the performance of a pre-trained model, a custom CNN model, and a CNN model with data augmentation.

deep-learning image-classifier data-augmentation cnn-model resnet-50 conv2d globalaveragepooling binary-crossentropy maxpooling2d

• Updated Mar 28, 2023
• Jupyter Notebook

The number of visually impaired people worldwide is estimated to be 2.2 billion, of whom at least 1 billion have a vision impairment that could have been prevented or is yet to be addressed. Early detection and diagnosis of ocular pathologies would enable forestall of visual impairment.

visualization opencv tensorflow plotly keras os seaborn dropout classification densenet matplotlib confusion-matrix retinal-images sequential-models 3d-graph retinal-diseases maxpooling2d test-train-split

• Updated Aug 14, 2024
• Jupyter Notebook

Brain Tumor Detection using EfficientNetB3-based Deep Learning model. The project leverages transfer learning on MRI brain scan images to classify and detect brain tumors with high accuracy. Includes full workflow: data preprocessing, image augmentation, model building, evaluation, and deployment.

python deep-learning tensorflow keras flatten imagedatagenerator efficientnet batchnormalization streamlit regularizers maxpooling2d

• Updated Apr 22, 2025
• Jupyter Notebook

Skin cancer can be broadly classified into two major categories: Melanoma (Malignant) and non-melanoma (Benign). Melanoma is one of the deadliest kinds of cancer. However, the detection of this cancer at an early stage can help in improving the chances of survival.

tensorflow numpy keras os pandas dropout classification matplotlib image-dataset convolutional-neural-networks flatten dense cnn-classification skin-cancer sequential-models pathlib batchnormalization maxpooling2d sample-images

• Updated Sep 2, 2024
• Jupyter Notebook

Deep learning is a subset of machine learning based on artificial neural networks with multiple layers (hence "deep") that mimic the human brain to process data.

dropout artificial-neural-networks convolutional-neural-networks transfer-learning activation hidden-layers keras-tensorflow dense efficientnetb0 maxpooling2d output-layer input-layer

• Updated Mar 21, 2026
• Jupyter Notebook

This project focuses on detecting driver behavior from images using Convolutional Neural Networks (CNNs). The dataset consists of images categorized into five classes: other_activities, safe_driving, talking_phone, texting_phone, and turning.

tensorflow numpy pandas matplotlib imagedatagenerator cnn-classification conv2d maxpooling2d

• Updated Jan 2, 2026
• Jupyter Notebook

CNN-based handwritten digit recognition ML web application built with Django and TensorFlow.

python html machine-learning django deep-learning tensorflow ml cnn mnist image-classification digit-recognition digit-recognizer sequential-models conv2d maxpooling2d

• Updated Dec 21, 2025
• Python

This project aims to create a deep learning model for classifying fashion items using the Fashion MNIST dataset. Below, you can find the steps of the project and the results obtained.

classification convolutional-neural-network cnn-keras rmsprop maxpooling2d

• Updated Jan 4, 2024
• Python

The primary objective s to develop an accurate and efficient classification model capable of identifying pneumonia cases in patients based on chest X-ray images. Pneumonia is a prevalent and potentially life-threatening respiratory infection. Early detection plays a critical role in timely intervention and effective treatment.

python tensorflow numpy keras seaborn dropout matplotlib vgg16 roc-curve flatten loadimg sequential-models regularizers maxpooling2d binary-accuracy

• Updated Jul 13, 2024
• Jupyter Notebook