Medical Diagnosis in Chest X-ray images.
-
Updated
Jul 26, 2023 - Jupyter Notebook
Medical Diagnosis in Chest X-ray images.
An Image-Classifier made using pre-trained network/model 'densenet121' having an accuracy of 98%.
Medical Images processing
Employing Error Level Analysis (ELA) and Edge Detection techniques, this project aims to identify potential image forgery by analyzing discrepancies in error levels and abrupt intensity changes within images.
Optimization of CheXNet in PyTorch with Intel OpenVINO
Followed a paper published on NIH. Replicated the same process and got similar results.
🚀DenseNet Model by Pytorch
An Image Classification project w/ MobileNetV2 and DenseNet-121. Leveraging techniques like Hyperparameter Tuning, Transfer Learning, Imagine Preprocessing Techniques and Ensemble Methods.
Hello visitor,
Using Densenet121 & Adam Optimizer on a Jupyter Notebook
Led a facial emotion classification project with CNNs, comparing 'AlexNet' and 'DenseNet-121' through hyperparameter tuning. 'DenseNet-121' emerged as optimal for large datasets, while 'AlexNet' excelled in resource-constrained settings, highlighting potential applications in real-time emotion detection.
Various codes and scripts used during AI research. Orginally developed in the Binary_label_predictions_with_CNNs repository
cifar 10 dataset and minist dataset
The main concentration of this project lies on image calssification using traditional CNN(Convolution Neural Networks), and also a couple of "BASE MODELS" such as "RestNet50", "DenseNet121" and "EfficientNetB0" that upgraded the performance of our CNN, followed by the Fully Connected NN, that we are using to train our model on.
The code in this repository was a part of a Bachelor thesis project at KTH.
Custom DenseNet for deepfake detection
Various codes and scripts used during AI research, all neatly organised
Add a description, image, and links to the densenet121 topic page so that developers can more easily learn about it.
To associate your repository with the densenet121 topic, visit your repo's landing page and select "manage topics."