You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This project is our submission, for the Google Solution Challenge 2023. With this project, we hope to make an impact and contribute to the field of Good Health and Wellbeing. This project aims to make early stage cancer detection of various types (specifically Brain Tumor, Breast Cancer & Leukemia) sustainable.
Clasificación de imágenes y reconocimiento de objetos mediante la red neuronal convolucional CNN DenseNet y EfficientNet con el modelo frozen model y el framework Coffe. Posteriomente, mediante la red neuronal convolucional CNN MobileNet-SSD y YOLO con el framework TensorFlow
This project utilizes transfer learning with the EfficientNetB7 model for image classification on a challenging food dataset consisting of 101 food categories and 101,000 images
Multi-label CV classification with 87% accuracy in detecting correct catheter placement in COVID-19 patient chest x-rays under the Royal Australian and New Zealand College of Radiologists Catheter and Line Position Challenge (RANZCR-CLiP) scoring higher than 180 teams on Kaggle.
The aim is not only to make a model which can classify the chest x-ray data but also to extract the heat maps of the x-ray for faster diagnosis and making it more reliable to use in real time.