A CNN‑based model to predict Covid‑19
Implemented my own CNN model that is able to classify a given lung x‑ray image as ”normal” or ”pneumonia” or ”covid” with an accuracy of 87% • To improve the accuracy, implemented transfer learning by using the pre‑trained VGG16 model • By optimizing the parameters such as learning rate, batch size and by using the EarlyStopping callback technique I was able to improve the accuracy to 90.3% • Technical Skills: Python, Pandas, NumPy, Matplotlib, sklearn, Tensorflow, keras. • Soft Skills: Presentation Skills, Report Writing.
Notebook Link => https://colab.research.google.com/drive/1ET_EJRVHewjcTN3OT7xhiegKU7M6kw6C?usp=sharing