CNN based model which can detect melanoma.
This project is to create a CNNbased model to detect Melanoma. Melanoma is a type of cancer that can be deadly if not detected early. It accounts for 75% of skin cancer deaths. A solution which can evaluate images and alert the dermatologists about the presence of melanoma has the potential to reduce a lot of manual effort needed in diagnosis.
Dataset contains a total of ~2.2k images belonging to 9 classes.
Dataset is loaded as a Tensorflow Batch Dataset. The image_batch
is a tensor of the shape (32, 180, 180, 3)
. This is a batch of 32 images of shape 180x180x3
(the last dimension refers to color channels RGB). The label_batch
is a tensor of the shape (32,)
, these are corresponding labels to the 32 images.
- Create a Basic CNN model, with two sets of convolution layers followed by 2 dense layers, ending with a softmax layer with 9 outcomes.
- Adding droput layers
- testing the change in accuracy with adding more layers and increasing the filter size.
- Agumenting image data to deal with class imbalance
- Python 3.10.9
- Jupyterlab 3.6.3
- numpy 1.23.5
- pandas 1.5.3
- matplotlib 3.7.0
- tensorflow 2.10.0
Created by Pawan Mani Teja Kuppili