Skin cancer classification using CNN with Intel oneAPI AI toolkit

Installation of Anaconda and Intel oneAPI AI toolkits

Download Anaconda to run the files in Intel optimized Python and Intel optimized Tensorflow here .

After installing Anaconda, open the CMD.exe prompt from the Anaconda and run the following commands

Install Intel optimized python in conda

conda install -c intel intelpython3_full

Create a virtual environment with Intel optimized Python

conda create -n <your_environment_name> intelpython3_full python=3.8

Activate virtual environment

conda activate <your_environment_name>

Add intel channel

conda config --add channels intel

Install Intel optimized Tensorflow

conda install intel-tensorflow

or

pip install intel-tensorflow

In case any duplicacy error occurs, use the below command to avoid it

set KMP_DUPLICATE_LIB_OK=TRUE

Installation of Python dependencies to be able to train and test the classification model

conda install matplotlib

pip install keras_preprocessing

pip install Pillow

pip install opencv-python

pip install numpy

pip install scikit-image

Usage

Get into the directory where you saved the dataset and codes

cd <cloned_Directory_name>

Run the file to train and save the model

python Train.py

Run this file to test images using the saved model

python Test.py