In this competition, you must create an algorithm to identify metastatic cancer in small image patches taken from larger digital pathology scans. The data for this competition is a slightly modified version of the PatchCamelyon (PCam) benchmark dataset (the original PCam dataset contains duplicate images due to its probabilistic sampling, however, the version presented on Kaggle does not contain duplicates).
This notebook is based on the fast ai 1.0 framework and all the concepts are from Jeremy Howard lessons 3 and 6.
Besides a big thank you to Jeremy, I all so want to thank the creators of the following Kernels. https://www.kaggle.com/suicaokhoailang/wip-densenet121-baseline-with-fastai
https://www.kaggle.com/qitvision/a-complete-ml-pipeline-fast-ai
https://www.kaggle.com/guntherthepenguin/fastai-v1-pretrained-resnet-with-focalloss