This week was all about model building and model validation. Initially, I was stuck a bit on the metric portion, but was later able to overcome it by using special keras libraries. The labyrinthine keras and tensorflow documentation proved to be invaluable.
The dataset has labelled-images, unlabelled-images, labelled videos and segmented images. For the classification process I am going to use the labelled-images. They have 22 classes labelled in them.
I am training two model, out of which one model will be a custom model and other one will be pre-trained one which is adapted to Kvasir Dataset. A size of 224x224 will be used as the input shape for the model. For data logging purpose i have used tensorboard.
Both the models were trained. The pre-trained model provides low generalisation error in-comparison to the Custom-Model.
CustomModel: loss: 2.4398 - accuracy: 0.7283 - f1_m: 1.1505 - precision_m: 142484.9571 - recall_m: 1.1362 - val_loss: 3.0672 - val_accuracy: 0.0990 - val_f1_m: 0.9958 - val_precision_m: 0.9958 - val_recall_m: 0.9958
PreTrained Model: loss: 0.9046 - acc: 0.7174 - f1_m: 0.2450 - precision_m: 301254.4277 - recall_m: 0.2275 - val_loss: 1.0795 - val_acc: 0.6811 - val_f1_m: 0.2366 - val_precision_m: 248592.8750 - val_recall_m: 0.2270
For handling virtual reality portion of the project I am going to use WebXR. This doe not require installation of application on the phone. It supports various platforms like oculus and android
That's all for today. Meet y'all later
Tl;dr: Model dev cycle complete