Description

The dataset I use is the 'Rock-Paper-Scissors Images' dataset from Kaggle.

First of all, i open my google colab, and download the dataset from the kaggle with the api command.

Then, I split the dataset into 2 parts, training and validation with a concentration of 80% training data and 20% validation data.

Define the train and validation data to be used in the model.

Here I try to visualize one of the data.

Next is the data preprocessing stage. I use image generator to process image data.

Then I create a model that will be used.

Compile models. Then the code below is a callback to stop the training process if it exceeds 97%.

Next run training on the model.

In the final stage, I try to make predictions from the results of the model that has been trained.