Building a model to automatically classify among rock, paper, and scissor images based on the label and features of the existing images
The result shows that the model has an accuracy rate of 0.95 and loss rate 0.15. It has a very good performance for predicting the images
I used Neural Network. The Image Augmentation process was also carried out before the model training stage
OVERVIEW
This is my personal project provided by Dicoding to build a model that can automatically classify among rock, paper, and scissor images based on the label and features of the existing images. The dataset has 2,188 total images divided into 3 classes (rock, paper, scissors). The proportion of train set and validation set is 60:40.
For the initial stage, I cropped the images so that the prediction results were more accurate and faster. Then, I did an image Augmentation which divided the image into training, test, and validation subdirectories.
I used the Neuron Network algorithm with Convolution and Max Pooling architecture for model training with a total of 3,584,707 parameters used. I divided the dataset into two parts, the training set and the validation set with a proportion of 60:40.
Based on the results of model training, the accuracy rate obtained was 0.95 with a loss rate of 0.15. It has a very good performance for predicting the images
