https://github.com/databaseplaymaker/classification-of-rock-paper-scissors-images-with-convolutional-neural-network-cnn-using-tensorflow

Final Project to fulfill the Machine Learning for Beginners competency certification
https://github.com/databaseplaymaker/classification-of-rock-paper-scissors-images-with-convolutional-neural-network-cnn-using-tensorflow

classification cnn-keras dataset image-classification machine-learning rock-paper-scissors tensorflow-tutorials

Last synced: 1 day ago
JSON representation

Final Project to fulfill the Machine Learning for Beginners competency certification

• Host: GitHub
• URL: https://github.com/databaseplaymaker/classification-of-rock-paper-scissors-images-with-convolutional-neural-network-cnn-using-tensorflow
• Owner: DatabasePlaymaker
• Created: 2024-03-21T12:21:21.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-03-21T12:28:17.000Z (8 months ago)
• Last Synced: 2024-10-10T08:40:51.258Z (26 days ago)
• Topics: classification, cnn-keras, dataset, image-classification, machine-learning, rock-paper-scissors, tensorflow-tutorials
• Language: Jupyter Notebook
• Homepage:
• Size: 108 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Classification-of-Rock-Paper-Scissors-Images-with-Convolutional-Neural-Network-CNN-using-TensorFlow

Final Project to fulfill the Machine Learning for Beginners competency certification

- The dataset used must be the following dataset: rockpaperscissors, or use this link in the wget command: https://github.com/dicodingacademy/assets/releases/download/release/rockpaperscissors.zip.

- The dataset must be divided into train set and validation set.

- The size of the validation set must be 40% of the total dataset (training data has 1314 samples, and validation data has 874 samples).

- Must implement image augmentation.

- Using an image data generator.

- The model must use a sequential model.

- The training model does not exceed 30 minutes.

- The program was carried out at Google Colaboratory.

- The accuracy of the model is at least 85%.

- Can predict images uploaded to Colab