Skip to content

Latest commit

 

History

History
23 lines (17 loc) · 954 Bytes

README.md

File metadata and controls

23 lines (17 loc) · 954 Bytes
Raw

Finger-Recognition

Finger Recognition Using CNN in TFLearn

TFlearn is a modular and transparent deep learning library built on top of Tensorflow. It was designed to provide a higher-level API to TensorFlow in order to facilitate and speed-up experimentations, while remaining fully transparent and compatible with it.

link: http://tflearn.org/

I have used TFLearn to create CNN and openCV to collect and store data, and to process data.

  • record.py uses openCV to record and store data in folders.
    • Press 1,2,3,4 or 5 to change the finger image that is being stored.
    • press 'space' to store the image.
    • press 'esc' to quit.
  • Use train.py to train the CNN. It automatically saves the weights when it finishes training.
  • Use run_cnn.py to run the finger detection. It automatically loads the saved weights.

元リポジトリのをpython3.7に対応させました。