Skip to content

Files

model

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
Jun 19, 2020
Jul 12, 2020
Jun 19, 2020
Jun 19, 2020
Jul 12, 2020
Jul 12, 2020
Jun 21, 2020
Jun 22, 2020
Jun 20, 2020
Jun 19, 2020
Jul 12, 2020
Jun 19, 2020

Final Project - Bangkit JKT-1A

This directory host the Tensorflow model of Ocular Disease Intelligent Recognition (ODIR) Classification using Tensorflow as a Final Project of Google Bangkit Machine Learning Academy by team JKT1-A

For complete project files including model files are available at Our cloud storage.

File Owner

  1. ODIR_5K.ipynb > Azhari
  2. Multi_Label_Image_Classification_ODIR.ipynb.ipynb > Irfani
  3. Ocular_Model_[version].ipnyb > Bima
  4. ODIR_dadang.ipynb > Dadang

Explanation

Ocular Model Version 1 (Bima)

I used images that have explicit one label on it.

Train and Validation Data:

I splitted the data into train and validation data by 80% train and 20% validation

  1. train_data = 4662 images belonging to 8 classes.
  2. validation_data = 1166 images belonging to 8 classes

Training parameter:

  1. learning_rate = 0.001
  2. optimizer = Adam
  3. epoch = 30
  4. Training time is +- 4 hours

Neural Network Configuration

model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(150, 150, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(8, activation='softmax')
])

Result:

model loss auc accuracy val_loss val_auc val_accuracy
bima_model_V1 0.0497 0.9994 0.9869 4.1342 0.8076 0.5206
<irfani_model> 0.0 0.0 0.0 0.0 0.0 0.0
<azhari_model> 0.0 0.0 0.0 0.0 0.0 0.0

Graphic Result

Accuracy Vs Epochs [BIMA] (hover to see title text): alt text

Loss Vs Epochs [BIMA] (hover to see title text): alt text