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.
- ODIR_5K.ipynb > Azhari
- Multi_Label_Image_Classification_ODIR.ipynb.ipynb > Irfani
- Ocular_Model_[version].ipnyb > Bima
- ODIR_dadang.ipynb > Dadang
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
train_data
= 4662 images belonging to 8 classes.validation_data
= 1166 images belonging to 8 classes
Training parameter:
learning_rate = 0.001
optimizer = Adam
epoch = 30
- 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