mimg = MoleImages()
X_test, y_test = mimg.load_test_images('data_scaled_test/benign',
'data_scaled_test/malign')
mycnn = CNN()
train_datagen = ImageDataGenerator(
vertical_flip=True,
horizontal_flip=True)
test_datagen = ImageDataGenerator()
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(128, 128),
batch_size=batch_size,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(128, 128),
batch_size=batch_size,
class_mode='binary')
model = mycnn.fit_generator(train_generator,validation_generator,
nb_train_samples, nb_validation_samples, epochs, batch_size)
model.save('models/mymodel-3.h5')
y_pred_proba = model.predict(X_test)
y_pred = (y_pred_proba >0.5)*1
print(classification_report(y_test,y_pred))
plot_roc(y_test, y_pred_proba, title='ROC Curve CNN from scratch')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(128, 128),
batch_size=batch_size,
class_mode='binary')
best_model_VA = ModelCheckpoint('BM_VA_' + model_path,
monitor='val_acc',
mode='max',
verbose=1,
save_best_only=True)
best_model_VL = ModelCheckpoint('BM_VL_' + model_path,
monitor='val_loss',
mode='min',
verbose=1,
save_best_only=True)
model = mycnn.fit_generator(train_generator,
validation_generator,
10 * nb_train_samples,
nb_validation_samples,
epochs,
batch_size,
callbacks=[best_model_VA, best_model_VL])
model.save(model_path)
#y_pred_proba = model.predict(X_test)
#y_pred = (y_pred_proba >0.5)*1
#print(classification_report(y_test,y_pred))
#plot_roc(y_test, y_pred_proba, title='ROC Curve CNN from scratch')