batch_size = 16,
epochs = 20,
validation_split= 0.25,
verbose = 2,
)
# model_test
testEvaluate = model.evaluate(xTestData, yTestData, verbose=0)
print("loss: " + str(testEvaluate[0]) + "\t accuracy: " + str(testEvaluate[1]))
#%% Save weights
model.save("my_h5_model.h5")
model.save_weights("covid19_weights.h5")
#%% Load weights
model.load_weights("my_h5_model.h5")
#%% Plotting
print(history.history.keys())
#Accuracy and Loss
accuracy = history.history['accuracy']
val_accuracy = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(len(accuracy))
plt.plot(epochs, accuracy, 'b', label='Training accuracy', color="green")
plt.plot(epochs, val_accuracy, 'b', label='Validation accuracy', color="blue")
plt.title('Training and validation accuracy')
from keras.preprocessing.image import ImageDataGenerator
if __name__ == "__main__":
path_test = "./test/"
obj_weight = "model_w.h5"
shape = (128, 512)
shape_t = (128, 512, 1)
model = CNN(shape_t)
if not os.path.exists(obj_weight):
raise ValueError("Can't find model weights")
model.load_weights(obj_weight)
data_gen = ImageDataGenerator()
batch_size = 2
test_gen = data_gen.flow_from_directory(path_test,
batch_size=batch_size,
target_size=shape,
class_mode='categorical',
color_mode='grayscale')
results = model.evaluate_generator(test_gen)
print("Results:: \n\n", results)
# loss, roc_auc, accuracy
