model = CNN()
history = model.fit(xTrainData, yTrainData,
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))
batch_size=batch_size,
target_size=shape,
class_mode='categorical',
color_mode='grayscale')
valid_gen = data_gen.flow_from_directory(path_valid,
batch_size=batch_size,
target_size=shape,
class_mode='categorical',
color_mode='grayscale')
history = []
try:
history = model.fit_generator(train_gen, steps_epoch, epochs,
valid_gen, valid_steps)
print("Saving weights")
model.save_weights(obj_weight)
print("Saving history")
pickle.dump(history.history, open(obj_history, 'wb'))
except KeyboardInterrupt:
print("\n\n --- Interruption ---\n ---Saving weights---")
model.save_weights(obj_weight)
print(" ---Saving history---")
pickle.dump(history.history, open(obj_history, 'wb'))
sys.exit(0)
