return model
text_class_model = build_model(113)
earlyStopping = keras.callbacks.EarlyStopping(monitor='loss',
patience=10,
verbose=1,
mode='auto')
text_class_model.fit(train_data,
train_labels,
epochs=50,
batch_size=5,
callbacks=[earlyStopping])
ml_utils.save_model(text_class_model, 'text_class_model.h5')
test_predicted_res = text_class_model.predict(test_data, batch_size=1)
print(
'\n****************Classification result for text classification************************'
)
ml_utils.display_result(
test_labels_raw, test_predicted_res.argmax(axis=1),
'text classification') # Print the classification result
# for result in test_predicted_res:
# ml_utils.display_confidence(result)
import ml_utils
from numpy import genfromtxt
"""
This File is used to generate the final confusion matrix.
Please add the bottom_color,left_color,right_color,Predicted_boxNumber,Actual_boxNumber values in 'result_confusion_matrix'
file and then run the below code.
"""
if __name__ == "__main__":
csv_path = "./resources/result_confusion_matrix.csv"
dt = genfromtxt(csv_path, delimiter=',', skip_header=1)
actual_labels = dt[:, -1]
predicted_labels = dt[:, -2]
ml_utils.display_result(actual_labels, predicted_labels,
'Real Time Prediction')
callbacks=[earlyStopping])
elapsed_time = time.time() - start_time
print('Deep Learning Training time: {}'.format(elapsed_time))
ml_utils.save_model(model_container, 'model_container.h5')
test_predicted_container_res = model_container.predict(test_container_data,
batch_size=1)
test_predicted_rack_res = model_rack.predict(test_rack_data,
batch_size=1).argmax(axis=-1)
# print('Color Space: {}'.format(color_space))
print(
'\n****************Classification result for rack************************'
)
ml_utils.display_result(test_rack_labels_raw, test_predicted_rack_res,
'rack') # Print the classification result
print(
'\n****************Classification result for container************************'
)
ml_utils.display_result(test_container_labels_raw,
test_predicted_container_res.argmax(axis=1),
'container') # Print the classification result
# for result in test_predicted_container_res:
# ml_utils.display_confidence(result)
if not ml_utils.load_configurations_from_files(
): # If parameters are loaded from file then we can not get history.
ml_plots_utils.plot_history(history_rack, 'rack')
ml_plots_utils.plot_history(history_container, 'container')
# iterate over classifiers
for name, clf in zip(names, classifiers):
clf.fit(train_left_data, train_left_labels_raw)
# score = clf.score(test_container_data, test_container_labels_raw)
start_time = time.time()
clf.fit(train_left_data, train_left_labels_raw)
elapsed_time = time.time() - start_time
training_time[name] = elapsed_time
start_time = time.time()
test_predicted_left_res = clf.predict(test_left_data)
elapsed_time = time.time() - start_time
prediction_time[name] = elapsed_time
precision, recall, f1score, accuracy = ml_utils.display_result(
test_left_labels_raw, test_predicted_left_res, name)
precisions[name] = precision * 100
recalls[name] = recall * 100
f1scores[name] = f1score * 100
accuracy_scores[name] = accuracy * 100
# ------------------------------------------- Deep learning --------------------------------------------------
model_left = dl_clf.build_model(7, 6)
start_time = time.time()
history_left = model_left.fit(train_left_data,
train_left_labels,
epochs=10,
validation_data=(test_left_data,
test_left_labels),
batch_size=500,
verbose=2)
ml_utils.save_model(model_bottom, 'model_bottom.h5',
config_save_load_dir_path)
ml_utils.save_model(model_left, 'model_left.h5', config_save_load_dir_path)
ml_utils.save_model(model_right, 'model_right.h5',
config_save_load_dir_path)
test_predicted_bottom_res = model_bottom.predict(test_bottom_data,
batch_size=1)
print(
'\n****************Classification result for Bottom************************'
)
ml_utils.display_result(test_bottom_labels_raw,
test_predicted_bottom_res.argmax(axis=1),
'Bottom') # Print the classification result
# for result in test_predicted_bottom_res:
# ml_utils.display_confidence(result)
test_predicted_left_res = model_left.predict(test_left_data, batch_size=1)
print(
'\n****************Classification result for Left************************')
ml_utils.display_result(test_left_labels_raw,
test_predicted_left_res.argmax(axis=1),
'Left') # Print the classification result
# for result in test_predicted_left_res:
# ml_utils.display_confidence(result)
test_predicted_right_res = model_right.predict(test_right_data, batch_size=1)