diff --git a/.idea/encodings.xml b/.idea/encodings.xml new file mode 100644 index 0000000..90d6ea8 --- /dev/null +++ b/.idea/encodings.xml @@ -0,0 +1,6 @@ + + + + + + \ No newline at end of file diff --git a/Number-Of-Pool/_mian_tensorflow_One_PoolCNN.py b/Number-Of-Pool/_mian_tensorflow_One_PoolCNN.py index b4712b1..ea27d02 100644 --- a/Number-Of-Pool/_mian_tensorflow_One_PoolCNN.py +++ b/Number-Of-Pool/_mian_tensorflow_One_PoolCNN.py @@ -35,7 +35,6 @@ def CNN_model_level_one(): tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), - tf.keras.layers.Flatten(), tf.keras.layers.Dense(5, activation='softmax'), # add dropout layer, dropout rate = 0.2 diff --git a/Number_Of_Filters/Nine/logs/20230327-195432/train/events.out.tfevents.1679918075.WEIYUQING.21276.0.v2 b/Number_Of_Filters/Nine/logs/20230327-195432/train/events.out.tfevents.1679918075.WEIYUQING.21276.0.v2 new file mode 100644 index 0000000..231f1bb Binary files /dev/null and b/Number_Of_Filters/Nine/logs/20230327-195432/train/events.out.tfevents.1679918075.WEIYUQING.21276.0.v2 differ diff --git a/Number_Of_Filters/Nine/logs/20230327-195432/validation/events.out.tfevents.1679918078.WEIYUQING.21276.1.v2 b/Number_Of_Filters/Nine/logs/20230327-195432/validation/events.out.tfevents.1679918078.WEIYUQING.21276.1.v2 new file mode 100644 index 0000000..5afc4a1 Binary files /dev/null and b/Number_Of_Filters/Nine/logs/20230327-195432/validation/events.out.tfevents.1679918078.WEIYUQING.21276.1.v2 differ diff --git a/Number_Of_Filters/Nine/model/ecg_model_nine_filters.h5 b/Number_Of_Filters/Nine/model/ecg_model_nine_filters.h5 new file mode 100644 index 0000000..90798c2 Binary files /dev/null and b/Number_Of_Filters/Nine/model/ecg_model_nine_filters.h5 differ diff --git a/Number_Of_Filters/SeventyOne/logs/20230327-204628/train/events.out.tfevents.1679921194.WEIYUQING.8076.0.v2 b/Number_Of_Filters/SeventyOne/logs/20230327-204628/train/events.out.tfevents.1679921194.WEIYUQING.8076.0.v2 new file mode 100644 index 0000000..d650ec5 Binary files /dev/null and b/Number_Of_Filters/SeventyOne/logs/20230327-204628/train/events.out.tfevents.1679921194.WEIYUQING.8076.0.v2 differ diff --git a/Number_Of_Filters/SeventyOne/logs/20230327-204628/validation/events.out.tfevents.1679921198.WEIYUQING.8076.1.v2 b/Number_Of_Filters/SeventyOne/logs/20230327-204628/validation/events.out.tfevents.1679921198.WEIYUQING.8076.1.v2 new file mode 100644 index 0000000..d3c6037 Binary files /dev/null and b/Number_Of_Filters/SeventyOne/logs/20230327-204628/validation/events.out.tfevents.1679921198.WEIYUQING.8076.1.v2 differ diff --git a/Number_Of_Filters/SeventyOne/model/ecg_model_three_filters.h5 b/Number_Of_Filters/SeventyOne/model/ecg_model_three_filters.h5 new file mode 100644 index 0000000..21de0a2 Binary files /dev/null and b/Number_Of_Filters/SeventyOne/model/ecg_model_three_filters.h5 differ diff --git a/Number_Of_Filters/SeventyOne/picture/accuracy.png b/Number_Of_Filters/SeventyOne/picture/accuracy.png new file mode 100644 index 0000000..1550b07 Binary files /dev/null and b/Number_Of_Filters/SeventyOne/picture/accuracy.png differ diff --git a/Number_Of_Filters/SeventyOne/picture/confusion_matrix.png b/Number_Of_Filters/SeventyOne/picture/confusion_matrix.png new file mode 100644 index 0000000..4bf3414 Binary files /dev/null and b/Number_Of_Filters/SeventyOne/picture/confusion_matrix.png differ diff --git a/Number_Of_Filters/SeventyOne/picture/loss.png b/Number_Of_Filters/SeventyOne/picture/loss.png new file mode 100644 index 0000000..13bc217 Binary files /dev/null and b/Number_Of_Filters/SeventyOne/picture/loss.png differ diff --git a/Number_Of_Filters/Three/logs/20230327-191247/train/events.out.tfevents.1679915572.WEIYUQING.24472.0.v2 b/Number_Of_Filters/Three/logs/20230327-191247/train/events.out.tfevents.1679915572.WEIYUQING.24472.0.v2 new file mode 100644 index 0000000..4cb9d3b Binary files /dev/null and b/Number_Of_Filters/Three/logs/20230327-191247/train/events.out.tfevents.1679915572.WEIYUQING.24472.0.v2 differ diff --git a/Number_Of_Filters/Three/logs/20230327-191247/validation/events.out.tfevents.1679915577.WEIYUQING.24472.1.v2 b/Number_Of_Filters/Three/logs/20230327-191247/validation/events.out.tfevents.1679915577.WEIYUQING.24472.1.v2 new file mode 100644 index 0000000..7c1ab1f Binary files /dev/null and b/Number_Of_Filters/Three/logs/20230327-191247/validation/events.out.tfevents.1679915577.WEIYUQING.24472.1.v2 differ diff --git a/Number_Of_Filters/Three/model/ecg_model_three_filters.h5 b/Number_Of_Filters/Three/model/ecg_model_three_filters.h5 new file mode 100644 index 0000000..06df59b Binary files /dev/null and b/Number_Of_Filters/Three/model/ecg_model_three_filters.h5 differ diff --git a/Number_Of_Filters/Three/picture/accuracy.png b/Number_Of_Filters/Three/picture/accuracy.png new file mode 100644 index 0000000..1898bb3 Binary files /dev/null and b/Number_Of_Filters/Three/picture/accuracy.png differ diff --git a/Number_Of_Filters/Three/picture/confusion_matrix.png b/Number_Of_Filters/Three/picture/confusion_matrix.png new file mode 100644 index 0000000..55569cb Binary files /dev/null and b/Number_Of_Filters/Three/picture/confusion_matrix.png differ diff --git a/Number_Of_Filters/Three/picture/loss.png b/Number_Of_Filters/Three/picture/loss.png new file mode 100644 index 0000000..1cbb93a Binary files /dev/null and b/Number_Of_Filters/Three/picture/loss.png differ diff --git a/Number_Of_Filters/TwentySeven/logs/20230327-200941/train/events.out.tfevents.1679918986.WEIYUQING.23560.0.v2 b/Number_Of_Filters/TwentySeven/logs/20230327-200941/train/events.out.tfevents.1679918986.WEIYUQING.23560.0.v2 new file mode 100644 index 0000000..6bc4815 Binary files /dev/null and b/Number_Of_Filters/TwentySeven/logs/20230327-200941/train/events.out.tfevents.1679918986.WEIYUQING.23560.0.v2 differ diff --git a/Number_Of_Filters/TwentySeven/logs/20230327-200941/validation/events.out.tfevents.1679918997.WEIYUQING.23560.1.v2 b/Number_Of_Filters/TwentySeven/logs/20230327-200941/validation/events.out.tfevents.1679918997.WEIYUQING.23560.1.v2 new file mode 100644 index 0000000..21ab21a Binary files /dev/null and b/Number_Of_Filters/TwentySeven/logs/20230327-200941/validation/events.out.tfevents.1679918997.WEIYUQING.23560.1.v2 differ diff --git a/Number_Of_Filters/TwentySeven/logs/20230327-201433/train/events.out.tfevents.1679919281.WEIYUQING.24544.0.v2 b/Number_Of_Filters/TwentySeven/logs/20230327-201433/train/events.out.tfevents.1679919281.WEIYUQING.24544.0.v2 new file mode 100644 index 0000000..2d3d577 Binary files /dev/null and b/Number_Of_Filters/TwentySeven/logs/20230327-201433/train/events.out.tfevents.1679919281.WEIYUQING.24544.0.v2 differ diff --git a/Number_Of_Filters/TwentySeven/logs/20230327-201433/validation/events.out.tfevents.1679919292.WEIYUQING.24544.1.v2 b/Number_Of_Filters/TwentySeven/logs/20230327-201433/validation/events.out.tfevents.1679919292.WEIYUQING.24544.1.v2 new file mode 100644 index 0000000..86084a1 Binary files /dev/null and b/Number_Of_Filters/TwentySeven/logs/20230327-201433/validation/events.out.tfevents.1679919292.WEIYUQING.24544.1.v2 differ diff --git a/Number_Of_Filters/TwentySeven/model/ecg_model_twentySeven_filters.h5 b/Number_Of_Filters/TwentySeven/model/ecg_model_twentySeven_filters.h5 new file mode 100644 index 0000000..c6f8f9d Binary files /dev/null and b/Number_Of_Filters/TwentySeven/model/ecg_model_twentySeven_filters.h5 differ diff --git a/Number_Of_Filters/TwentySeven/picture/accuracy.png b/Number_Of_Filters/TwentySeven/picture/accuracy.png new file mode 100644 index 0000000..3de351a Binary files /dev/null and b/Number_Of_Filters/TwentySeven/picture/accuracy.png differ diff --git a/Number_Of_Filters/TwentySeven/picture/confusion_matrix.png b/Number_Of_Filters/TwentySeven/picture/confusion_matrix.png new file mode 100644 index 0000000..9b2568a Binary files /dev/null and b/Number_Of_Filters/TwentySeven/picture/confusion_matrix.png differ diff --git a/Number_Of_Filters/TwentySeven/picture/loss.png b/Number_Of_Filters/TwentySeven/picture/loss.png new file mode 100644 index 0000000..a968019 Binary files /dev/null and b/Number_Of_Filters/TwentySeven/picture/loss.png differ diff --git a/Number_Of_Filters/_mian_tensorflow_Nine_Filters.py b/Number_Of_Filters/_mian_tensorflow_Nine_Filters.py new file mode 100644 index 0000000..6d370cb --- /dev/null +++ b/Number_Of_Filters/_mian_tensorflow_Nine_Filters.py @@ -0,0 +1,84 @@ +import datetime +import os + +import numpy as np +import pywt +import wfdb +import tensorflow as tf +from tensorflow import keras +from utils_three_of_Filters import loadData, plot_history_tf, plot_heat_map + +#from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH +#PATH of this test +Project_PATH = "../Number_Of_Filters/Nine/" +#PICTUREPATH= Project_PATH + "picture/" +log_dir = Project_PATH + "logs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S") +model_Path_one = Project_PATH + "model/ecg_model_nine_filters.h5" +#model_Path_one = Project_PATH + "ecg_model_one_layer.h5" + +RATIO = 0.3 +RANDOM_SEED = 42 +BATCH_SIZE = 128 +#迭代次数 +NUM_EPOCHS = 10 + + +def CNN_model_level_one(): + leavlOneModel = tf.keras.models.Sequential([ + + #take test for one CNN layers model + + tf.keras.layers.InputLayer(input_shape=(300,)), + tf.keras.layers.Reshape(target_shape=(300, 1)), + + tf.keras.layers.Conv1D(filters=9, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + tf.keras.layers.Conv1D(filters=9, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + tf.keras.layers.Conv1D(filters=9, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + + tf.keras.layers.Flatten(), + tf.keras.layers.Dense(5, activation='softmax'), + # add dropout layer, dropout rate = 0.2 + # tf.keras.layers.Dropout(rate=0.2), + # tf.keras.layers.Dense(5, activation='softmax') + ]) + return leavlOneModel + + +def main(): + # get traxin test + X_train, X_test, y_train, y_test = loadData(RATIO, RANDOM_SEED) + + # get model or create model + if os.path.exists(model_Path_one): + print(' get model in h5 file') + model = tf.keras.models.load_model(filepath=model_Path_one) + else: + # create new model(if model unexists) + model = CNN_model_level_one() + model.compile(optimizer='adam', + loss='sparse_categorical_crossentropy', + metrics=['accuracy']) + model.summary() + # TB make + tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, + histogram_freq=1, + ) + # Training and validation + history = model.fit(X_train, y_train, epochs=NUM_EPOCHS, + batch_size=BATCH_SIZE, + validation_data=(X_test, y_test), + callbacks=[tensorboard_callback]) + # validation_split=RATIO, + model.save(filepath=model_Path_one) + plot_history_tf(history) + + y_pred = np.argmax(model.predict(X_test), axis=-1) + plot_heat_map(y_test, y_pred) + + +if __name__ == '__main__': + os.environ["CUDA_VISIBLE_DEVICES"] = "-1" + main() diff --git a/Number_Of_Filters/_mian_tensorflow_SeventyOne_Filters.py b/Number_Of_Filters/_mian_tensorflow_SeventyOne_Filters.py new file mode 100644 index 0000000..6129310 --- /dev/null +++ b/Number_Of_Filters/_mian_tensorflow_SeventyOne_Filters.py @@ -0,0 +1,84 @@ +import datetime +import os + +import numpy as np +import pywt +import wfdb +import tensorflow as tf +from tensorflow import keras +from utils_seventyOne_of_Filters import loadData, plot_history_tf, plot_heat_map + +#from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH +#PATH of this test +Project_PATH = "../Number_Of_Filters/SeventyOne/" +#PICTUREPATH= Project_PATH + "picture/" +log_dir = Project_PATH + "logs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S") +model_Path_one = Project_PATH + "model/ecg_model_three_filters.h5" +#model_Path_one = Project_PATH + "ecg_model_one_layer.h5" + +RATIO = 0.3 +RANDOM_SEED = 42 +BATCH_SIZE = 128 +#迭代次数 +NUM_EPOCHS = 10 + + +def CNN_model_level_one(): + leavlOneModel = tf.keras.models.Sequential([ + + #take test for one CNN layers model + + tf.keras.layers.InputLayer(input_shape=(300,)), + tf.keras.layers.Reshape(target_shape=(300, 1)), + + tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + + tf.keras.layers.Flatten(), + tf.keras.layers.Dense(5, activation='softmax'), + # add dropout layer, dropout rate = 0.2 + # tf.keras.layers.Dropout(rate=0.2), + # tf.keras.layers.Dense(5, activation='softmax') + ]) + return leavlOneModel + + +def main(): + # get traxin test + X_train, X_test, y_train, y_test = loadData(RATIO, RANDOM_SEED) + + # get model or create model + if os.path.exists(model_Path_one): + print(' get model in h5 file') + model = tf.keras.models.load_model(filepath=model_Path_one) + else: + # create new model(if model unexists) + model = CNN_model_level_one() + model.compile(optimizer='adam', + loss='sparse_categorical_crossentropy', + metrics=['accuracy']) + model.summary() + # TB make + tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, + histogram_freq=1, + ) + # Training and validation + history = model.fit(X_train, y_train, epochs=NUM_EPOCHS, + batch_size=BATCH_SIZE, + validation_data=(X_test, y_test), + callbacks=[tensorboard_callback]) + # validation_split=RATIO, + model.save(filepath=model_Path_one) + plot_history_tf(history) + + y_pred = np.argmax(model.predict(X_test), axis=-1) + plot_heat_map(y_test, y_pred) + + +if __name__ == '__main__': + os.environ["CUDA_VISIBLE_DEVICES"] = "-1" + main() diff --git a/Number_Of_Filters/_mian_tensorflow_Three_Filters.py b/Number_Of_Filters/_mian_tensorflow_Three_Filters.py new file mode 100644 index 0000000..64020a3 --- /dev/null +++ b/Number_Of_Filters/_mian_tensorflow_Three_Filters.py @@ -0,0 +1,84 @@ +import datetime +import os + +import numpy as np +import pywt +import wfdb +import tensorflow as tf +from tensorflow import keras +from utils_three_of_Filters import loadData, plot_history_tf, plot_heat_map + +#from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH +#PATH of this test +Project_PATH = "../Number_Of_Filters/Three/" +#PICTUREPATH= Project_PATH + "picture/" +log_dir = Project_PATH + "logs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S") +model_Path_one = Project_PATH + "model/ecg_model_three_filters.h5" +#model_Path_one = Project_PATH + "ecg_model_one_layer.h5" + +RATIO = 0.3 +RANDOM_SEED = 42 +BATCH_SIZE = 128 +#迭代次数 +NUM_EPOCHS = 10 + + +def CNN_model_level_one(): + leavlOneModel = tf.keras.models.Sequential([ + + #take test for one CNN layers model + + tf.keras.layers.InputLayer(input_shape=(300,)), + tf.keras.layers.Reshape(target_shape=(300, 1)), + + tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + tf.keras.layers.Conv1D(filters=3, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + + tf.keras.layers.Flatten(), + tf.keras.layers.Dense(5, activation='softmax'), + # add dropout layer, dropout rate = 0.2 + # tf.keras.layers.Dropout(rate=0.2), + # tf.keras.layers.Dense(5, activation='softmax') + ]) + return leavlOneModel + + +def main(): + # get traxin test + X_train, X_test, y_train, y_test = loadData(RATIO, RANDOM_SEED) + + # get model or create model + if os.path.exists(model_Path_one): + print(' get model in h5 file') + model = tf.keras.models.load_model(filepath=model_Path_one) + else: + # create new model(if model unexists) + model = CNN_model_level_one() + model.compile(optimizer='adam', + loss='sparse_categorical_crossentropy', + metrics=['accuracy']) + model.summary() + # TB make + tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, + histogram_freq=1, + ) + # Training and validation + history = model.fit(X_train, y_train, epochs=NUM_EPOCHS, + batch_size=BATCH_SIZE, + validation_data=(X_test, y_test), + callbacks=[tensorboard_callback]) + # validation_split=RATIO, + model.save(filepath=model_Path_one) + plot_history_tf(history) + + y_pred = np.argmax(model.predict(X_test), axis=-1) + plot_heat_map(y_test, y_pred) + + +if __name__ == '__main__': + os.environ["CUDA_VISIBLE_DEVICES"] = "-1" + main() diff --git a/Number_Of_Filters/_mian_tensorflow_TwentySeven_Filters.py b/Number_Of_Filters/_mian_tensorflow_TwentySeven_Filters.py new file mode 100644 index 0000000..53ea3b7 --- /dev/null +++ b/Number_Of_Filters/_mian_tensorflow_TwentySeven_Filters.py @@ -0,0 +1,84 @@ +import datetime +import os + +import numpy as np +import pywt +import wfdb +import tensorflow as tf +from tensorflow import keras +from utils_twentyseven_of_Filters import loadData, plot_history_tf, plot_heat_map + +#from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH +#PATH of this test +Project_PATH = "../Number_Of_Filters/TwentySeven/" +#PICTUREPATH= Project_PATH + "picture/" +log_dir = Project_PATH + "logs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S") +model_Path_one = Project_PATH + "model/ecg_model_twentySeven_filters.h5" +#model_Path_one = Project_PATH + "ecg_model_one_layer.h5" + +RATIO = 0.3 +RANDOM_SEED = 42 +BATCH_SIZE = 128 +#迭代次数 +NUM_EPOCHS = 10 + + +def CNN_model_level_one(): + leavlOneModel = tf.keras.models.Sequential([ + + #take test for one CNN layers model + + tf.keras.layers.InputLayer(input_shape=(300,)), + tf.keras.layers.Reshape(target_shape=(300, 1)), + + tf.keras.layers.Conv1D(filters=27, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + tf.keras.layers.Conv1D(filters=27, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + tf.keras.layers.Conv1D(filters=27, kernel_size=3, strides=2, padding='same', activation='relu'), + tf.keras.layers.MaxPool1D(pool_size=1, strides=2, padding='same'), + + tf.keras.layers.Flatten(), + tf.keras.layers.Dense(5, activation='softmax'), + # add dropout layer, dropout rate = 0.2 + # tf.keras.layers.Dropout(rate=0.2), + # tf.keras.layers.Dense(5, activation='softmax') + ]) + return leavlOneModel + + +def main(): + # get traxin test + X_train, X_test, y_train, y_test = loadData(RATIO, RANDOM_SEED) + + # get model or create model + if os.path.exists(model_Path_one): + print(' get model in h5 file') + model = tf.keras.models.load_model(filepath=model_Path_one) + else: + # create new model(if model unexists) + model = CNN_model_level_one() + model.compile(optimizer='adam', + loss='sparse_categorical_crossentropy', + metrics=['accuracy']) + model.summary() + # TB make + tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, + histogram_freq=1, + ) + # Training and validation + history = model.fit(X_train, y_train, epochs=NUM_EPOCHS, + batch_size=BATCH_SIZE, + validation_data=(X_test, y_test), + callbacks=[tensorboard_callback]) + # validation_split=RATIO, + model.save(filepath=model_Path_one) + plot_history_tf(history) + + y_pred = np.argmax(model.predict(X_test), axis=-1) + plot_heat_map(y_test, y_pred) + + +if __name__ == '__main__': + os.environ["CUDA_VISIBLE_DEVICES"] = "-1" + main() diff --git a/Number_Of_Filters/utils_nine_of_Filters.py b/Number_Of_Filters/utils_nine_of_Filters.py new file mode 100644 index 0000000..b1bad3a --- /dev/null +++ b/Number_Of_Filters/utils_nine_of_Filters.py @@ -0,0 +1,172 @@ +# this file give +import os + +import wfdb +import pywt +import seaborn +import numpy as np +import matplotlib.pyplot as plt +from sklearn.metrics import confusion_matrix +from sklearn.model_selection import train_test_split + +# from _mian_tensorflow import Project_PATH +Project_PATH = '../Number_Of_Filters/Nine/' + +PICTUREPATH = Project_PATH + 'picture/' + +# from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH +MITBITECGDATAPATH = '../MIT-BIT/' + + +# wavelet denoise preprocess using mallat algorithm + +def denoise(date): + # Wavelet db5 level9 + coeffs = pywt.wavedec(data=date, wavelet='db5', level=9) + cA9, cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs + # noice del + threshold = (np.median(np.abs(cD1)) / 0.6745) * (np.sqrt(2 * np.log(len(cD1)))) + # take cD 1,2 turn 0 to denoise + cD1.fill(0) + cD2.fill(0) + for i in range(1, len(coeffs) - 2): + coeffs[i] = pywt.threshold(coeffs[i], threshold) + # get signal that before wavelet + rdata = pywt.waverec(coeffs=coeffs, wavelet='db5') + return rdata + + +# get ECG data,date type and denoise +# this function without return +# use append take return data to pass data +def getDataSet(number, X_data, Y_data): + ecgClassSet = ['N', 'A', 'V', 'L', 'R'] + print('get' + number + ' ECG data') + record = wfdb.rdrecord(MITBITECGDATAPATH + number, channel_names=['MLII']) + data = record.p_signal.flatten() + # use def denoise + rdata = denoise(date=data) + + # get type of ECG data + annotation = wfdb.rdann(MITBITECGDATAPATH + number, 'atr') + Rlocation = annotation.sample # annotation.sample:get R + Rclass = annotation.symbol + + # delete stable date near R + start = 10 + end = 5 + i = start + j = len(annotation.symbol) - end + + # get NAVLR type data + while i < j: + try: + lable = ecgClassSet.index(Rclass[i]) + x_train = rdata[Rlocation[i] - 99:Rlocation[i] + 201] + X_data.append(x_train) + Y_data.append(lable) + i += 1 + except ValueError: + i += 1 + return + + +# RATIO=The ratio of the training set to the test set，usually is 0.3 +def loadData(ratio, random_seed): + numberSet = ['100', '101', '103', '105', '106', '107', '108', '109', '111', '112', '113', '114', '115', + '116', '117', '119', '121', '122', '123', '124', '200', '201', '202', '203', '205', '208', + '210', '212', '213', '214', '215', '217', '219', '220', '221', '222', '223', '228', '230', + '231', '232', '233', '234'] + dataSet = [] + labelSet = [] + for n in numberSet: + getDataSet(n, dataSet, labelSet) + + # dataSet = np.array(dataSet).reshape(-1, 300) + # labelSet = np.array(labelSet).reshape(-1, 1) + + # reshape the data and split the dataset + dataSet = np.array(dataSet).reshape(-1, 300) + lableSet = np.array(labelSet).reshape(-1) + X_train, X_test, y_train, y_test = train_test_split(dataSet, lableSet, test_size=ratio, random_state=random_seed) + # print(X_train, X_test, y_train, y_test) + return X_train, X_test, y_train, y_test + + # train_ds = np.hstack((dataSet, labelSet)) + # np.random.shuffle(train_ds) + # + # X = train_ds[:, :300].reshape(-1, 300, 1) + # Y = train_ds[:, 300] + # # cut test and train data from ECG data + # shuffle_index = np.random.permutation(len(X)) + # test_length = int(RATIO * len(shuffle_index)) + # test_index = shuffle_index[:test_length] + # train_index = shuffle_index[test_index:] + # X_test, Y_test = X[test_index:], Y[test_index] + # X_train, Y_train = X[train_index], Y[train_index] + # return X_train, Y_test, X_test, Y_train + + +# confusion matrix +def plot_heat_map(y_test, y_pred): + con_mat = confusion_matrix(y_test, y_pred) + # normalize + # con_mat_norm = con_mat.astype('float') / con_mat.sum(axis=1)[:, np.newaxis] + # con_mat_norm = np.around(con_mat_norm, decimals=2) + # os.remove(PICTUREPATH+'confusion_matrix.png') + # plot + plt.figure(figsize=(8, 8)) + seaborn.heatmap(con_mat, annot=True, fmt='.20g', cmap='Blues') + plt.ylim(0, 5) + plt.xlabel('Predicted labels') + plt.ylabel('True labels') + plt.title('Confusion Matrix') + plt.savefig(PICTUREPATH + 'confusion_matrix.png') + plt.show() + + +def plot_history_tf(history): + # os.remove(PICTUREPATH+'accuracy.png') + # os.remove(PICTUREPATH+'loss.png') + + plt.figure(figsize=(8, 8)) + plt.plot(history.history['accuracy']) + plt.plot(history.history['val_accuracy']) + plt.title('Model Accuracy') + plt.ylabel('Accuracy') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'accuracy.png') + plt.show() + + plt.figure(figsize=(8, 8)) + plt.plot(history.history['loss']) + plt.plot(history.history['val_loss']) + plt.title('Model Loss') + plt.ylabel('Loss') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'loss.png') + plt.show() + + +def plot_history_torch(history): + plt.figure(figsize=(8, 8)) + plt.plot(history['train_acc']) + plt.plot(history['test_acc']) + plt.title('Model Accuracy') + plt.ylabel('Accuracy') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'accuracy.png') + plt.show() + + plt.figure(figsize=(8, 8)) + plt.plot(history['train_loss']) + plt.plot(history['test_loss']) + plt.title('Model Loss') + plt.ylabel('Loss') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'loss.png') + plt.show() diff --git a/Number_Of_Filters/utils_seventyOne_of_Filters.py b/Number_Of_Filters/utils_seventyOne_of_Filters.py new file mode 100644 index 0000000..c1d031f --- /dev/null +++ b/Number_Of_Filters/utils_seventyOne_of_Filters.py @@ -0,0 +1,172 @@ +# this file give +import os + +import wfdb +import pywt +import seaborn +import numpy as np +import matplotlib.pyplot as plt +from sklearn.metrics import confusion_matrix +from sklearn.model_selection import train_test_split + +# from _mian_tensorflow import Project_PATH +Project_PATH = '../Number_Of_Filters/SeventyOne/' + +PICTUREPATH = Project_PATH + 'picture/' + +# from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH +MITBITECGDATAPATH = '../MIT-BIT/' + + +# wavelet denoise preprocess using mallat algorithm + +def denoise(date): + # Wavelet db5 level9 + coeffs = pywt.wavedec(data=date, wavelet='db5', level=9) + cA9, cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs + # noice del + threshold = (np.median(np.abs(cD1)) / 0.6745) * (np.sqrt(2 * np.log(len(cD1)))) + # take cD 1,2 turn 0 to denoise + cD1.fill(0) + cD2.fill(0) + for i in range(1, len(coeffs) - 2): + coeffs[i] = pywt.threshold(coeffs[i], threshold) + # get signal that before wavelet + rdata = pywt.waverec(coeffs=coeffs, wavelet='db5') + return rdata + + +# get ECG data,date type and denoise +# this function without return +# use append take return data to pass data +def getDataSet(number, X_data, Y_data): + ecgClassSet = ['N', 'A', 'V', 'L', 'R'] + print('get' + number + ' ECG data') + record = wfdb.rdrecord(MITBITECGDATAPATH + number, channel_names=['MLII']) + data = record.p_signal.flatten() + # use def denoise + rdata = denoise(date=data) + + # get type of ECG data + annotation = wfdb.rdann(MITBITECGDATAPATH + number, 'atr') + Rlocation = annotation.sample # annotation.sample:get R + Rclass = annotation.symbol + + # delete stable date near R + start = 10 + end = 5 + i = start + j = len(annotation.symbol) - end + + # get NAVLR type data + while i < j: + try: + lable = ecgClassSet.index(Rclass[i]) + x_train = rdata[Rlocation[i] - 99:Rlocation[i] + 201] + X_data.append(x_train) + Y_data.append(lable) + i += 1 + except ValueError: + i += 1 + return + + +# RATIO=The ratio of the training set to the test set，usually is 0.3 +def loadData(ratio, random_seed): + numberSet = ['100', '101', '103', '105', '106', '107', '108', '109', '111', '112', '113', '114', '115', + '116', '117', '119', '121', '122', '123', '124', '200', '201', '202', '203', '205', '208', + '210', '212', '213', '214', '215', '217', '219', '220', '221', '222', '223', '228', '230', + '231', '232', '233', '234'] + dataSet = [] + labelSet = [] + for n in numberSet: + getDataSet(n, dataSet, labelSet) + + # dataSet = np.array(dataSet).reshape(-1, 300) + # labelSet = np.array(labelSet).reshape(-1, 1) + + # reshape the data and split the dataset + dataSet = np.array(dataSet).reshape(-1, 300) + lableSet = np.array(labelSet).reshape(-1) + X_train, X_test, y_train, y_test = train_test_split(dataSet, lableSet, test_size=ratio, random_state=random_seed) + # print(X_train, X_test, y_train, y_test) + return X_train, X_test, y_train, y_test + + # train_ds = np.hstack((dataSet, labelSet)) + # np.random.shuffle(train_ds) + # + # X = train_ds[:, :300].reshape(-1, 300, 1) + # Y = train_ds[:, 300] + # # cut test and train data from ECG data + # shuffle_index = np.random.permutation(len(X)) + # test_length = int(RATIO * len(shuffle_index)) + # test_index = shuffle_index[:test_length] + # train_index = shuffle_index[test_index:] + # X_test, Y_test = X[test_index:], Y[test_index] + # X_train, Y_train = X[train_index], Y[train_index] + # return X_train, Y_test, X_test, Y_train + + +# confusion matrix +def plot_heat_map(y_test, y_pred): + con_mat = confusion_matrix(y_test, y_pred) + # normalize + # con_mat_norm = con_mat.astype('float') / con_mat.sum(axis=1)[:, np.newaxis] + # con_mat_norm = np.around(con_mat_norm, decimals=2) + # os.remove(PICTUREPATH+'confusion_matrix.png') + # plot + plt.figure(figsize=(8, 8)) + seaborn.heatmap(con_mat, annot=True, fmt='.20g', cmap='Blues') + plt.ylim(0, 5) + plt.xlabel('Predicted labels') + plt.ylabel('True labels') + plt.title('Confusion Matrix') + plt.savefig(PICTUREPATH + 'confusion_matrix.png') + plt.show() + + +def plot_history_tf(history): + # os.remove(PICTUREPATH+'accuracy.png') + # os.remove(PICTUREPATH+'loss.png') + + plt.figure(figsize=(8, 8)) + plt.plot(history.history['accuracy']) + plt.plot(history.history['val_accuracy']) + plt.title('Model Accuracy') + plt.ylabel('Accuracy') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'accuracy.png') + plt.show() + + plt.figure(figsize=(8, 8)) + plt.plot(history.history['loss']) + plt.plot(history.history['val_loss']) + plt.title('Model Loss') + plt.ylabel('Loss') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'loss.png') + plt.show() + + +def plot_history_torch(history): + plt.figure(figsize=(8, 8)) + plt.plot(history['train_acc']) + plt.plot(history['test_acc']) + plt.title('Model Accuracy') + plt.ylabel('Accuracy') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'accuracy.png') + plt.show() + + plt.figure(figsize=(8, 8)) + plt.plot(history['train_loss']) + plt.plot(history['test_loss']) + plt.title('Model Loss') + plt.ylabel('Loss') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'loss.png') + plt.show() diff --git a/Number_Of_Filters/utils_three_of_Filters.py b/Number_Of_Filters/utils_three_of_Filters.py new file mode 100644 index 0000000..8188c83 --- /dev/null +++ b/Number_Of_Filters/utils_three_of_Filters.py @@ -0,0 +1,172 @@ +# this file give +import os + +import wfdb +import pywt +import seaborn +import numpy as np +import matplotlib.pyplot as plt +from sklearn.metrics import confusion_matrix +from sklearn.model_selection import train_test_split + +# from _mian_tensorflow import Project_PATH +Project_PATH = '../Number_Of_Filters/Three/' + +PICTUREPATH = Project_PATH + 'picture/' + +# from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH +MITBITECGDATAPATH = '../MIT-BIT/' + + +# wavelet denoise preprocess using mallat algorithm + +def denoise(date): + # Wavelet db5 level9 + coeffs = pywt.wavedec(data=date, wavelet='db5', level=9) + cA9, cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs + # noice del + threshold = (np.median(np.abs(cD1)) / 0.6745) * (np.sqrt(2 * np.log(len(cD1)))) + # take cD 1,2 turn 0 to denoise + cD1.fill(0) + cD2.fill(0) + for i in range(1, len(coeffs) - 2): + coeffs[i] = pywt.threshold(coeffs[i], threshold) + # get signal that before wavelet + rdata = pywt.waverec(coeffs=coeffs, wavelet='db5') + return rdata + + +# get ECG data,date type and denoise +# this function without return +# use append take return data to pass data +def getDataSet(number, X_data, Y_data): + ecgClassSet = ['N', 'A', 'V', 'L', 'R'] + print('get' + number + ' ECG data') + record = wfdb.rdrecord(MITBITECGDATAPATH + number, channel_names=['MLII']) + data = record.p_signal.flatten() + # use def denoise + rdata = denoise(date=data) + + # get type of ECG data + annotation = wfdb.rdann(MITBITECGDATAPATH + number, 'atr') + Rlocation = annotation.sample # annotation.sample:get R + Rclass = annotation.symbol + + # delete stable date near R + start = 10 + end = 5 + i = start + j = len(annotation.symbol) - end + + # get NAVLR type data + while i < j: + try: + lable = ecgClassSet.index(Rclass[i]) + x_train = rdata[Rlocation[i] - 99:Rlocation[i] + 201] + X_data.append(x_train) + Y_data.append(lable) + i += 1 + except ValueError: + i += 1 + return + + +# RATIO=The ratio of the training set to the test set，usually is 0.3 +def loadData(ratio, random_seed): + numberSet = ['100', '101', '103', '105', '106', '107', '108', '109', '111', '112', '113', '114', '115', + '116', '117', '119', '121', '122', '123', '124', '200', '201', '202', '203', '205', '208', + '210', '212', '213', '214', '215', '217', '219', '220', '221', '222', '223', '228', '230', + '231', '232', '233', '234'] + dataSet = [] + labelSet = [] + for n in numberSet: + getDataSet(n, dataSet, labelSet) + + # dataSet = np.array(dataSet).reshape(-1, 300) + # labelSet = np.array(labelSet).reshape(-1, 1) + + # reshape the data and split the dataset + dataSet = np.array(dataSet).reshape(-1, 300) + lableSet = np.array(labelSet).reshape(-1) + X_train, X_test, y_train, y_test = train_test_split(dataSet, lableSet, test_size=ratio, random_state=random_seed) + # print(X_train, X_test, y_train, y_test) + return X_train, X_test, y_train, y_test + + # train_ds = np.hstack((dataSet, labelSet)) + # np.random.shuffle(train_ds) + # + # X = train_ds[:, :300].reshape(-1, 300, 1) + # Y = train_ds[:, 300] + # # cut test and train data from ECG data + # shuffle_index = np.random.permutation(len(X)) + # test_length = int(RATIO * len(shuffle_index)) + # test_index = shuffle_index[:test_length] + # train_index = shuffle_index[test_index:] + # X_test, Y_test = X[test_index:], Y[test_index] + # X_train, Y_train = X[train_index], Y[train_index] + # return X_train, Y_test, X_test, Y_train + + +# confusion matrix +def plot_heat_map(y_test, y_pred): + con_mat = confusion_matrix(y_test, y_pred) + # normalize + # con_mat_norm = con_mat.astype('float') / con_mat.sum(axis=1)[:, np.newaxis] + # con_mat_norm = np.around(con_mat_norm, decimals=2) + # os.remove(PICTUREPATH+'confusion_matrix.png') + # plot + plt.figure(figsize=(8, 8)) + seaborn.heatmap(con_mat, annot=True, fmt='.20g', cmap='Blues') + plt.ylim(0, 5) + plt.xlabel('Predicted labels') + plt.ylabel('True labels') + plt.title('Confusion Matrix') + plt.savefig(PICTUREPATH + 'confusion_matrix.png') + plt.show() + + +def plot_history_tf(history): + # os.remove(PICTUREPATH+'accuracy.png') + # os.remove(PICTUREPATH+'loss.png') + + plt.figure(figsize=(8, 8)) + plt.plot(history.history['accuracy']) + plt.plot(history.history['val_accuracy']) + plt.title('Model Accuracy') + plt.ylabel('Accuracy') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'accuracy.png') + plt.show() + + plt.figure(figsize=(8, 8)) + plt.plot(history.history['loss']) + plt.plot(history.history['val_loss']) + plt.title('Model Loss') + plt.ylabel('Loss') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'loss.png') + plt.show() + + +def plot_history_torch(history): + plt.figure(figsize=(8, 8)) + plt.plot(history['train_acc']) + plt.plot(history['test_acc']) + plt.title('Model Accuracy') + plt.ylabel('Accuracy') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'accuracy.png') + plt.show() + + plt.figure(figsize=(8, 8)) + plt.plot(history['train_loss']) + plt.plot(history['test_loss']) + plt.title('Model Loss') + plt.ylabel('Loss') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'loss.png') + plt.show() diff --git a/Number_Of_Filters/utils_twentyseven_of_Filters.py b/Number_Of_Filters/utils_twentyseven_of_Filters.py new file mode 100644 index 0000000..2d8ab8e --- /dev/null +++ b/Number_Of_Filters/utils_twentyseven_of_Filters.py @@ -0,0 +1,172 @@ +# this file give +import os + +import wfdb +import pywt +import seaborn +import numpy as np +import matplotlib.pyplot as plt +from sklearn.metrics import confusion_matrix +from sklearn.model_selection import train_test_split + +# from _mian_tensorflow import Project_PATH +Project_PATH = '../Number_Of_Filters/TwentySeven/' + +PICTUREPATH = Project_PATH + 'picture/' + +# from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH +MITBITECGDATAPATH = '../MIT-BIT/' + + +# wavelet denoise preprocess using mallat algorithm + +def denoise(date): + # Wavelet db5 level9 + coeffs = pywt.wavedec(data=date, wavelet='db5', level=9) + cA9, cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs + # noice del + threshold = (np.median(np.abs(cD1)) / 0.6745) * (np.sqrt(2 * np.log(len(cD1)))) + # take cD 1,2 turn 0 to denoise + cD1.fill(0) + cD2.fill(0) + for i in range(1, len(coeffs) - 2): + coeffs[i] = pywt.threshold(coeffs[i], threshold) + # get signal that before wavelet + rdata = pywt.waverec(coeffs=coeffs, wavelet='db5') + return rdata + + +# get ECG data,date type and denoise +# this function without return +# use append take return data to pass data +def getDataSet(number, X_data, Y_data): + ecgClassSet = ['N', 'A', 'V', 'L', 'R'] + print('get' + number + ' ECG data') + record = wfdb.rdrecord(MITBITECGDATAPATH + number, channel_names=['MLII']) + data = record.p_signal.flatten() + # use def denoise + rdata = denoise(date=data) + + # get type of ECG data + annotation = wfdb.rdann(MITBITECGDATAPATH + number, 'atr') + Rlocation = annotation.sample # annotation.sample:get R + Rclass = annotation.symbol + + # delete stable date near R + start = 10 + end = 5 + i = start + j = len(annotation.symbol) - end + + # get NAVLR type data + while i < j: + try: + lable = ecgClassSet.index(Rclass[i]) + x_train = rdata[Rlocation[i] - 99:Rlocation[i] + 201] + X_data.append(x_train) + Y_data.append(lable) + i += 1 + except ValueError: + i += 1 + return + + +# RATIO=The ratio of the training set to the test set，usually is 0.3 +def loadData(ratio, random_seed): + numberSet = ['100', '101', '103', '105', '106', '107', '108', '109', '111', '112', '113', '114', '115', + '116', '117', '119', '121', '122', '123', '124', '200', '201', '202', '203', '205', '208', + '210', '212', '213', '214', '215', '217', '219', '220', '221', '222', '223', '228', '230', + '231', '232', '233', '234'] + dataSet = [] + labelSet = [] + for n in numberSet: + getDataSet(n, dataSet, labelSet) + + # dataSet = np.array(dataSet).reshape(-1, 300) + # labelSet = np.array(labelSet).reshape(-1, 1) + + # reshape the data and split the dataset + dataSet = np.array(dataSet).reshape(-1, 300) + lableSet = np.array(labelSet).reshape(-1) + X_train, X_test, y_train, y_test = train_test_split(dataSet, lableSet, test_size=ratio, random_state=random_seed) + # print(X_train, X_test, y_train, y_test) + return X_train, X_test, y_train, y_test + + # train_ds = np.hstack((dataSet, labelSet)) + # np.random.shuffle(train_ds) + # + # X = train_ds[:, :300].reshape(-1, 300, 1) + # Y = train_ds[:, 300] + # # cut test and train data from ECG data + # shuffle_index = np.random.permutation(len(X)) + # test_length = int(RATIO * len(shuffle_index)) + # test_index = shuffle_index[:test_length] + # train_index = shuffle_index[test_index:] + # X_test, Y_test = X[test_index:], Y[test_index] + # X_train, Y_train = X[train_index], Y[train_index] + # return X_train, Y_test, X_test, Y_train + + +# confusion matrix +def plot_heat_map(y_test, y_pred): + con_mat = confusion_matrix(y_test, y_pred) + # normalize + # con_mat_norm = con_mat.astype('float') / con_mat.sum(axis=1)[:, np.newaxis] + # con_mat_norm = np.around(con_mat_norm, decimals=2) + # os.remove(PICTUREPATH+'confusion_matrix.png') + # plot + plt.figure(figsize=(8, 8)) + seaborn.heatmap(con_mat, annot=True, fmt='.20g', cmap='Blues') + plt.ylim(0, 5) + plt.xlabel('Predicted labels') + plt.ylabel('True labels') + plt.title('Confusion Matrix') + plt.savefig(PICTUREPATH + 'confusion_matrix.png') + plt.show() + + +def plot_history_tf(history): + # os.remove(PICTUREPATH+'accuracy.png') + # os.remove(PICTUREPATH+'loss.png') + + plt.figure(figsize=(8, 8)) + plt.plot(history.history['accuracy']) + plt.plot(history.history['val_accuracy']) + plt.title('Model Accuracy') + plt.ylabel('Accuracy') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'accuracy.png') + plt.show() + + plt.figure(figsize=(8, 8)) + plt.plot(history.history['loss']) + plt.plot(history.history['val_loss']) + plt.title('Model Loss') + plt.ylabel('Loss') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'loss.png') + plt.show() + + +def plot_history_torch(history): + plt.figure(figsize=(8, 8)) + plt.plot(history['train_acc']) + plt.plot(history['test_acc']) + plt.title('Model Accuracy') + plt.ylabel('Accuracy') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'accuracy.png') + plt.show() + + plt.figure(figsize=(8, 8)) + plt.plot(history['train_loss']) + plt.plot(history['test_loss']) + plt.title('Model Loss') + plt.ylabel('Loss') + plt.xlabel('Epoch') + plt.legend(['Train', 'Test'], loc='upper left') + plt.savefig(PICTUREPATH + 'loss.png') + plt.show()