04_kaggle_diabetes_data

[1] 데이터 로드 및 기본 정보 확인

In [ ]:

import matplotlib
import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv('./kaggle_diabetes.csv')

In [ ]:

df.head()

Out[ ]:

PregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome01234

6	148	72	35	0	33.6	0.627	50	1
1	85	66	29	0	26.6	0.351	31	0
8	183	64	0	0	23.3	0.672	32	1
1	89	66	23	94	28.1	0.167	21	0
0	137	40	35	168	43.1	2.288	33	1

In [ ]:

# 전체 Histogram

df.hist()

plt.tight_layout()
plt.show()

In [ ]:

# 개별 histogram
df['BloodPressure'].hist()

plt.tight_layout()
plt.show()

In [ ]:

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 768 entries, 0 to 767
Data columns (total 9 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   Pregnancies               768 non-null    int64  
 1   Glucose                   768 non-null    int64  
 2   BloodPressure             768 non-null    int64  
 3   SkinThickness             768 non-null    int64  
 4   Insulin                   768 non-null    int64  
 5   BMI                       768 non-null    float64
 6   DiabetesPedigreeFunction  768 non-null    float64
 7   Age                       768 non-null    int64  
 8   Outcome                   768 non-null    int64  
dtypes: float64(2), int64(7)
memory usage: 54.1 KB

In [ ]:

df.describe()

Out[ ]:

PregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcomecountmeanstdmin25%50%75%max

768.000000	768.000000	768.000000	768.000000	768.000000	768.000000	768.000000	768.000000	768.000000
3.845052	120.894531	69.105469	20.536458	79.799479	31.992578	0.471876	33.240885	0.348958
3.369578	31.972618	19.355807	15.952218	115.244002	7.884160	0.331329	11.760232	0.476951
0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.078000	21.000000	0.000000
1.000000	99.000000	62.000000	0.000000	0.000000	27.300000	0.243750	24.000000	0.000000
3.000000	117.000000	72.000000	23.000000	30.500000	32.000000	0.372500	29.000000	0.000000
6.000000	140.250000	80.000000	32.000000	127.250000	36.600000	0.626250	41.000000	1.000000
17.000000	199.000000	122.000000	99.000000	846.000000	67.100000	2.420000	81.000000	1.000000

[2] 데이터 전처리

In [ ]:

# missing value 확인

df.isnull().sum()

Out[ ]:

Pregnancies                 0
Glucose                     0
BloodPressure               0
SkinThickness               0
Insulin                     0
BMI                         0
DiabetesPedigreeFunction    0
Age                         0
Outcome                     0
dtype: int64

In [ ]:

# 데이터 0인 값 개수 확인

for col in df.columns:
    missing_rows = df.loc[df[col]==0].shape[0]
    print(col + ": " + str(missing_rows))

Pregnancies: 111
Glucose: 5
BloodPressure: 35
SkinThickness: 227
Insulin: 374
BMI: 11
DiabetesPedigreeFunction: 0
Age: 0
Outcome: 500

In [ ]:

import numpy as np

# outlier 처리

df['Glucose'] = df['Glucose'].replace(0, np.nan)
df['BloodPressure'] = df['BloodPressure'].replace(0, np.nan)
df['SkinThickness'] = df['SkinThickness'].replace(0, np.nan)
df['Insulin'] = df['Insulin'].replace(0, np.nan)
df['BMI'] = df['BMI'].replace(0, np.nan)

# missing value 처리

df['Glucose'] = df['Glucose'].fillna(df['Glucose'].mean())
df['BloodPressure'] = df['BloodPressure'].fillna(df['BloodPressure'].mean())
df['SkinThickness'] = df['SkinThickness'].fillna(df['SkinThickness'].mean())
df['Insulin'] = df['Insulin'].fillna(df['Insulin'].mean())
df['BMI'] = df['BMI'].fillna(df['BMI'].mean())

In [ ]:

for col in df.columns:
    
    missing_rows = df.loc[df[col] == 0].shape[0]
    print(col + ": " + str(missing_rows))

Pregnancies: 111
Glucose: 0
BloodPressure: 0
SkinThickness: 0
Insulin: 0
BMI: 0
DiabetesPedigreeFunction: 0
Age: 0
Outcome: 500

In [ ]:

df.columns

Out[ ]:

Index(['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin',
       'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome'],
      dtype='object')

In [ ]:

df_scaled = df.copy() # 원본 DataFrame 보존

In [ ]:

## feature column, label column 추출 후 DF 생성

feature_df = df_scaled[df_scaled.columns.difference(['Outcome'])] # outcome 제외한 df

label_df = df_scaled['Outcome']

print(feature_df.shape, label_df.shape)

(768, 8) (768,)

In [ ]:

# 스케일링

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()

df_std = scaler.fit_transform(feature_df)
print(type(df_std))

df_std = pd.DataFrame(df_std, columns = feature_df.columns)

<class 'numpy.ndarray'>

In [ ]:

# pandas <=> numpy

feature_np = df_std.to_numpy().astype('float32')
label_np = label_df.to_numpy().astype('float32')

print(feature_np.shape, label_np.shape)

(768, 8) (768,)

[3] 머신러닝/딥러닝

In [ ]:

s = np.arange(len(feature_np))

np.random.shuffle(s)

feature_np = feature_np[s]
label_np = label_np[s]

In [ ]:

split = 0.15

test_num = int(split*len(label_np))

x_test = feature_np[0:test_num]
y_test = label_np[0:test_num]

x_train = feature_np[test_num:]
y_train = label_np[test_num:]

print(x_test.shape, y_test.shape, x_train.shape, y_train.shape)

(115, 8) (115,) (653, 8) (653,)

In [ ]:

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.optimizers import SGD, Adam

model = Sequential()

model.add(Dense(4, activation = 'relu', input_shape = (8,) ))
model.add(Dense(1, activation = 'sigmoid', input_shape = (32,) ))

In [ ]:

model.compile(optimizer= SGD(learning_rate=1e-3), loss='binary_crossentropy', metrics=['accuracy'])

In [ ]:

from datetime import datetime

start_time = datetime.now()

hist = model.fit(x_train, y_train, epochs=400, validation_data=(x_test, y_test))

end_time = datetime.now()

print('\nElapsed time => ', end_time - start_time)

Epoch 1/400
21/21 [==============================] - 1s 10ms/step - loss: 0.6938 - accuracy: 0.5513 - val_loss: 0.7018 - val_accuracy: 0.5652
Epoch 2/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6906 - accuracy: 0.5528 - val_loss: 0.6991 - val_accuracy: 0.5652
Epoch 3/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6875 - accuracy: 0.5528 - val_loss: 0.6965 - val_accuracy: 0.5652
Epoch 4/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6846 - accuracy: 0.5559 - val_loss: 0.6941 - val_accuracy: 0.5739
Epoch 5/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6818 - accuracy: 0.5559 - val_loss: 0.6917 - val_accuracy: 0.5652
Epoch 6/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6791 - accuracy: 0.5605 - val_loss: 0.6893 - val_accuracy: 0.5652
Epoch 7/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6763 - accuracy: 0.5651 - val_loss: 0.6870 - val_accuracy: 0.5652
Epoch 8/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6737 - accuracy: 0.5666 - val_loss: 0.6847 - val_accuracy: 0.5652
Epoch 9/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6711 - accuracy: 0.5666 - val_loss: 0.6825 - val_accuracy: 0.5652
Epoch 10/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6685 - accuracy: 0.5697 - val_loss: 0.6804 - val_accuracy: 0.5652
Epoch 11/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6661 - accuracy: 0.5727 - val_loss: 0.6783 - val_accuracy: 0.5652
Epoch 12/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6637 - accuracy: 0.5697 - val_loss: 0.6763 - val_accuracy: 0.5652
Epoch 13/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6614 - accuracy: 0.5712 - val_loss: 0.6743 - val_accuracy: 0.5652
Epoch 14/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6590 - accuracy: 0.5712 - val_loss: 0.6723 - val_accuracy: 0.5826
Epoch 15/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6568 - accuracy: 0.5712 - val_loss: 0.6704 - val_accuracy: 0.5826
Epoch 16/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6546 - accuracy: 0.5758 - val_loss: 0.6686 - val_accuracy: 0.5826
Epoch 17/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6525 - accuracy: 0.5835 - val_loss: 0.6668 - val_accuracy: 0.5913
Epoch 18/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6504 - accuracy: 0.5835 - val_loss: 0.6651 - val_accuracy: 0.5826
Epoch 19/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6483 - accuracy: 0.5865 - val_loss: 0.6633 - val_accuracy: 0.5826
Epoch 20/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6463 - accuracy: 0.5865 - val_loss: 0.6617 - val_accuracy: 0.5913
Epoch 21/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6444 - accuracy: 0.5911 - val_loss: 0.6601 - val_accuracy: 0.6000
Epoch 22/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6425 - accuracy: 0.5957 - val_loss: 0.6585 - val_accuracy: 0.6000
Epoch 23/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6407 - accuracy: 0.5957 - val_loss: 0.6569 - val_accuracy: 0.6000
Epoch 24/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6388 - accuracy: 0.5972 - val_loss: 0.6554 - val_accuracy: 0.6000
Epoch 25/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6371 - accuracy: 0.5926 - val_loss: 0.6540 - val_accuracy: 0.6087
Epoch 26/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6353 - accuracy: 0.5911 - val_loss: 0.6525 - val_accuracy: 0.6087
Epoch 27/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6337 - accuracy: 0.5957 - val_loss: 0.6512 - val_accuracy: 0.6087
Epoch 28/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6320 - accuracy: 0.5988 - val_loss: 0.6498 - val_accuracy: 0.6087
Epoch 29/400
21/21 [==============================] - 0s 2ms/step - loss: 0.6304 - accuracy: 0.6018 - val_loss: 0.6485 - val_accuracy: 0.6087
Epoch 30/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6288 - accuracy: 0.6064 - val_loss: 0.6472 - val_accuracy: 0.6174
Epoch 31/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6272 - accuracy: 0.6064 - val_loss: 0.6459 - val_accuracy: 0.6174
Epoch 32/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6257 - accuracy: 0.6080 - val_loss: 0.6446 - val_accuracy: 0.6174
Epoch 33/400
21/21 [==============================] - 0s 2ms/step - loss: 0.6242 - accuracy: 0.6064 - val_loss: 0.6434 - val_accuracy: 0.6174
Epoch 34/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6227 - accuracy: 0.6064 - val_loss: 0.6422 - val_accuracy: 0.6261
Epoch 35/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6212 - accuracy: 0.6080 - val_loss: 0.6410 - val_accuracy: 0.6261
Epoch 36/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6198 - accuracy: 0.6110 - val_loss: 0.6398 - val_accuracy: 0.6261
Epoch 37/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6184 - accuracy: 0.6110 - val_loss: 0.6387 - val_accuracy: 0.6087
Epoch 38/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6170 - accuracy: 0.6110 - val_loss: 0.6376 - val_accuracy: 0.6087
Epoch 39/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6157 - accuracy: 0.6095 - val_loss: 0.6365 - val_accuracy: 0.6087
Epoch 40/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6144 - accuracy: 0.6110 - val_loss: 0.6354 - val_accuracy: 0.6174
Epoch 41/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6131 - accuracy: 0.6126 - val_loss: 0.6343 - val_accuracy: 0.6261
Epoch 42/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6118 - accuracy: 0.6141 - val_loss: 0.6333 - val_accuracy: 0.6261
Epoch 43/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6105 - accuracy: 0.6141 - val_loss: 0.6322 - val_accuracy: 0.6261
Epoch 44/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6093 - accuracy: 0.6141 - val_loss: 0.6312 - val_accuracy: 0.6261
Epoch 45/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6081 - accuracy: 0.6156 - val_loss: 0.6303 - val_accuracy: 0.6261
Epoch 46/400
21/21 [==============================] - 0s 4ms/step - loss: 0.6069 - accuracy: 0.6172 - val_loss: 0.6293 - val_accuracy: 0.6261
Epoch 47/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6057 - accuracy: 0.6187 - val_loss: 0.6283 - val_accuracy: 0.6174
Epoch 48/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6044 - accuracy: 0.6187 - val_loss: 0.6273 - val_accuracy: 0.6174
Epoch 49/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6033 - accuracy: 0.6172 - val_loss: 0.6264 - val_accuracy: 0.6261
Epoch 50/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6021 - accuracy: 0.6202 - val_loss: 0.6255 - val_accuracy: 0.6261
Epoch 51/400
21/21 [==============================] - 0s 3ms/step - loss: 0.6009 - accuracy: 0.6233 - val_loss: 0.6246 - val_accuracy: 0.6261
Epoch 52/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5999 - accuracy: 0.6248 - val_loss: 0.6237 - val_accuracy: 0.6261
Epoch 53/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5988 - accuracy: 0.6263 - val_loss: 0.6228 - val_accuracy: 0.6261
Epoch 54/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5977 - accuracy: 0.6263 - val_loss: 0.6219 - val_accuracy: 0.6261
Epoch 55/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5966 - accuracy: 0.6263 - val_loss: 0.6211 - val_accuracy: 0.6174
Epoch 56/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5956 - accuracy: 0.6263 - val_loss: 0.6202 - val_accuracy: 0.6174
Epoch 57/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5946 - accuracy: 0.6325 - val_loss: 0.6194 - val_accuracy: 0.6174
Epoch 58/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5936 - accuracy: 0.6325 - val_loss: 0.6186 - val_accuracy: 0.6174
Epoch 59/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5926 - accuracy: 0.6325 - val_loss: 0.6178 - val_accuracy: 0.6174
Epoch 60/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5916 - accuracy: 0.6340 - val_loss: 0.6170 - val_accuracy: 0.6174
Epoch 61/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5907 - accuracy: 0.6355 - val_loss: 0.6162 - val_accuracy: 0.6174
Epoch 62/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5897 - accuracy: 0.6371 - val_loss: 0.6154 - val_accuracy: 0.6174
Epoch 63/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5888 - accuracy: 0.6386 - val_loss: 0.6147 - val_accuracy: 0.6087
Epoch 64/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5879 - accuracy: 0.6401 - val_loss: 0.6139 - val_accuracy: 0.6087
Epoch 65/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5870 - accuracy: 0.6478 - val_loss: 0.6132 - val_accuracy: 0.6087
Epoch 66/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5861 - accuracy: 0.6493 - val_loss: 0.6125 - val_accuracy: 0.6087
Epoch 67/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5853 - accuracy: 0.6493 - val_loss: 0.6117 - val_accuracy: 0.6087
Epoch 68/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5844 - accuracy: 0.6508 - val_loss: 0.6111 - val_accuracy: 0.6087
Epoch 69/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5836 - accuracy: 0.6524 - val_loss: 0.6104 - val_accuracy: 0.6087
Epoch 70/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5827 - accuracy: 0.6570 - val_loss: 0.6097 - val_accuracy: 0.6087
Epoch 71/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5819 - accuracy: 0.6570 - val_loss: 0.6090 - val_accuracy: 0.6087
Epoch 72/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5811 - accuracy: 0.6600 - val_loss: 0.6084 - val_accuracy: 0.6087
Epoch 73/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5803 - accuracy: 0.6570 - val_loss: 0.6077 - val_accuracy: 0.6087
Epoch 74/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5796 - accuracy: 0.6600 - val_loss: 0.6070 - val_accuracy: 0.6087
Epoch 75/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5788 - accuracy: 0.6631 - val_loss: 0.6064 - val_accuracy: 0.6087
Epoch 76/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5780 - accuracy: 0.6616 - val_loss: 0.6058 - val_accuracy: 0.6087
Epoch 77/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5773 - accuracy: 0.6662 - val_loss: 0.6052 - val_accuracy: 0.6174
Epoch 78/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5765 - accuracy: 0.6662 - val_loss: 0.6045 - val_accuracy: 0.6261
Epoch 79/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5758 - accuracy: 0.6662 - val_loss: 0.6039 - val_accuracy: 0.6261
Epoch 80/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5751 - accuracy: 0.6692 - val_loss: 0.6033 - val_accuracy: 0.6261
Epoch 81/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5744 - accuracy: 0.6708 - val_loss: 0.6026 - val_accuracy: 0.6261
Epoch 82/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5737 - accuracy: 0.6738 - val_loss: 0.6021 - val_accuracy: 0.6261
Epoch 83/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5730 - accuracy: 0.6738 - val_loss: 0.6015 - val_accuracy: 0.6261
Epoch 84/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5724 - accuracy: 0.6738 - val_loss: 0.6009 - val_accuracy: 0.6261
Epoch 85/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5717 - accuracy: 0.6738 - val_loss: 0.6004 - val_accuracy: 0.6261
Epoch 86/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5711 - accuracy: 0.6738 - val_loss: 0.5998 - val_accuracy: 0.6261
Epoch 87/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5705 - accuracy: 0.6753 - val_loss: 0.5993 - val_accuracy: 0.6261
Epoch 88/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5698 - accuracy: 0.6815 - val_loss: 0.5987 - val_accuracy: 0.6261
Epoch 89/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5692 - accuracy: 0.6784 - val_loss: 0.5982 - val_accuracy: 0.6261
Epoch 90/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5686 - accuracy: 0.6799 - val_loss: 0.5977 - val_accuracy: 0.6261
Epoch 91/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5680 - accuracy: 0.6784 - val_loss: 0.5971 - val_accuracy: 0.6261
Epoch 92/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5673 - accuracy: 0.6830 - val_loss: 0.5966 - val_accuracy: 0.6261
Epoch 93/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5668 - accuracy: 0.6815 - val_loss: 0.5961 - val_accuracy: 0.6261
Epoch 94/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5662 - accuracy: 0.6830 - val_loss: 0.5956 - val_accuracy: 0.6261
Epoch 95/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5656 - accuracy: 0.6861 - val_loss: 0.5951 - val_accuracy: 0.6261
Epoch 96/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5650 - accuracy: 0.6876 - val_loss: 0.5946 - val_accuracy: 0.6261
Epoch 97/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5644 - accuracy: 0.6907 - val_loss: 0.5941 - val_accuracy: 0.6348
Epoch 98/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5639 - accuracy: 0.6922 - val_loss: 0.5936 - val_accuracy: 0.6348
Epoch 99/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5633 - accuracy: 0.6922 - val_loss: 0.5931 - val_accuracy: 0.6348
Epoch 100/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5627 - accuracy: 0.6922 - val_loss: 0.5926 - val_accuracy: 0.6348
Epoch 101/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5622 - accuracy: 0.6937 - val_loss: 0.5921 - val_accuracy: 0.6348
Epoch 102/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5616 - accuracy: 0.6937 - val_loss: 0.5917 - val_accuracy: 0.6261
Epoch 103/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5611 - accuracy: 0.6937 - val_loss: 0.5912 - val_accuracy: 0.6174
Epoch 104/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5605 - accuracy: 0.6937 - val_loss: 0.5907 - val_accuracy: 0.6174
Epoch 105/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5599 - accuracy: 0.6937 - val_loss: 0.5902 - val_accuracy: 0.6174
Epoch 106/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5594 - accuracy: 0.6953 - val_loss: 0.5897 - val_accuracy: 0.6174
Epoch 107/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5588 - accuracy: 0.6968 - val_loss: 0.5893 - val_accuracy: 0.6174
Epoch 108/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5583 - accuracy: 0.6953 - val_loss: 0.5888 - val_accuracy: 0.6174
Epoch 109/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5578 - accuracy: 0.6937 - val_loss: 0.5883 - val_accuracy: 0.6174
Epoch 110/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5572 - accuracy: 0.6937 - val_loss: 0.5879 - val_accuracy: 0.6174
Epoch 111/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5567 - accuracy: 0.6922 - val_loss: 0.5874 - val_accuracy: 0.6174
Epoch 112/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5562 - accuracy: 0.6937 - val_loss: 0.5870 - val_accuracy: 0.6174
Epoch 113/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5557 - accuracy: 0.6937 - val_loss: 0.5865 - val_accuracy: 0.6174
Epoch 114/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5552 - accuracy: 0.6953 - val_loss: 0.5861 - val_accuracy: 0.6174
Epoch 115/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5547 - accuracy: 0.6953 - val_loss: 0.5856 - val_accuracy: 0.6174
Epoch 116/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5543 - accuracy: 0.6953 - val_loss: 0.5852 - val_accuracy: 0.6174
Epoch 117/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5538 - accuracy: 0.6953 - val_loss: 0.5848 - val_accuracy: 0.6174
Epoch 118/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5533 - accuracy: 0.6953 - val_loss: 0.5844 - val_accuracy: 0.6261
Epoch 119/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5528 - accuracy: 0.6937 - val_loss: 0.5839 - val_accuracy: 0.6261
Epoch 120/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5524 - accuracy: 0.6953 - val_loss: 0.5835 - val_accuracy: 0.6261
Epoch 121/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5520 - accuracy: 0.6968 - val_loss: 0.5831 - val_accuracy: 0.6174
Epoch 122/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5515 - accuracy: 0.6983 - val_loss: 0.5827 - val_accuracy: 0.6174
Epoch 123/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5511 - accuracy: 0.6998 - val_loss: 0.5823 - val_accuracy: 0.6174
Epoch 124/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5506 - accuracy: 0.7014 - val_loss: 0.5819 - val_accuracy: 0.6174
Epoch 125/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5502 - accuracy: 0.7014 - val_loss: 0.5815 - val_accuracy: 0.6174
Epoch 126/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5498 - accuracy: 0.7029 - val_loss: 0.5811 - val_accuracy: 0.6174
Epoch 127/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5494 - accuracy: 0.7029 - val_loss: 0.5807 - val_accuracy: 0.6261
Epoch 128/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5490 - accuracy: 0.7029 - val_loss: 0.5803 - val_accuracy: 0.6261
Epoch 129/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5486 - accuracy: 0.7060 - val_loss: 0.5799 - val_accuracy: 0.6261
Epoch 130/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5482 - accuracy: 0.7060 - val_loss: 0.5795 - val_accuracy: 0.6261
Epoch 131/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5478 - accuracy: 0.7060 - val_loss: 0.5792 - val_accuracy: 0.6261
Epoch 132/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5474 - accuracy: 0.7060 - val_loss: 0.5788 - val_accuracy: 0.6261
Epoch 133/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5470 - accuracy: 0.7060 - val_loss: 0.5784 - val_accuracy: 0.6174
Epoch 134/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5467 - accuracy: 0.7060 - val_loss: 0.5781 - val_accuracy: 0.6174
Epoch 135/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5463 - accuracy: 0.7075 - val_loss: 0.5777 - val_accuracy: 0.6174
Epoch 136/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5459 - accuracy: 0.7075 - val_loss: 0.5774 - val_accuracy: 0.6174
Epoch 137/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5456 - accuracy: 0.7075 - val_loss: 0.5770 - val_accuracy: 0.6174
Epoch 138/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5452 - accuracy: 0.7075 - val_loss: 0.5767 - val_accuracy: 0.6174
Epoch 139/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5448 - accuracy: 0.7075 - val_loss: 0.5763 - val_accuracy: 0.6174
Epoch 140/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5445 - accuracy: 0.7075 - val_loss: 0.5760 - val_accuracy: 0.6174
Epoch 141/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5441 - accuracy: 0.7121 - val_loss: 0.5756 - val_accuracy: 0.6174
Epoch 142/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5438 - accuracy: 0.7106 - val_loss: 0.5753 - val_accuracy: 0.6174
Epoch 143/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5434 - accuracy: 0.7106 - val_loss: 0.5750 - val_accuracy: 0.6174
Epoch 144/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5431 - accuracy: 0.7121 - val_loss: 0.5746 - val_accuracy: 0.6174
Epoch 145/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5427 - accuracy: 0.7121 - val_loss: 0.5743 - val_accuracy: 0.6174
Epoch 146/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5424 - accuracy: 0.7121 - val_loss: 0.5740 - val_accuracy: 0.6174
Epoch 147/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5421 - accuracy: 0.7121 - val_loss: 0.5736 - val_accuracy: 0.6087
Epoch 148/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5418 - accuracy: 0.7121 - val_loss: 0.5733 - val_accuracy: 0.6087
Epoch 149/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5415 - accuracy: 0.7136 - val_loss: 0.5730 - val_accuracy: 0.6087
Epoch 150/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5411 - accuracy: 0.7152 - val_loss: 0.5727 - val_accuracy: 0.6087
Epoch 151/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5408 - accuracy: 0.7152 - val_loss: 0.5724 - val_accuracy: 0.6087
Epoch 152/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5405 - accuracy: 0.7152 - val_loss: 0.5720 - val_accuracy: 0.6087
Epoch 153/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5402 - accuracy: 0.7152 - val_loss: 0.5717 - val_accuracy: 0.6087
Epoch 154/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5399 - accuracy: 0.7136 - val_loss: 0.5714 - val_accuracy: 0.6087
Epoch 155/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5396 - accuracy: 0.7167 - val_loss: 0.5711 - val_accuracy: 0.6087
Epoch 156/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5393 - accuracy: 0.7167 - val_loss: 0.5708 - val_accuracy: 0.6087
Epoch 157/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5390 - accuracy: 0.7167 - val_loss: 0.5705 - val_accuracy: 0.6087
Epoch 158/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5386 - accuracy: 0.7182 - val_loss: 0.5702 - val_accuracy: 0.6087
Epoch 159/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5383 - accuracy: 0.7182 - val_loss: 0.5699 - val_accuracy: 0.6087
Epoch 160/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5380 - accuracy: 0.7182 - val_loss: 0.5696 - val_accuracy: 0.6087
Epoch 161/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5377 - accuracy: 0.7182 - val_loss: 0.5693 - val_accuracy: 0.6087
Epoch 162/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5374 - accuracy: 0.7198 - val_loss: 0.5690 - val_accuracy: 0.6087
Epoch 163/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5371 - accuracy: 0.7182 - val_loss: 0.5687 - val_accuracy: 0.6087
Epoch 164/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5368 - accuracy: 0.7198 - val_loss: 0.5684 - val_accuracy: 0.6087
Epoch 165/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5365 - accuracy: 0.7198 - val_loss: 0.5681 - val_accuracy: 0.6087
Epoch 166/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5362 - accuracy: 0.7198 - val_loss: 0.5678 - val_accuracy: 0.6087
Epoch 167/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5360 - accuracy: 0.7198 - val_loss: 0.5675 - val_accuracy: 0.6087
Epoch 168/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5357 - accuracy: 0.7198 - val_loss: 0.5672 - val_accuracy: 0.6087
Epoch 169/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5354 - accuracy: 0.7198 - val_loss: 0.5670 - val_accuracy: 0.6087
Epoch 170/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5351 - accuracy: 0.7198 - val_loss: 0.5667 - val_accuracy: 0.6087
Epoch 171/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5348 - accuracy: 0.7198 - val_loss: 0.5664 - val_accuracy: 0.6087
Epoch 172/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5345 - accuracy: 0.7198 - val_loss: 0.5661 - val_accuracy: 0.6087
Epoch 173/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5343 - accuracy: 0.7198 - val_loss: 0.5658 - val_accuracy: 0.6174
Epoch 174/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5340 - accuracy: 0.7228 - val_loss: 0.5656 - val_accuracy: 0.6174
Epoch 175/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5337 - accuracy: 0.7228 - val_loss: 0.5653 - val_accuracy: 0.6174
Epoch 176/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5334 - accuracy: 0.7228 - val_loss: 0.5650 - val_accuracy: 0.6174
Epoch 177/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5332 - accuracy: 0.7228 - val_loss: 0.5647 - val_accuracy: 0.6174
Epoch 178/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5329 - accuracy: 0.7243 - val_loss: 0.5644 - val_accuracy: 0.6174
Epoch 179/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5326 - accuracy: 0.7243 - val_loss: 0.5641 - val_accuracy: 0.6261
Epoch 180/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5323 - accuracy: 0.7243 - val_loss: 0.5639 - val_accuracy: 0.6261
Epoch 181/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5321 - accuracy: 0.7243 - val_loss: 0.5636 - val_accuracy: 0.6261
Epoch 182/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5318 - accuracy: 0.7259 - val_loss: 0.5633 - val_accuracy: 0.6261
Epoch 183/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5316 - accuracy: 0.7259 - val_loss: 0.5630 - val_accuracy: 0.6261
Epoch 184/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5313 - accuracy: 0.7274 - val_loss: 0.5628 - val_accuracy: 0.6261
Epoch 185/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5310 - accuracy: 0.7289 - val_loss: 0.5625 - val_accuracy: 0.6261
Epoch 186/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5308 - accuracy: 0.7289 - val_loss: 0.5622 - val_accuracy: 0.6261
Epoch 187/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5305 - accuracy: 0.7305 - val_loss: 0.5620 - val_accuracy: 0.6261
Epoch 188/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5303 - accuracy: 0.7305 - val_loss: 0.5617 - val_accuracy: 0.6261
Epoch 189/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5300 - accuracy: 0.7305 - val_loss: 0.5614 - val_accuracy: 0.6261
Epoch 190/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5298 - accuracy: 0.7305 - val_loss: 0.5612 - val_accuracy: 0.6261
Epoch 191/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5295 - accuracy: 0.7289 - val_loss: 0.5609 - val_accuracy: 0.6261
Epoch 192/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5293 - accuracy: 0.7289 - val_loss: 0.5606 - val_accuracy: 0.6348
Epoch 193/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5290 - accuracy: 0.7289 - val_loss: 0.5604 - val_accuracy: 0.6348
Epoch 194/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5288 - accuracy: 0.7305 - val_loss: 0.5601 - val_accuracy: 0.6348
Epoch 195/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5286 - accuracy: 0.7289 - val_loss: 0.5599 - val_accuracy: 0.6348
Epoch 196/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5283 - accuracy: 0.7305 - val_loss: 0.5596 - val_accuracy: 0.6348
Epoch 197/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5281 - accuracy: 0.7320 - val_loss: 0.5593 - val_accuracy: 0.6435
Epoch 198/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5278 - accuracy: 0.7320 - val_loss: 0.5591 - val_accuracy: 0.6435
Epoch 199/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5276 - accuracy: 0.7320 - val_loss: 0.5588 - val_accuracy: 0.6435
Epoch 200/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5273 - accuracy: 0.7320 - val_loss: 0.5585 - val_accuracy: 0.6435
Epoch 201/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5271 - accuracy: 0.7320 - val_loss: 0.5583 - val_accuracy: 0.6435
Epoch 202/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5269 - accuracy: 0.7320 - val_loss: 0.5580 - val_accuracy: 0.6435
Epoch 203/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5266 - accuracy: 0.7320 - val_loss: 0.5578 - val_accuracy: 0.6435
Epoch 204/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5264 - accuracy: 0.7335 - val_loss: 0.5575 - val_accuracy: 0.6435
Epoch 205/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5262 - accuracy: 0.7335 - val_loss: 0.5573 - val_accuracy: 0.6435
Epoch 206/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5260 - accuracy: 0.7335 - val_loss: 0.5570 - val_accuracy: 0.6609
Epoch 207/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5257 - accuracy: 0.7335 - val_loss: 0.5567 - val_accuracy: 0.6522
Epoch 208/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5255 - accuracy: 0.7335 - val_loss: 0.5565 - val_accuracy: 0.6522
Epoch 209/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5253 - accuracy: 0.7335 - val_loss: 0.5563 - val_accuracy: 0.6522
Epoch 210/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5251 - accuracy: 0.7335 - val_loss: 0.5560 - val_accuracy: 0.6522
Epoch 211/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5249 - accuracy: 0.7335 - val_loss: 0.5558 - val_accuracy: 0.6522
Epoch 212/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5247 - accuracy: 0.7335 - val_loss: 0.5556 - val_accuracy: 0.6522
Epoch 213/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5245 - accuracy: 0.7335 - val_loss: 0.5553 - val_accuracy: 0.6522
Epoch 214/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5242 - accuracy: 0.7335 - val_loss: 0.5551 - val_accuracy: 0.6522
Epoch 215/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5240 - accuracy: 0.7335 - val_loss: 0.5548 - val_accuracy: 0.6522
Epoch 216/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5238 - accuracy: 0.7335 - val_loss: 0.5546 - val_accuracy: 0.6522
Epoch 217/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5236 - accuracy: 0.7335 - val_loss: 0.5543 - val_accuracy: 0.6522
Epoch 218/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5234 - accuracy: 0.7351 - val_loss: 0.5541 - val_accuracy: 0.6522
Epoch 219/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5232 - accuracy: 0.7366 - val_loss: 0.5538 - val_accuracy: 0.6522
Epoch 220/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5230 - accuracy: 0.7381 - val_loss: 0.5535 - val_accuracy: 0.6522
Epoch 221/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5228 - accuracy: 0.7381 - val_loss: 0.5533 - val_accuracy: 0.6522
Epoch 222/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5226 - accuracy: 0.7381 - val_loss: 0.5531 - val_accuracy: 0.6522
Epoch 223/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5224 - accuracy: 0.7397 - val_loss: 0.5528 - val_accuracy: 0.6522
Epoch 224/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5222 - accuracy: 0.7381 - val_loss: 0.5525 - val_accuracy: 0.6522
Epoch 225/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5220 - accuracy: 0.7381 - val_loss: 0.5523 - val_accuracy: 0.6522
Epoch 226/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5218 - accuracy: 0.7381 - val_loss: 0.5520 - val_accuracy: 0.6522
Epoch 227/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5216 - accuracy: 0.7381 - val_loss: 0.5518 - val_accuracy: 0.6609
Epoch 228/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5214 - accuracy: 0.7381 - val_loss: 0.5515 - val_accuracy: 0.6609
Epoch 229/400
21/21 [==============================] - 0s 2ms/step - loss: 0.5212 - accuracy: 0.7381 - val_loss: 0.5512 - val_accuracy: 0.6609
Epoch 230/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5210 - accuracy: 0.7381 - val_loss: 0.5510 - val_accuracy: 0.6609
Epoch 231/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5208 - accuracy: 0.7381 - val_loss: 0.5507 - val_accuracy: 0.6609
Epoch 232/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5206 - accuracy: 0.7381 - val_loss: 0.5505 - val_accuracy: 0.6609
Epoch 233/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5205 - accuracy: 0.7381 - val_loss: 0.5502 - val_accuracy: 0.6609
Epoch 234/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5203 - accuracy: 0.7381 - val_loss: 0.5499 - val_accuracy: 0.6609
Epoch 235/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5201 - accuracy: 0.7381 - val_loss: 0.5497 - val_accuracy: 0.6609
Epoch 236/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5199 - accuracy: 0.7366 - val_loss: 0.5495 - val_accuracy: 0.6609
Epoch 237/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5197 - accuracy: 0.7366 - val_loss: 0.5492 - val_accuracy: 0.6609
Epoch 238/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5195 - accuracy: 0.7366 - val_loss: 0.5489 - val_accuracy: 0.6609
Epoch 239/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5193 - accuracy: 0.7366 - val_loss: 0.5487 - val_accuracy: 0.6609
Epoch 240/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5191 - accuracy: 0.7366 - val_loss: 0.5484 - val_accuracy: 0.6522
Epoch 241/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5189 - accuracy: 0.7366 - val_loss: 0.5482 - val_accuracy: 0.6522
Epoch 242/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5187 - accuracy: 0.7366 - val_loss: 0.5479 - val_accuracy: 0.6522
Epoch 243/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5185 - accuracy: 0.7366 - val_loss: 0.5477 - val_accuracy: 0.6522
Epoch 244/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5183 - accuracy: 0.7351 - val_loss: 0.5474 - val_accuracy: 0.6522
Epoch 245/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5181 - accuracy: 0.7351 - val_loss: 0.5472 - val_accuracy: 0.6609
Epoch 246/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5180 - accuracy: 0.7366 - val_loss: 0.5469 - val_accuracy: 0.6609
Epoch 247/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5178 - accuracy: 0.7381 - val_loss: 0.5467 - val_accuracy: 0.6609
Epoch 248/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5176 - accuracy: 0.7381 - val_loss: 0.5465 - val_accuracy: 0.6609
Epoch 249/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5174 - accuracy: 0.7381 - val_loss: 0.5462 - val_accuracy: 0.6609
Epoch 250/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5172 - accuracy: 0.7381 - val_loss: 0.5460 - val_accuracy: 0.6609
Epoch 251/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5171 - accuracy: 0.7366 - val_loss: 0.5457 - val_accuracy: 0.6609
Epoch 252/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5169 - accuracy: 0.7366 - val_loss: 0.5455 - val_accuracy: 0.6609
Epoch 253/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5167 - accuracy: 0.7366 - val_loss: 0.5452 - val_accuracy: 0.6609
Epoch 254/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5165 - accuracy: 0.7366 - val_loss: 0.5450 - val_accuracy: 0.6609
Epoch 255/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5163 - accuracy: 0.7366 - val_loss: 0.5448 - val_accuracy: 0.6609
Epoch 256/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5162 - accuracy: 0.7366 - val_loss: 0.5445 - val_accuracy: 0.6609
Epoch 257/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5160 - accuracy: 0.7366 - val_loss: 0.5443 - val_accuracy: 0.6609
Epoch 258/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5158 - accuracy: 0.7366 - val_loss: 0.5440 - val_accuracy: 0.6609
Epoch 259/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5156 - accuracy: 0.7366 - val_loss: 0.5438 - val_accuracy: 0.6609
Epoch 260/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5155 - accuracy: 0.7366 - val_loss: 0.5435 - val_accuracy: 0.6609
Epoch 261/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5153 - accuracy: 0.7366 - val_loss: 0.5433 - val_accuracy: 0.6609
Epoch 262/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5151 - accuracy: 0.7366 - val_loss: 0.5431 - val_accuracy: 0.6609
Epoch 263/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5149 - accuracy: 0.7366 - val_loss: 0.5428 - val_accuracy: 0.6609
Epoch 264/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5148 - accuracy: 0.7366 - val_loss: 0.5426 - val_accuracy: 0.6609
Epoch 265/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5146 - accuracy: 0.7366 - val_loss: 0.5423 - val_accuracy: 0.6609
Epoch 266/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5144 - accuracy: 0.7366 - val_loss: 0.5421 - val_accuracy: 0.6609
Epoch 267/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5143 - accuracy: 0.7366 - val_loss: 0.5419 - val_accuracy: 0.6609
Epoch 268/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5141 - accuracy: 0.7366 - val_loss: 0.5416 - val_accuracy: 0.6609
Epoch 269/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5139 - accuracy: 0.7366 - val_loss: 0.5414 - val_accuracy: 0.6609
Epoch 270/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5138 - accuracy: 0.7366 - val_loss: 0.5412 - val_accuracy: 0.6609
Epoch 271/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5136 - accuracy: 0.7381 - val_loss: 0.5409 - val_accuracy: 0.6609
Epoch 272/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5135 - accuracy: 0.7381 - val_loss: 0.5407 - val_accuracy: 0.6609
Epoch 273/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5133 - accuracy: 0.7381 - val_loss: 0.5405 - val_accuracy: 0.6609
Epoch 274/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5132 - accuracy: 0.7381 - val_loss: 0.5403 - val_accuracy: 0.6609
Epoch 275/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5130 - accuracy: 0.7381 - val_loss: 0.5400 - val_accuracy: 0.6609
Epoch 276/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5129 - accuracy: 0.7381 - val_loss: 0.5398 - val_accuracy: 0.6609
Epoch 277/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5127 - accuracy: 0.7381 - val_loss: 0.5396 - val_accuracy: 0.6609
Epoch 278/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5126 - accuracy: 0.7381 - val_loss: 0.5394 - val_accuracy: 0.6609
Epoch 279/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5124 - accuracy: 0.7381 - val_loss: 0.5392 - val_accuracy: 0.6609
Epoch 280/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5123 - accuracy: 0.7381 - val_loss: 0.5390 - val_accuracy: 0.6609
Epoch 281/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5121 - accuracy: 0.7381 - val_loss: 0.5387 - val_accuracy: 0.6609
Epoch 282/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5120 - accuracy: 0.7381 - val_loss: 0.5385 - val_accuracy: 0.6609
Epoch 283/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5118 - accuracy: 0.7397 - val_loss: 0.5383 - val_accuracy: 0.6609
Epoch 284/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5117 - accuracy: 0.7397 - val_loss: 0.5381 - val_accuracy: 0.6609
Epoch 285/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5115 - accuracy: 0.7397 - val_loss: 0.5379 - val_accuracy: 0.6609
Epoch 286/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5114 - accuracy: 0.7397 - val_loss: 0.5377 - val_accuracy: 0.6609
Epoch 287/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5112 - accuracy: 0.7397 - val_loss: 0.5374 - val_accuracy: 0.6609
Epoch 288/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5111 - accuracy: 0.7397 - val_loss: 0.5372 - val_accuracy: 0.6609
Epoch 289/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5110 - accuracy: 0.7412 - val_loss: 0.5370 - val_accuracy: 0.6609
Epoch 290/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5108 - accuracy: 0.7412 - val_loss: 0.5368 - val_accuracy: 0.6609
Epoch 291/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5107 - accuracy: 0.7412 - val_loss: 0.5366 - val_accuracy: 0.6609
Epoch 292/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5105 - accuracy: 0.7412 - val_loss: 0.5364 - val_accuracy: 0.6609
Epoch 293/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5104 - accuracy: 0.7427 - val_loss: 0.5362 - val_accuracy: 0.6609
Epoch 294/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5102 - accuracy: 0.7443 - val_loss: 0.5360 - val_accuracy: 0.6609
Epoch 295/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5101 - accuracy: 0.7443 - val_loss: 0.5358 - val_accuracy: 0.6609
Epoch 296/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5100 - accuracy: 0.7443 - val_loss: 0.5356 - val_accuracy: 0.6696
Epoch 297/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5098 - accuracy: 0.7443 - val_loss: 0.5354 - val_accuracy: 0.6696
Epoch 298/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5097 - accuracy: 0.7473 - val_loss: 0.5352 - val_accuracy: 0.6696
Epoch 299/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5096 - accuracy: 0.7473 - val_loss: 0.5350 - val_accuracy: 0.6696
Epoch 300/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5094 - accuracy: 0.7473 - val_loss: 0.5349 - val_accuracy: 0.6696
Epoch 301/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5093 - accuracy: 0.7473 - val_loss: 0.5347 - val_accuracy: 0.6696
Epoch 302/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5091 - accuracy: 0.7489 - val_loss: 0.5345 - val_accuracy: 0.6696
Epoch 303/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5090 - accuracy: 0.7504 - val_loss: 0.5343 - val_accuracy: 0.6696
Epoch 304/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5089 - accuracy: 0.7504 - val_loss: 0.5341 - val_accuracy: 0.6696
Epoch 305/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5087 - accuracy: 0.7504 - val_loss: 0.5339 - val_accuracy: 0.6696
Epoch 306/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5086 - accuracy: 0.7504 - val_loss: 0.5337 - val_accuracy: 0.6783
Epoch 307/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5084 - accuracy: 0.7504 - val_loss: 0.5335 - val_accuracy: 0.6783
Epoch 308/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5083 - accuracy: 0.7504 - val_loss: 0.5333 - val_accuracy: 0.6783
Epoch 309/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5082 - accuracy: 0.7504 - val_loss: 0.5332 - val_accuracy: 0.6783
Epoch 310/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5081 - accuracy: 0.7504 - val_loss: 0.5330 - val_accuracy: 0.6783
Epoch 311/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5079 - accuracy: 0.7504 - val_loss: 0.5328 - val_accuracy: 0.6783
Epoch 312/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5078 - accuracy: 0.7504 - val_loss: 0.5326 - val_accuracy: 0.6783
Epoch 313/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5077 - accuracy: 0.7504 - val_loss: 0.5325 - val_accuracy: 0.6783
Epoch 314/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5075 - accuracy: 0.7504 - val_loss: 0.5323 - val_accuracy: 0.6783
Epoch 315/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5074 - accuracy: 0.7504 - val_loss: 0.5321 - val_accuracy: 0.6783
Epoch 316/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5073 - accuracy: 0.7504 - val_loss: 0.5319 - val_accuracy: 0.6783
Epoch 317/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5072 - accuracy: 0.7504 - val_loss: 0.5318 - val_accuracy: 0.6783
Epoch 318/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5070 - accuracy: 0.7504 - val_loss: 0.5316 - val_accuracy: 0.6783
Epoch 319/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5069 - accuracy: 0.7504 - val_loss: 0.5314 - val_accuracy: 0.6783
Epoch 320/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5068 - accuracy: 0.7504 - val_loss: 0.5312 - val_accuracy: 0.6783
Epoch 321/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5067 - accuracy: 0.7504 - val_loss: 0.5310 - val_accuracy: 0.6783
Epoch 322/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5065 - accuracy: 0.7504 - val_loss: 0.5309 - val_accuracy: 0.6783
Epoch 323/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5064 - accuracy: 0.7504 - val_loss: 0.5307 - val_accuracy: 0.6783
Epoch 324/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5063 - accuracy: 0.7504 - val_loss: 0.5305 - val_accuracy: 0.6783
Epoch 325/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5062 - accuracy: 0.7504 - val_loss: 0.5303 - val_accuracy: 0.6783
Epoch 326/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5060 - accuracy: 0.7504 - val_loss: 0.5302 - val_accuracy: 0.6783
Epoch 327/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5059 - accuracy: 0.7504 - val_loss: 0.5300 - val_accuracy: 0.6783
Epoch 328/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5058 - accuracy: 0.7504 - val_loss: 0.5298 - val_accuracy: 0.6783
Epoch 329/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5057 - accuracy: 0.7504 - val_loss: 0.5296 - val_accuracy: 0.6783
Epoch 330/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5055 - accuracy: 0.7504 - val_loss: 0.5295 - val_accuracy: 0.6783
Epoch 331/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5054 - accuracy: 0.7504 - val_loss: 0.5293 - val_accuracy: 0.6783
Epoch 332/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5053 - accuracy: 0.7504 - val_loss: 0.5291 - val_accuracy: 0.6783
Epoch 333/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5052 - accuracy: 0.7504 - val_loss: 0.5290 - val_accuracy: 0.6783
Epoch 334/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5051 - accuracy: 0.7504 - val_loss: 0.5288 - val_accuracy: 0.6783
Epoch 335/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5050 - accuracy: 0.7504 - val_loss: 0.5286 - val_accuracy: 0.6870
Epoch 336/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5048 - accuracy: 0.7504 - val_loss: 0.5285 - val_accuracy: 0.6870
Epoch 337/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5047 - accuracy: 0.7504 - val_loss: 0.5283 - val_accuracy: 0.6870
Epoch 338/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5046 - accuracy: 0.7489 - val_loss: 0.5281 - val_accuracy: 0.6870
Epoch 339/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5045 - accuracy: 0.7504 - val_loss: 0.5280 - val_accuracy: 0.6870
Epoch 340/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5044 - accuracy: 0.7504 - val_loss: 0.5278 - val_accuracy: 0.6870
Epoch 341/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5042 - accuracy: 0.7504 - val_loss: 0.5277 - val_accuracy: 0.6870
Epoch 342/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5041 - accuracy: 0.7504 - val_loss: 0.5275 - val_accuracy: 0.6870
Epoch 343/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5040 - accuracy: 0.7519 - val_loss: 0.5273 - val_accuracy: 0.6870
Epoch 344/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5039 - accuracy: 0.7519 - val_loss: 0.5272 - val_accuracy: 0.6870
Epoch 345/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5038 - accuracy: 0.7534 - val_loss: 0.5270 - val_accuracy: 0.6870
Epoch 346/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5037 - accuracy: 0.7534 - val_loss: 0.5269 - val_accuracy: 0.6870
Epoch 347/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5035 - accuracy: 0.7534 - val_loss: 0.5267 - val_accuracy: 0.6870
Epoch 348/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5034 - accuracy: 0.7534 - val_loss: 0.5266 - val_accuracy: 0.6870
Epoch 349/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5033 - accuracy: 0.7534 - val_loss: 0.5264 - val_accuracy: 0.6870
Epoch 350/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5032 - accuracy: 0.7534 - val_loss: 0.5262 - val_accuracy: 0.6870
Epoch 351/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5031 - accuracy: 0.7534 - val_loss: 0.5261 - val_accuracy: 0.6870
Epoch 352/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5030 - accuracy: 0.7534 - val_loss: 0.5259 - val_accuracy: 0.6870
Epoch 353/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5029 - accuracy: 0.7534 - val_loss: 0.5258 - val_accuracy: 0.6870
Epoch 354/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5028 - accuracy: 0.7534 - val_loss: 0.5256 - val_accuracy: 0.6870
Epoch 355/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5027 - accuracy: 0.7550 - val_loss: 0.5255 - val_accuracy: 0.6870
Epoch 356/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5026 - accuracy: 0.7550 - val_loss: 0.5253 - val_accuracy: 0.6870
Epoch 357/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5025 - accuracy: 0.7550 - val_loss: 0.5252 - val_accuracy: 0.6870
Epoch 358/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5024 - accuracy: 0.7534 - val_loss: 0.5250 - val_accuracy: 0.6870
Epoch 359/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5022 - accuracy: 0.7550 - val_loss: 0.5249 - val_accuracy: 0.6870
Epoch 360/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5021 - accuracy: 0.7550 - val_loss: 0.5247 - val_accuracy: 0.6870
Epoch 361/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5020 - accuracy: 0.7550 - val_loss: 0.5246 - val_accuracy: 0.6870
Epoch 362/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5019 - accuracy: 0.7565 - val_loss: 0.5244 - val_accuracy: 0.6870
Epoch 363/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5018 - accuracy: 0.7565 - val_loss: 0.5243 - val_accuracy: 0.6870
Epoch 364/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5017 - accuracy: 0.7580 - val_loss: 0.5241 - val_accuracy: 0.6870
Epoch 365/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5016 - accuracy: 0.7565 - val_loss: 0.5240 - val_accuracy: 0.6870
Epoch 366/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5015 - accuracy: 0.7565 - val_loss: 0.5238 - val_accuracy: 0.6870
Epoch 367/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5014 - accuracy: 0.7550 - val_loss: 0.5237 - val_accuracy: 0.6870
Epoch 368/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5013 - accuracy: 0.7550 - val_loss: 0.5236 - val_accuracy: 0.6870
Epoch 369/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5012 - accuracy: 0.7550 - val_loss: 0.5234 - val_accuracy: 0.6870
Epoch 370/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5011 - accuracy: 0.7550 - val_loss: 0.5233 - val_accuracy: 0.6870
Epoch 371/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5010 - accuracy: 0.7550 - val_loss: 0.5231 - val_accuracy: 0.6870
Epoch 372/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5009 - accuracy: 0.7550 - val_loss: 0.5230 - val_accuracy: 0.6870
Epoch 373/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5008 - accuracy: 0.7550 - val_loss: 0.5228 - val_accuracy: 0.6870
Epoch 374/400
21/21 [==============================] - 0s 4ms/step - loss: 0.5007 - accuracy: 0.7550 - val_loss: 0.5227 - val_accuracy: 0.6870
Epoch 375/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5006 - accuracy: 0.7550 - val_loss: 0.5225 - val_accuracy: 0.6870
Epoch 376/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5005 - accuracy: 0.7550 - val_loss: 0.5223 - val_accuracy: 0.6870
Epoch 377/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5004 - accuracy: 0.7550 - val_loss: 0.5222 - val_accuracy: 0.6870
Epoch 378/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5003 - accuracy: 0.7550 - val_loss: 0.5220 - val_accuracy: 0.6870
Epoch 379/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5002 - accuracy: 0.7534 - val_loss: 0.5219 - val_accuracy: 0.6870
Epoch 380/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5001 - accuracy: 0.7534 - val_loss: 0.5217 - val_accuracy: 0.6870
Epoch 381/400
21/21 [==============================] - 0s 3ms/step - loss: 0.5000 - accuracy: 0.7534 - val_loss: 0.5216 - val_accuracy: 0.6870
Epoch 382/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4999 - accuracy: 0.7534 - val_loss: 0.5214 - val_accuracy: 0.6870
Epoch 383/400
21/21 [==============================] - 0s 4ms/step - loss: 0.4998 - accuracy: 0.7534 - val_loss: 0.5213 - val_accuracy: 0.6870
Epoch 384/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4997 - accuracy: 0.7534 - val_loss: 0.5211 - val_accuracy: 0.6870
Epoch 385/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4996 - accuracy: 0.7534 - val_loss: 0.5210 - val_accuracy: 0.6870
Epoch 386/400
21/21 [==============================] - 0s 4ms/step - loss: 0.4995 - accuracy: 0.7534 - val_loss: 0.5208 - val_accuracy: 0.6870
Epoch 387/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4994 - accuracy: 0.7534 - val_loss: 0.5207 - val_accuracy: 0.6870
Epoch 388/400
21/21 [==============================] - 0s 4ms/step - loss: 0.4993 - accuracy: 0.7534 - val_loss: 0.5205 - val_accuracy: 0.6870
Epoch 389/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4992 - accuracy: 0.7550 - val_loss: 0.5204 - val_accuracy: 0.6870
Epoch 390/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4991 - accuracy: 0.7534 - val_loss: 0.5203 - val_accuracy: 0.6870
Epoch 391/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4990 - accuracy: 0.7534 - val_loss: 0.5201 - val_accuracy: 0.6870
Epoch 392/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4989 - accuracy: 0.7534 - val_loss: 0.5200 - val_accuracy: 0.6870
Epoch 393/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4988 - accuracy: 0.7534 - val_loss: 0.5199 - val_accuracy: 0.6870
Epoch 394/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4988 - accuracy: 0.7534 - val_loss: 0.5198 - val_accuracy: 0.6870
Epoch 395/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4987 - accuracy: 0.7534 - val_loss: 0.5196 - val_accuracy: 0.6870
Epoch 396/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4986 - accuracy: 0.7534 - val_loss: 0.5195 - val_accuracy: 0.6870
Epoch 397/400
21/21 [==============================] - 0s 4ms/step - loss: 0.4985 - accuracy: 0.7534 - val_loss: 0.5194 - val_accuracy: 0.6870
Epoch 398/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4984 - accuracy: 0.7534 - val_loss: 0.5193 - val_accuracy: 0.6870
Epoch 399/400
21/21 [==============================] - 0s 3ms/step - loss: 0.4983 - accuracy: 0.7534 - val_loss: 0.5191 - val_accuracy: 0.6870
Epoch 400/400
21/21 [==============================] - 0s 4ms/step - loss: 0.4982 - accuracy: 0.7534 - val_loss: 0.5190 - val_accuracy: 0.6870

Elapsed time =>  0:00:30.603552

In [ ]:

model.evaluate(x_test, y_test)  # 또는 pred = model.predict()

4/4 [==============================] - 0s 3ms/step - loss: 0.5190 - accuracy: 0.6870

Out[ ]:

[0.5190069675445557, 0.686956524848938]

In [ ]:

plt.title('loss trend')
plt.xlabel('epochs')
plt.ylabel('loss')
plt.grid()

plt.plot(hist.history['loss'], label = 'train loss')
plt.plot(hist.history['val_loss'], label = 'validation loss')
plt.legend(loc = 'best')

plt.show()

In [ ]:

plt.title('accuracy trend')
plt.xlabel('epochs')
plt.ylabel('loss')
plt.grid()

plt.plot(hist.history['accuracy'], label = 'train accuracy')
plt.plot(hist.history['val_accuracy'], label = 'validation accuracy')
plt.legend(loc = 'best')

plt.show()

In [ ]:

In [ ]:

 

 

캐글 당뇨병 데이터 분석