Cardiovascular diseases¶
Credit: AITS Cainvas Community
Photo by Mat Voyce on Dribbble
Are the most common cause of deaths globally, taking an estimated 17.9 million lives each year, which accounts for 31% of all deaths worldwide. Heart failure is a common event caused by Cardiovascular diseases.
It is characterized by the heart’s inability to pump an adequate supply of blood to the body. Without sufficient blood flow, all major body functions are disrupted. Heart failure is a condition or a collection of symptoms that weaken the heart.
TABLE OF CONTENTS¶
IMPORTING LIBRARIES
LOADING DATA
DATA ANALYSIS
DATA PREPROCESSING
MODEL BUILDING
CONCLUSIONS
IMPORTING LIBRARIES¶
In [1]:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import preprocessing
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
import seaborn as sns
from tensorflow.keras.layers import Dense, BatchNormalization, Dropout, LSTM
from tensorflow.keras.models import Sequential
from tensorflow.keras.utils import to_categorical
from tensorflow.keras import callbacks
from sklearn.metrics import precision_score, recall_score, confusion_matrix, classification_report, accuracy_score, f1_score
LOADING DATA¶
In [2]:
#loading data
data = pd.read_csv("https://cainvas-static.s3.amazonaws.com/media/user_data/cainvas-admin/heart_failure_clinical_records_dataset_lsgYy2P.csv")
data.head()
Out[2]:
| age | anaemia | creatinine_phosphokinase | diabetes | ejection_fraction | high_blood_pressure | platelets | serum_creatinine | serum_sodium | sex | smoking | time | DEATH_EVENT | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 75.0 | 0 | 582 | 0 | 20 | 1 | 265000.00 | 1.9 | 130 | 1 | 0 | 4 | 1 |
| 1 | 55.0 | 0 | 7861 | 0 | 38 | 0 | 263358.03 | 1.1 | 136 | 1 | 0 | 6 | 1 |
| 2 | 65.0 | 0 | 146 | 0 | 20 | 0 | 162000.00 | 1.3 | 129 | 1 | 1 | 7 | 1 |
| 3 | 50.0 | 1 | 111 | 0 | 20 | 0 | 210000.00 | 1.9 | 137 | 1 | 0 | 7 | 1 |
| 4 | 65.0 | 1 | 160 | 1 | 20 | 0 | 327000.00 | 2.7 | 116 | 0 | 0 | 8 | 1 |
In [3]:
data.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 299 entries, 0 to 298 Data columns (total 13 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 age 299 non-null float64 1 anaemia 299 non-null int64 2 creatinine_phosphokinase 299 non-null int64 3 diabetes 299 non-null int64 4 ejection_fraction 299 non-null int64 5 high_blood_pressure 299 non-null int64 6 platelets 299 non-null float64 7 serum_creatinine 299 non-null float64 8 serum_sodium 299 non-null int64 9 sex 299 non-null int64 10 smoking 299 non-null int64 11 time 299 non-null int64 12 DEATH_EVENT 299 non-null int64 dtypes: float64(3), int64(10) memory usage: 30.5 KB
About the data:¶
age: Age of the patient
anaemia: If the patient had the haemoglobin below the normal range creatinine_phosphokinase: The level of the creatine phosphokinase in the blood in mcg/L
diabetes: If the patient was diabetic ejection_fraction: Ejection fraction is a measurement of how much blood the left ventricle pumps out with each contraction
high_blood_pressure: If the patient had hypertension
platelets: Platelet count of blood in kiloplatelets/mL
serum_creatinine: The level of serum creatinine in the blood in mg/dL
serum_sodium: The level of serum sodium in the blood in mEq/L
sex: The sex of the patient
smoking: If the patient smokes actively or ever did in past
time: It is the time of the patient's follow-up visit for the disease in months
DEATH_EVENT: If the patient deceased during the follow-up period
DATA ANALYSIS¶
Steps in data analysis and visulisation:
We begin our analysis by plotting a count plot of the targer attribute. A corelation matrix od the various attributes to examine the feature importance.
In [4]:
#first of all let us evaluate the target and find out if our data is imbalanced or not
cols= ["#6daa9f","#774571"]
sns.countplot(x= data["DEATH_EVENT"], palette= cols)
Out[4]:
<AxesSubplot:xlabel='DEATH_EVENT', ylabel='count'>
In [5]:
#Examaning a corelation matrix of all the features
cmap = sns.diverging_palette(275,150, s=40, l=65, n=9)
corrmat = data.corr()
plt.subplots(figsize=(18,18))
sns.heatmap(corrmat,cmap= cmap,annot=True, square=True);
Notable points:¶
Time of the patient's follow-up visit for the disease is crucial in as initial diagnosis with cardiovascular issue and treatment reduces the chances of any fatality. It holds and inverse relation.
Ejection fraction is the second most important feature. It is quite expected as it is basically the efficiency of the heart.
Age of the patient is the third most correlated feature. Clearly as heart's functioning declines with ageing
Next, we will examine the count plot of age.
In [6]:
#Evauating age distrivution
plt.figure(figsize=(20,12))
#colours =["#774571","#b398af","#f1f1f1" ,"#afcdc7", "#6daa9f"]
Days_of_week=sns.countplot(x=data['age'],data=data, hue ="DEATH_EVENT",palette = cols)
Days_of_week.set_title("Distribution Of Age", color="#774571")
Out[6]:
Text(0.5, 1.0, 'Distribution Of Age')
In [7]:
# Boxen and swarm plot of some non binary features.
feature = ["age","creatinine_phosphokinase","ejection_fraction","platelets","serum_creatinine","serum_sodium", "time"]
for i in feature:
plt.figure(figsize=(8,8))
sns.swarmplot(x=data["DEATH_EVENT"], y=data[i], color="black", alpha=0.5)
sns.boxenplot(x=data["DEATH_EVENT"], y=data[i], palette=cols)
sns.stripplot(x=data["DEATH_EVENT"], y=data[i], palette=cols)
plt.show()
/opt/tljh/user/lib/python3.7/site-packages/seaborn/categorical.py:1296: UserWarning: 17.7% of the points cannot be placed; you may want to decrease the size of the markers or use stripplot. warnings.warn(msg, UserWarning)
I spotted outliers on our dataset. I didn't remove them yet as it may lead to overfitting. Though we may end up with better statistics. In this case, with medical data, the outliers may be an important deciding factor.
Next, we examine the kdeplot of time and age as they both are significant features.
In [8]:
sns.kdeplot(x=data["time"], y=data["age"], hue =data["DEATH_EVENT"], palette=cols)
Out[8]:
<AxesSubplot:xlabel='time', ylabel='age'>
In [9]:
data.describe().T
Out[9]:
| count | mean | std | min | 25% | 50% | 75% | max | |
|---|---|---|---|---|---|---|---|---|
| age | 299.0 | 60.833893 | 11.894809 | 40.0 | 51.0 | 60.0 | 70.0 | 95.0 |
| anaemia | 299.0 | 0.431438 | 0.496107 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 |
| creatinine_phosphokinase | 299.0 | 581.839465 | 970.287881 | 23.0 | 116.5 | 250.0 | 582.0 | 7861.0 |
| diabetes | 299.0 | 0.418060 | 0.494067 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 |
| ejection_fraction | 299.0 | 38.083612 | 11.834841 | 14.0 | 30.0 | 38.0 | 45.0 | 80.0 |
| high_blood_pressure | 299.0 | 0.351171 | 0.478136 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 |
| platelets | 299.0 | 263358.029264 | 97804.236869 | 25100.0 | 212500.0 | 262000.0 | 303500.0 | 850000.0 |
| serum_creatinine | 299.0 | 1.393880 | 1.034510 | 0.5 | 0.9 | 1.1 | 1.4 | 9.4 |
| serum_sodium | 299.0 | 136.625418 | 4.412477 | 113.0 | 134.0 | 137.0 | 140.0 | 148.0 |
| sex | 299.0 | 0.648829 | 0.478136 | 0.0 | 0.0 | 1.0 | 1.0 | 1.0 |
| smoking | 299.0 | 0.321070 | 0.467670 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 |
| time | 299.0 | 130.260870 | 77.614208 | 4.0 | 73.0 | 115.0 | 203.0 | 285.0 |
| DEATH_EVENT | 299.0 | 0.321070 | 0.467670 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 |
In [10]:
#assigning values to features as X and target as y
X=data.drop(["DEATH_EVENT"],axis=1)
y=data["DEATH_EVENT"]
In [11]:
#Set up a standard scaler for the features
col_names = list(X.columns)
s_scaler = preprocessing.StandardScaler()
X_df= s_scaler.fit_transform(X)
X_df = pd.DataFrame(X_df, columns=col_names)
X_df.describe().T
Out[11]:
| count | mean | std | min | 25% | 50% | 75% | max | |
|---|---|---|---|---|---|---|---|---|
| age | 299.0 | 5.703353e-16 | 1.001676 | -1.754448 | -0.828124 | -0.070223 | 0.771889 | 2.877170 |
| anaemia | 299.0 | 1.009969e-16 | 1.001676 | -0.871105 | -0.871105 | -0.871105 | 1.147968 | 1.147968 |
| creatinine_phosphokinase | 299.0 | 0.000000e+00 | 1.001676 | -0.576918 | -0.480393 | -0.342574 | 0.000166 | 7.514640 |
| diabetes | 299.0 | 9.060014e-17 | 1.001676 | -0.847579 | -0.847579 | -0.847579 | 1.179830 | 1.179830 |
| ejection_fraction | 299.0 | -3.267546e-17 | 1.001676 | -2.038387 | -0.684180 | -0.007077 | 0.585389 | 3.547716 |
| high_blood_pressure | 299.0 | 0.000000e+00 | 1.001676 | -0.735688 | -0.735688 | -0.735688 | 1.359272 | 1.359272 |
| platelets | 299.0 | 7.723291e-17 | 1.001676 | -2.440155 | -0.520870 | -0.013908 | 0.411120 | 6.008180 |
| serum_creatinine | 299.0 | 1.425838e-16 | 1.001676 | -0.865509 | -0.478205 | -0.284552 | 0.005926 | 7.752020 |
| serum_sodium | 299.0 | -8.673849e-16 | 1.001676 | -5.363206 | -0.595996 | 0.085034 | 0.766064 | 2.582144 |
| sex | 299.0 | -8.911489e-18 | 1.001676 | -1.359272 | -1.359272 | 0.735688 | 0.735688 | 0.735688 |
| smoking | 299.0 | -1.188199e-17 | 1.001676 | -0.687682 | -0.687682 | -0.687682 | 1.454161 | 1.454161 |
| time | 299.0 | -1.901118e-16 | 1.001676 | -1.629502 | -0.739000 | -0.196954 | 0.938759 | 1.997038 |
In [12]:
#looking at the scaled features
colours =["#774571","#b398af","#f1f1f1" ,"#afcdc7", "#6daa9f"]
plt.figure(figsize=(20,10))
sns.boxenplot(data = X_df,palette = colours)
plt.xticks(rotation=90)
plt.show()
In [13]:
#spliting test and training sets
X_train, X_test, y_train,y_test = train_test_split(X_df,y,test_size=0.25,random_state=7)
In [23]:
early_stopping = callbacks.EarlyStopping(
min_delta=0.001, # minimium amount of change to count as an improvement
patience=20, # how many epochs to wait before stopping
restore_best_weights=True)
# Initialising the NN
model = Sequential()
# layers
model.add(Dense(units = 16, kernel_initializer = 'uniform', activation = 'relu', input_dim = 12))
model.add(Dense(units = 8, kernel_initializer = 'uniform', activation = 'relu'))
model.add(Dropout(0.5))
model.add(Dense(units = 4, kernel_initializer = 'uniform', activation = 'relu'))
model.add(Dropout(0.5))
model.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
from tensorflow.keras.optimizers import SGD
# Compiling the ANN
model.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
# Train the ANN
history = model.fit(X_train, y_train, batch_size = 32, epochs = 500, validation_split=0.2)
Epoch 1/500 6/6 [==============================] - 0s 21ms/step - loss: 0.6928 - accuracy: 0.5922 - val_loss: 0.6921 - val_accuracy: 0.6667 Epoch 2/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6919 - accuracy: 0.6480 - val_loss: 0.6912 - val_accuracy: 0.6667 Epoch 3/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6911 - accuracy: 0.6480 - val_loss: 0.6902 - val_accuracy: 0.6667 Epoch 4/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6903 - accuracy: 0.6480 - val_loss: 0.6893 - val_accuracy: 0.6667 Epoch 5/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6894 - accuracy: 0.6480 - val_loss: 0.6884 - val_accuracy: 0.6667 Epoch 6/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6886 - accuracy: 0.6480 - val_loss: 0.6874 - val_accuracy: 0.6667 Epoch 7/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6877 - accuracy: 0.6480 - val_loss: 0.6864 - val_accuracy: 0.6667 Epoch 8/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6868 - accuracy: 0.6480 - val_loss: 0.6854 - val_accuracy: 0.6667 Epoch 9/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6860 - accuracy: 0.6480 - val_loss: 0.6843 - val_accuracy: 0.6667 Epoch 10/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6847 - accuracy: 0.6480 - val_loss: 0.6831 - val_accuracy: 0.6667 Epoch 11/500 6/6 [==============================] - 0s 3ms/step - loss: 0.6840 - accuracy: 0.6480 - val_loss: 0.6818 - val_accuracy: 0.6667 Epoch 12/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6823 - accuracy: 0.6480 - val_loss: 0.6804 - val_accuracy: 0.6667 Epoch 13/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6814 - accuracy: 0.6480 - val_loss: 0.6786 - val_accuracy: 0.6667 Epoch 14/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6801 - accuracy: 0.6480 - val_loss: 0.6766 - val_accuracy: 0.6667 Epoch 15/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6778 - accuracy: 0.6480 - val_loss: 0.6741 - val_accuracy: 0.6667 Epoch 16/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6745 - accuracy: 0.6480 - val_loss: 0.6710 - val_accuracy: 0.6667 Epoch 17/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6708 - accuracy: 0.6480 - val_loss: 0.6670 - val_accuracy: 0.6667 Epoch 18/500 6/6 [==============================] - 0s 7ms/step - loss: 0.6712 - accuracy: 0.6480 - val_loss: 0.6623 - val_accuracy: 0.6667 Epoch 19/500 6/6 [==============================] - 0s 6ms/step - loss: 0.6629 - accuracy: 0.6480 - val_loss: 0.6564 - val_accuracy: 0.6667 Epoch 20/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6532 - accuracy: 0.6480 - val_loss: 0.6489 - val_accuracy: 0.6667 Epoch 21/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6527 - accuracy: 0.6480 - val_loss: 0.6400 - val_accuracy: 0.6667 Epoch 22/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6436 - accuracy: 0.6480 - val_loss: 0.6294 - val_accuracy: 0.6667 Epoch 23/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6257 - accuracy: 0.6480 - val_loss: 0.6169 - val_accuracy: 0.6667 Epoch 24/500 6/6 [==============================] - 0s 3ms/step - loss: 0.6299 - accuracy: 0.6480 - val_loss: 0.6032 - val_accuracy: 0.6667 Epoch 25/500 6/6 [==============================] - 0s 4ms/step - loss: 0.6104 - accuracy: 0.6480 - val_loss: 0.5890 - val_accuracy: 0.6667 Epoch 26/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5906 - accuracy: 0.6536 - val_loss: 0.5752 - val_accuracy: 0.6667 Epoch 27/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5914 - accuracy: 0.6480 - val_loss: 0.5617 - val_accuracy: 0.6667 Epoch 28/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5827 - accuracy: 0.6480 - val_loss: 0.5492 - val_accuracy: 0.6667 Epoch 29/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5796 - accuracy: 0.6648 - val_loss: 0.5377 - val_accuracy: 0.6667 Epoch 30/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5494 - accuracy: 0.6872 - val_loss: 0.5296 - val_accuracy: 0.6667 Epoch 31/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5548 - accuracy: 0.6704 - val_loss: 0.5226 - val_accuracy: 0.6667 Epoch 32/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5324 - accuracy: 0.6983 - val_loss: 0.5184 - val_accuracy: 0.6667 Epoch 33/500 6/6 [==============================] - 0s 3ms/step - loss: 0.5448 - accuracy: 0.6983 - val_loss: 0.5148 - val_accuracy: 0.6667 Epoch 34/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5075 - accuracy: 0.7263 - val_loss: 0.5123 - val_accuracy: 0.6889 Epoch 35/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5449 - accuracy: 0.7039 - val_loss: 0.5103 - val_accuracy: 0.7111 Epoch 36/500 6/6 [==============================] - 0s 11ms/step - loss: 0.5470 - accuracy: 0.7151 - val_loss: 0.5078 - val_accuracy: 0.7111 Epoch 37/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4977 - accuracy: 0.7374 - val_loss: 0.5041 - val_accuracy: 0.7333 Epoch 38/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5364 - accuracy: 0.7151 - val_loss: 0.5009 - val_accuracy: 0.7111 Epoch 39/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5117 - accuracy: 0.7318 - val_loss: 0.5012 - val_accuracy: 0.7333 Epoch 40/500 6/6 [==============================] - 0s 3ms/step - loss: 0.5054 - accuracy: 0.7207 - val_loss: 0.5014 - val_accuracy: 0.7333 Epoch 41/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4724 - accuracy: 0.7598 - val_loss: 0.4995 - val_accuracy: 0.7333 Epoch 42/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5439 - accuracy: 0.7486 - val_loss: 0.4994 - val_accuracy: 0.7556 Epoch 43/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4811 - accuracy: 0.7821 - val_loss: 0.4980 - val_accuracy: 0.8222 Epoch 44/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5134 - accuracy: 0.7318 - val_loss: 0.4974 - val_accuracy: 0.8222 Epoch 45/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5024 - accuracy: 0.7207 - val_loss: 0.4972 - val_accuracy: 0.8222 Epoch 46/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4747 - accuracy: 0.7821 - val_loss: 0.4978 - val_accuracy: 0.8222 Epoch 47/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4848 - accuracy: 0.7374 - val_loss: 0.4971 - val_accuracy: 0.8222 Epoch 48/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5001 - accuracy: 0.6927 - val_loss: 0.4979 - val_accuracy: 0.8222 Epoch 49/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4891 - accuracy: 0.7151 - val_loss: 0.4992 - val_accuracy: 0.8222 Epoch 50/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4886 - accuracy: 0.7598 - val_loss: 0.5004 - val_accuracy: 0.8222 Epoch 51/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4541 - accuracy: 0.7151 - val_loss: 0.5017 - val_accuracy: 0.8222 Epoch 52/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4910 - accuracy: 0.7598 - val_loss: 0.5020 - val_accuracy: 0.8000 Epoch 53/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5131 - accuracy: 0.6872 - val_loss: 0.5008 - val_accuracy: 0.8000 Epoch 54/500 6/6 [==============================] - 0s 9ms/step - loss: 0.4504 - accuracy: 0.7207 - val_loss: 0.5000 - val_accuracy: 0.8000 Epoch 55/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4989 - accuracy: 0.6927 - val_loss: 0.4999 - val_accuracy: 0.8000 Epoch 56/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5308 - accuracy: 0.6425 - val_loss: 0.5009 - val_accuracy: 0.8000 Epoch 57/500 6/6 [==============================] - 0s 3ms/step - loss: 0.4583 - accuracy: 0.7318 - val_loss: 0.5026 - val_accuracy: 0.8000 Epoch 58/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4888 - accuracy: 0.7374 - val_loss: 0.5039 - val_accuracy: 0.8000 Epoch 59/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4838 - accuracy: 0.7486 - val_loss: 0.5036 - val_accuracy: 0.8000 Epoch 60/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4241 - accuracy: 0.7877 - val_loss: 0.5037 - val_accuracy: 0.8000 Epoch 61/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5341 - accuracy: 0.6927 - val_loss: 0.5022 - val_accuracy: 0.8000 Epoch 62/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5330 - accuracy: 0.6983 - val_loss: 0.5001 - val_accuracy: 0.8000 Epoch 63/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4445 - accuracy: 0.7374 - val_loss: 0.4994 - val_accuracy: 0.8000 Epoch 64/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4403 - accuracy: 0.7765 - val_loss: 0.4979 - val_accuracy: 0.8000 Epoch 65/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4713 - accuracy: 0.7207 - val_loss: 0.4973 - val_accuracy: 0.8000 Epoch 66/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4534 - accuracy: 0.7486 - val_loss: 0.4988 - val_accuracy: 0.7778 Epoch 67/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4841 - accuracy: 0.7486 - val_loss: 0.5009 - val_accuracy: 0.7778 Epoch 68/500 6/6 [==============================] - 0s 3ms/step - loss: 0.5119 - accuracy: 0.7095 - val_loss: 0.5032 - val_accuracy: 0.7778 Epoch 69/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4634 - accuracy: 0.7430 - val_loss: 0.5042 - val_accuracy: 0.8000 Epoch 70/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4938 - accuracy: 0.7933 - val_loss: 0.5038 - val_accuracy: 0.8000 Epoch 71/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4503 - accuracy: 0.7430 - val_loss: 0.5008 - val_accuracy: 0.8000 Epoch 72/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4655 - accuracy: 0.7207 - val_loss: 0.5005 - val_accuracy: 0.8000 Epoch 73/500 6/6 [==============================] - 0s 9ms/step - loss: 0.4720 - accuracy: 0.7430 - val_loss: 0.5006 - val_accuracy: 0.8000 Epoch 74/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4354 - accuracy: 0.7598 - val_loss: 0.5004 - val_accuracy: 0.8000 Epoch 75/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4536 - accuracy: 0.6983 - val_loss: 0.5017 - val_accuracy: 0.7778 Epoch 76/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4699 - accuracy: 0.7318 - val_loss: 0.5037 - val_accuracy: 0.7778 Epoch 77/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4632 - accuracy: 0.7542 - val_loss: 0.5053 - val_accuracy: 0.7778 Epoch 78/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4916 - accuracy: 0.6927 - val_loss: 0.5072 - val_accuracy: 0.7778 Epoch 79/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4293 - accuracy: 0.7374 - val_loss: 0.5083 - val_accuracy: 0.8000 Epoch 80/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4957 - accuracy: 0.7318 - val_loss: 0.5094 - val_accuracy: 0.8000 Epoch 81/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4779 - accuracy: 0.7318 - val_loss: 0.5080 - val_accuracy: 0.8000 Epoch 82/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5238 - accuracy: 0.6983 - val_loss: 0.5040 - val_accuracy: 0.8222 Epoch 83/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4916 - accuracy: 0.7430 - val_loss: 0.5010 - val_accuracy: 0.8222 Epoch 84/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4623 - accuracy: 0.7318 - val_loss: 0.4998 - val_accuracy: 0.8222 Epoch 85/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4484 - accuracy: 0.7654 - val_loss: 0.4982 - val_accuracy: 0.8444 Epoch 86/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4406 - accuracy: 0.7486 - val_loss: 0.5003 - val_accuracy: 0.8444 Epoch 87/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4328 - accuracy: 0.7486 - val_loss: 0.5030 - val_accuracy: 0.8444 Epoch 88/500 6/6 [==============================] - 0s 3ms/step - loss: 0.4584 - accuracy: 0.7598 - val_loss: 0.5069 - val_accuracy: 0.8222 Epoch 89/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4685 - accuracy: 0.7263 - val_loss: 0.5056 - val_accuracy: 0.8222 Epoch 90/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4722 - accuracy: 0.7207 - val_loss: 0.5049 - val_accuracy: 0.8222 Epoch 91/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3953 - accuracy: 0.7765 - val_loss: 0.5052 - val_accuracy: 0.8222 Epoch 92/500 6/6 [==============================] - 0s 11ms/step - loss: 0.4368 - accuracy: 0.7430 - val_loss: 0.5060 - val_accuracy: 0.8222 Epoch 93/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4458 - accuracy: 0.7263 - val_loss: 0.5084 - val_accuracy: 0.8222 Epoch 94/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4181 - accuracy: 0.7430 - val_loss: 0.5102 - val_accuracy: 0.8222 Epoch 95/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4155 - accuracy: 0.7263 - val_loss: 0.5129 - val_accuracy: 0.8222 Epoch 96/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4683 - accuracy: 0.7374 - val_loss: 0.5122 - val_accuracy: 0.8222 Epoch 97/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4140 - accuracy: 0.7765 - val_loss: 0.5120 - val_accuracy: 0.8222 Epoch 98/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4522 - accuracy: 0.7765 - val_loss: 0.5112 - val_accuracy: 0.8444 Epoch 99/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4660 - accuracy: 0.7598 - val_loss: 0.5108 - val_accuracy: 0.8444 Epoch 100/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4344 - accuracy: 0.7486 - val_loss: 0.5114 - val_accuracy: 0.8444 Epoch 101/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4740 - accuracy: 0.7207 - val_loss: 0.5123 - val_accuracy: 0.8444 Epoch 102/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3993 - accuracy: 0.7374 - val_loss: 0.5130 - val_accuracy: 0.8444 Epoch 103/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4606 - accuracy: 0.7765 - val_loss: 0.5139 - val_accuracy: 0.8444 Epoch 104/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3934 - accuracy: 0.7989 - val_loss: 0.5145 - val_accuracy: 0.8444 Epoch 105/500 6/6 [==============================] - 0s 4ms/step - loss: 0.5164 - accuracy: 0.7542 - val_loss: 0.5085 - val_accuracy: 0.8444 Epoch 106/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4802 - accuracy: 0.7318 - val_loss: 0.5059 - val_accuracy: 0.8444 Epoch 107/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4598 - accuracy: 0.6983 - val_loss: 0.5066 - val_accuracy: 0.8444 Epoch 108/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4387 - accuracy: 0.7709 - val_loss: 0.5066 - val_accuracy: 0.8444 Epoch 109/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4351 - accuracy: 0.7318 - val_loss: 0.5081 - val_accuracy: 0.8444 Epoch 110/500 6/6 [==============================] - 0s 9ms/step - loss: 0.4517 - accuracy: 0.7598 - val_loss: 0.5100 - val_accuracy: 0.8222 Epoch 111/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4560 - accuracy: 0.7598 - val_loss: 0.5107 - val_accuracy: 0.8222 Epoch 112/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4277 - accuracy: 0.7486 - val_loss: 0.5090 - val_accuracy: 0.8222 Epoch 113/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4364 - accuracy: 0.7542 - val_loss: 0.5080 - val_accuracy: 0.8444 Epoch 114/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4654 - accuracy: 0.7765 - val_loss: 0.5094 - val_accuracy: 0.8444 Epoch 115/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4353 - accuracy: 0.7542 - val_loss: 0.5075 - val_accuracy: 0.8444 Epoch 116/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4148 - accuracy: 0.7654 - val_loss: 0.5086 - val_accuracy: 0.8444 Epoch 117/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4358 - accuracy: 0.7430 - val_loss: 0.5108 - val_accuracy: 0.8444 Epoch 118/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4564 - accuracy: 0.7654 - val_loss: 0.5118 - val_accuracy: 0.8444 Epoch 119/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3914 - accuracy: 0.7542 - val_loss: 0.5138 - val_accuracy: 0.8444 Epoch 120/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4353 - accuracy: 0.7765 - val_loss: 0.5123 - val_accuracy: 0.8444 Epoch 121/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4124 - accuracy: 0.7542 - val_loss: 0.5118 - val_accuracy: 0.8444 Epoch 122/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4334 - accuracy: 0.7542 - val_loss: 0.5128 - val_accuracy: 0.8444 Epoch 123/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4242 - accuracy: 0.7263 - val_loss: 0.5140 - val_accuracy: 0.8444 Epoch 124/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4902 - accuracy: 0.6983 - val_loss: 0.5157 - val_accuracy: 0.8444 Epoch 125/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4565 - accuracy: 0.7430 - val_loss: 0.5137 - val_accuracy: 0.8222 Epoch 126/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4764 - accuracy: 0.7374 - val_loss: 0.5111 - val_accuracy: 0.8222 Epoch 127/500 6/6 [==============================] - 0s 5ms/step - loss: 0.4137 - accuracy: 0.7765 - val_loss: 0.5091 - val_accuracy: 0.8444 Epoch 128/500 6/6 [==============================] - 0s 9ms/step - loss: 0.4520 - accuracy: 0.7542 - val_loss: 0.5083 - val_accuracy: 0.8444 Epoch 129/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4467 - accuracy: 0.7654 - val_loss: 0.5098 - val_accuracy: 0.8444 Epoch 130/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4024 - accuracy: 0.7709 - val_loss: 0.5120 - val_accuracy: 0.8444 Epoch 131/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4071 - accuracy: 0.7821 - val_loss: 0.5131 - val_accuracy: 0.8444 Epoch 132/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4750 - accuracy: 0.7598 - val_loss: 0.5123 - val_accuracy: 0.8444 Epoch 133/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4561 - accuracy: 0.7877 - val_loss: 0.5115 - val_accuracy: 0.8444 Epoch 134/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4670 - accuracy: 0.7654 - val_loss: 0.5101 - val_accuracy: 0.8444 Epoch 135/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4229 - accuracy: 0.7877 - val_loss: 0.5078 - val_accuracy: 0.8444 Epoch 136/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4370 - accuracy: 0.7318 - val_loss: 0.5058 - val_accuracy: 0.8444 Epoch 137/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4471 - accuracy: 0.7542 - val_loss: 0.5048 - val_accuracy: 0.8444 Epoch 138/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4322 - accuracy: 0.7654 - val_loss: 0.5033 - val_accuracy: 0.8444 Epoch 139/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3938 - accuracy: 0.8045 - val_loss: 0.5038 - val_accuracy: 0.8444 Epoch 140/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4888 - accuracy: 0.7095 - val_loss: 0.5027 - val_accuracy: 0.8444 Epoch 141/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4216 - accuracy: 0.7486 - val_loss: 0.5022 - val_accuracy: 0.8444 Epoch 142/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4338 - accuracy: 0.7654 - val_loss: 0.5014 - val_accuracy: 0.8444 Epoch 143/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4275 - accuracy: 0.7765 - val_loss: 0.5004 - val_accuracy: 0.8444 Epoch 144/500 6/6 [==============================] - 0s 3ms/step - loss: 0.4492 - accuracy: 0.7598 - val_loss: 0.4992 - val_accuracy: 0.8444 Epoch 145/500 6/6 [==============================] - 0s 6ms/step - loss: 0.5018 - accuracy: 0.7207 - val_loss: 0.4999 - val_accuracy: 0.8444 Epoch 146/500 6/6 [==============================] - 0s 8ms/step - loss: 0.4743 - accuracy: 0.7318 - val_loss: 0.5012 - val_accuracy: 0.8444 Epoch 147/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4480 - accuracy: 0.7486 - val_loss: 0.5028 - val_accuracy: 0.8444 Epoch 148/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4510 - accuracy: 0.7374 - val_loss: 0.5050 - val_accuracy: 0.8444 Epoch 149/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3900 - accuracy: 0.7542 - val_loss: 0.5074 - val_accuracy: 0.8444 Epoch 150/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4403 - accuracy: 0.7542 - val_loss: 0.5059 - val_accuracy: 0.8444 Epoch 151/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4220 - accuracy: 0.7542 - val_loss: 0.5042 - val_accuracy: 0.8444 Epoch 152/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4351 - accuracy: 0.7654 - val_loss: 0.5049 - val_accuracy: 0.8444 Epoch 153/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4863 - accuracy: 0.7542 - val_loss: 0.5056 - val_accuracy: 0.8444 Epoch 154/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4951 - accuracy: 0.7207 - val_loss: 0.5044 - val_accuracy: 0.8444 Epoch 155/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4441 - accuracy: 0.7542 - val_loss: 0.5039 - val_accuracy: 0.8444 Epoch 156/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4522 - accuracy: 0.7598 - val_loss: 0.5039 - val_accuracy: 0.8444 Epoch 157/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4473 - accuracy: 0.7374 - val_loss: 0.5047 - val_accuracy: 0.8444 Epoch 158/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4479 - accuracy: 0.7486 - val_loss: 0.5044 - val_accuracy: 0.8444 Epoch 159/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3961 - accuracy: 0.7821 - val_loss: 0.5054 - val_accuracy: 0.8444 Epoch 160/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4253 - accuracy: 0.7374 - val_loss: 0.5086 - val_accuracy: 0.8444 Epoch 161/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4612 - accuracy: 0.7542 - val_loss: 0.5088 - val_accuracy: 0.8444 Epoch 162/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4391 - accuracy: 0.7318 - val_loss: 0.5097 - val_accuracy: 0.8444 Epoch 163/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4155 - accuracy: 0.7542 - val_loss: 0.5098 - val_accuracy: 0.8444 Epoch 164/500 6/6 [==============================] - 0s 11ms/step - loss: 0.4582 - accuracy: 0.6760 - val_loss: 0.5106 - val_accuracy: 0.8444 Epoch 165/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4258 - accuracy: 0.7430 - val_loss: 0.5120 - val_accuracy: 0.8444 Epoch 166/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4146 - accuracy: 0.7207 - val_loss: 0.5136 - val_accuracy: 0.8444 Epoch 167/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4150 - accuracy: 0.7765 - val_loss: 0.5156 - val_accuracy: 0.8444 Epoch 168/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4137 - accuracy: 0.7654 - val_loss: 0.5170 - val_accuracy: 0.8444 Epoch 169/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4743 - accuracy: 0.7430 - val_loss: 0.5192 - val_accuracy: 0.8444 Epoch 170/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4584 - accuracy: 0.7374 - val_loss: 0.5192 - val_accuracy: 0.8222 Epoch 171/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4153 - accuracy: 0.7598 - val_loss: 0.5211 - val_accuracy: 0.8222 Epoch 172/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4378 - accuracy: 0.7598 - val_loss: 0.5217 - val_accuracy: 0.8222 Epoch 173/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4315 - accuracy: 0.7542 - val_loss: 0.5212 - val_accuracy: 0.8222 Epoch 174/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4290 - accuracy: 0.7486 - val_loss: 0.5201 - val_accuracy: 0.8222 Epoch 175/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4477 - accuracy: 0.7151 - val_loss: 0.5166 - val_accuracy: 0.8222 Epoch 176/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3930 - accuracy: 0.7821 - val_loss: 0.5163 - val_accuracy: 0.8222 Epoch 177/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4442 - accuracy: 0.7430 - val_loss: 0.5196 - val_accuracy: 0.8222 Epoch 178/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4273 - accuracy: 0.7709 - val_loss: 0.5214 - val_accuracy: 0.8444 Epoch 179/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4049 - accuracy: 0.7318 - val_loss: 0.5232 - val_accuracy: 0.8444 Epoch 180/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4039 - accuracy: 0.7765 - val_loss: 0.5254 - val_accuracy: 0.8444 Epoch 181/500 6/6 [==============================] - 0s 6ms/step - loss: 0.3894 - accuracy: 0.7877 - val_loss: 0.5280 - val_accuracy: 0.8222 Epoch 182/500 6/6 [==============================] - 0s 9ms/step - loss: 0.4407 - accuracy: 0.7877 - val_loss: 0.5302 - val_accuracy: 0.8222 Epoch 183/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4185 - accuracy: 0.7709 - val_loss: 0.5311 - val_accuracy: 0.8222 Epoch 184/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4165 - accuracy: 0.7709 - val_loss: 0.5310 - val_accuracy: 0.8000 Epoch 185/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3920 - accuracy: 0.7374 - val_loss: 0.5302 - val_accuracy: 0.8222 Epoch 186/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4287 - accuracy: 0.7318 - val_loss: 0.5309 - val_accuracy: 0.8222 Epoch 187/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4134 - accuracy: 0.7765 - val_loss: 0.5312 - val_accuracy: 0.8222 Epoch 188/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4397 - accuracy: 0.7374 - val_loss: 0.5317 - val_accuracy: 0.8222 Epoch 189/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4618 - accuracy: 0.7654 - val_loss: 0.5337 - val_accuracy: 0.8222 Epoch 190/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4065 - accuracy: 0.7821 - val_loss: 0.5348 - val_accuracy: 0.8222 Epoch 191/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4317 - accuracy: 0.7486 - val_loss: 0.5356 - val_accuracy: 0.8222 Epoch 192/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3832 - accuracy: 0.7821 - val_loss: 0.5354 - val_accuracy: 0.8222 Epoch 193/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4658 - accuracy: 0.7486 - val_loss: 0.5318 - val_accuracy: 0.8222 Epoch 194/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4268 - accuracy: 0.7877 - val_loss: 0.5285 - val_accuracy: 0.8222 Epoch 195/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4102 - accuracy: 0.7542 - val_loss: 0.5286 - val_accuracy: 0.8222 Epoch 196/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4300 - accuracy: 0.7542 - val_loss: 0.5297 - val_accuracy: 0.8222 Epoch 197/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4339 - accuracy: 0.7709 - val_loss: 0.5286 - val_accuracy: 0.8222 Epoch 198/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3974 - accuracy: 0.7430 - val_loss: 0.5302 - val_accuracy: 0.8222 Epoch 199/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4201 - accuracy: 0.7374 - val_loss: 0.5336 - val_accuracy: 0.8222 Epoch 200/500 6/6 [==============================] - 0s 6ms/step - loss: 0.4040 - accuracy: 0.7598 - val_loss: 0.5359 - val_accuracy: 0.8222 Epoch 201/500 6/6 [==============================] - 0s 7ms/step - loss: 0.4300 - accuracy: 0.7598 - val_loss: 0.5391 - val_accuracy: 0.8222 Epoch 202/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3968 - accuracy: 0.7765 - val_loss: 0.5412 - val_accuracy: 0.8222 Epoch 203/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4120 - accuracy: 0.7709 - val_loss: 0.5424 - val_accuracy: 0.8222 Epoch 204/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4352 - accuracy: 0.7542 - val_loss: 0.5420 - val_accuracy: 0.8222 Epoch 205/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4290 - accuracy: 0.7207 - val_loss: 0.5441 - val_accuracy: 0.8222 Epoch 206/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3917 - accuracy: 0.7821 - val_loss: 0.5460 - val_accuracy: 0.8222 Epoch 207/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4310 - accuracy: 0.7486 - val_loss: 0.5451 - val_accuracy: 0.8222 Epoch 208/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3697 - accuracy: 0.7989 - val_loss: 0.5458 - val_accuracy: 0.8222 Epoch 209/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4143 - accuracy: 0.7374 - val_loss: 0.5474 - val_accuracy: 0.8222 Epoch 210/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3928 - accuracy: 0.7486 - val_loss: 0.5504 - val_accuracy: 0.8222 Epoch 211/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4107 - accuracy: 0.7765 - val_loss: 0.5482 - val_accuracy: 0.8222 Epoch 212/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3997 - accuracy: 0.7598 - val_loss: 0.5480 - val_accuracy: 0.8000 Epoch 213/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4144 - accuracy: 0.7430 - val_loss: 0.5481 - val_accuracy: 0.8000 Epoch 214/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4157 - accuracy: 0.7821 - val_loss: 0.5465 - val_accuracy: 0.8000 Epoch 215/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4069 - accuracy: 0.7933 - val_loss: 0.5465 - val_accuracy: 0.8000 Epoch 216/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3723 - accuracy: 0.8045 - val_loss: 0.5497 - val_accuracy: 0.8000 Epoch 217/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4123 - accuracy: 0.8045 - val_loss: 0.5534 - val_accuracy: 0.8000 Epoch 218/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4186 - accuracy: 0.8268 - val_loss: 0.5576 - val_accuracy: 0.8000 Epoch 219/500 6/6 [==============================] - 0s 11ms/step - loss: 0.3960 - accuracy: 0.7877 - val_loss: 0.5608 - val_accuracy: 0.8000 Epoch 220/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3922 - accuracy: 0.8268 - val_loss: 0.5616 - val_accuracy: 0.8000 Epoch 221/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4197 - accuracy: 0.7877 - val_loss: 0.5633 - val_accuracy: 0.8000 Epoch 222/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4164 - accuracy: 0.8045 - val_loss: 0.5630 - val_accuracy: 0.8000 Epoch 223/500 6/6 [==============================] - 0s 3ms/step - loss: 0.3924 - accuracy: 0.7765 - val_loss: 0.5634 - val_accuracy: 0.8222 Epoch 224/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3836 - accuracy: 0.7933 - val_loss: 0.5616 - val_accuracy: 0.8222 Epoch 225/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4018 - accuracy: 0.7933 - val_loss: 0.5619 - val_accuracy: 0.8222 Epoch 226/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4244 - accuracy: 0.7989 - val_loss: 0.5668 - val_accuracy: 0.8222 Epoch 227/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3901 - accuracy: 0.7821 - val_loss: 0.5705 - val_accuracy: 0.8222 Epoch 228/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4079 - accuracy: 0.7598 - val_loss: 0.5729 - val_accuracy: 0.8222 Epoch 229/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4367 - accuracy: 0.7542 - val_loss: 0.5710 - val_accuracy: 0.8222 Epoch 230/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4184 - accuracy: 0.7486 - val_loss: 0.5720 - val_accuracy: 0.8222 Epoch 231/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4108 - accuracy: 0.8156 - val_loss: 0.5704 - val_accuracy: 0.8222 Epoch 232/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4170 - accuracy: 0.7821 - val_loss: 0.5695 - val_accuracy: 0.8222 Epoch 233/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3655 - accuracy: 0.7654 - val_loss: 0.5704 - val_accuracy: 0.8222 Epoch 234/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3981 - accuracy: 0.8212 - val_loss: 0.5716 - val_accuracy: 0.8222 Epoch 235/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4333 - accuracy: 0.7933 - val_loss: 0.5736 - val_accuracy: 0.8000 Epoch 236/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4079 - accuracy: 0.7989 - val_loss: 0.5746 - val_accuracy: 0.8000 Epoch 237/500 6/6 [==============================] - 0s 10ms/step - loss: 0.3995 - accuracy: 0.7933 - val_loss: 0.5762 - val_accuracy: 0.8222 Epoch 238/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4122 - accuracy: 0.7821 - val_loss: 0.5717 - val_accuracy: 0.8222 Epoch 239/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4484 - accuracy: 0.7598 - val_loss: 0.5704 - val_accuracy: 0.8222 Epoch 240/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4184 - accuracy: 0.7709 - val_loss: 0.5719 - val_accuracy: 0.8222 Epoch 241/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4109 - accuracy: 0.8101 - val_loss: 0.5742 - val_accuracy: 0.8222 Epoch 242/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3947 - accuracy: 0.8101 - val_loss: 0.5757 - val_accuracy: 0.8222 Epoch 243/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3727 - accuracy: 0.8324 - val_loss: 0.5779 - val_accuracy: 0.8222 Epoch 244/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4101 - accuracy: 0.8045 - val_loss: 0.5807 - val_accuracy: 0.8222 Epoch 245/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4114 - accuracy: 0.7542 - val_loss: 0.5794 - val_accuracy: 0.8000 Epoch 246/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3948 - accuracy: 0.8101 - val_loss: 0.5795 - val_accuracy: 0.8000 Epoch 247/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3756 - accuracy: 0.7765 - val_loss: 0.5830 - val_accuracy: 0.8000 Epoch 248/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3848 - accuracy: 0.7821 - val_loss: 0.5869 - val_accuracy: 0.8000 Epoch 249/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4159 - accuracy: 0.7542 - val_loss: 0.5894 - val_accuracy: 0.7778 Epoch 250/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3798 - accuracy: 0.7989 - val_loss: 0.5896 - val_accuracy: 0.7778 Epoch 251/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4202 - accuracy: 0.7933 - val_loss: 0.5864 - val_accuracy: 0.8000 Epoch 252/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3738 - accuracy: 0.8212 - val_loss: 0.5852 - val_accuracy: 0.8000 Epoch 253/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3603 - accuracy: 0.8268 - val_loss: 0.5903 - val_accuracy: 0.8000 Epoch 254/500 6/6 [==============================] - 0s 6ms/step - loss: 0.3964 - accuracy: 0.7486 - val_loss: 0.5941 - val_accuracy: 0.8000 Epoch 255/500 6/6 [==============================] - 0s 7ms/step - loss: 0.3604 - accuracy: 0.8324 - val_loss: 0.5970 - val_accuracy: 0.8000 Epoch 256/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3889 - accuracy: 0.7989 - val_loss: 0.5950 - val_accuracy: 0.8000 Epoch 257/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4236 - accuracy: 0.7989 - val_loss: 0.5925 - val_accuracy: 0.8000 Epoch 258/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4185 - accuracy: 0.7989 - val_loss: 0.5894 - val_accuracy: 0.8000 Epoch 259/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4205 - accuracy: 0.7765 - val_loss: 0.5878 - val_accuracy: 0.8000 Epoch 260/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3786 - accuracy: 0.8045 - val_loss: 0.5896 - val_accuracy: 0.8000 Epoch 261/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3379 - accuracy: 0.8268 - val_loss: 0.5928 - val_accuracy: 0.8000 Epoch 262/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3470 - accuracy: 0.8156 - val_loss: 0.5949 - val_accuracy: 0.7778 Epoch 263/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3589 - accuracy: 0.8212 - val_loss: 0.5976 - val_accuracy: 0.7778 Epoch 264/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3871 - accuracy: 0.7933 - val_loss: 0.6018 - val_accuracy: 0.7778 Epoch 265/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3577 - accuracy: 0.7821 - val_loss: 0.6056 - val_accuracy: 0.7778 Epoch 266/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3469 - accuracy: 0.7933 - val_loss: 0.6064 - val_accuracy: 0.7778 Epoch 267/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3895 - accuracy: 0.8045 - val_loss: 0.6056 - val_accuracy: 0.7778 Epoch 268/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3726 - accuracy: 0.8156 - val_loss: 0.6080 - val_accuracy: 0.7778 Epoch 269/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3611 - accuracy: 0.7933 - val_loss: 0.6055 - val_accuracy: 0.7778 Epoch 270/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3880 - accuracy: 0.8380 - val_loss: 0.6038 - val_accuracy: 0.7778 Epoch 271/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3871 - accuracy: 0.8045 - val_loss: 0.6082 - val_accuracy: 0.7778 Epoch 272/500 6/6 [==============================] - 0s 7ms/step - loss: 0.3862 - accuracy: 0.7933 - val_loss: 0.6108 - val_accuracy: 0.8000 Epoch 273/500 6/6 [==============================] - 0s 6ms/step - loss: 0.3473 - accuracy: 0.8268 - val_loss: 0.6142 - val_accuracy: 0.8000 Epoch 274/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3725 - accuracy: 0.8212 - val_loss: 0.6162 - val_accuracy: 0.7778 Epoch 275/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4299 - accuracy: 0.8212 - val_loss: 0.6179 - val_accuracy: 0.7778 Epoch 276/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3701 - accuracy: 0.8436 - val_loss: 0.6160 - val_accuracy: 0.7778 Epoch 277/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3926 - accuracy: 0.7765 - val_loss: 0.6151 - val_accuracy: 0.7778 Epoch 278/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3858 - accuracy: 0.8603 - val_loss: 0.6123 - val_accuracy: 0.8000 Epoch 279/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4025 - accuracy: 0.7542 - val_loss: 0.6105 - val_accuracy: 0.8000 Epoch 280/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3747 - accuracy: 0.8045 - val_loss: 0.6077 - val_accuracy: 0.8000 Epoch 281/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3681 - accuracy: 0.7933 - val_loss: 0.6099 - val_accuracy: 0.8000 Epoch 282/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4073 - accuracy: 0.7877 - val_loss: 0.6095 - val_accuracy: 0.8000 Epoch 283/500 6/6 [==============================] - 0s 4ms/step - loss: 0.4009 - accuracy: 0.8156 - val_loss: 0.6091 - val_accuracy: 0.8000 Epoch 284/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3231 - accuracy: 0.8156 - val_loss: 0.6100 - val_accuracy: 0.7778 Epoch 285/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3796 - accuracy: 0.8101 - val_loss: 0.6125 - val_accuracy: 0.7778 Epoch 286/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3459 - accuracy: 0.8547 - val_loss: 0.6161 - val_accuracy: 0.7778 Epoch 287/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3559 - accuracy: 0.8212 - val_loss: 0.6192 - val_accuracy: 0.7778 Epoch 288/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3405 - accuracy: 0.8380 - val_loss: 0.6188 - val_accuracy: 0.7778 Epoch 289/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3778 - accuracy: 0.8436 - val_loss: 0.6203 - val_accuracy: 0.7778 Epoch 290/500 6/6 [==============================] - 0s 6ms/step - loss: 0.3774 - accuracy: 0.7989 - val_loss: 0.6211 - val_accuracy: 0.7778 Epoch 291/500 6/6 [==============================] - 0s 7ms/step - loss: 0.3261 - accuracy: 0.8715 - val_loss: 0.6247 - val_accuracy: 0.7778 Epoch 292/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3077 - accuracy: 0.8771 - val_loss: 0.6296 - val_accuracy: 0.7778 Epoch 293/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3803 - accuracy: 0.7821 - val_loss: 0.6376 - val_accuracy: 0.7778 Epoch 294/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3153 - accuracy: 0.8492 - val_loss: 0.6426 - val_accuracy: 0.7778 Epoch 295/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3557 - accuracy: 0.7821 - val_loss: 0.6368 - val_accuracy: 0.7778 Epoch 296/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3709 - accuracy: 0.8101 - val_loss: 0.6336 - val_accuracy: 0.7778 Epoch 297/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3167 - accuracy: 0.8380 - val_loss: 0.6336 - val_accuracy: 0.7778 Epoch 298/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3708 - accuracy: 0.7933 - val_loss: 0.6366 - val_accuracy: 0.7778 Epoch 299/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3304 - accuracy: 0.8324 - val_loss: 0.6440 - val_accuracy: 0.7778 Epoch 300/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3206 - accuracy: 0.8547 - val_loss: 0.6519 - val_accuracy: 0.7778 Epoch 301/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3748 - accuracy: 0.7989 - val_loss: 0.6513 - val_accuracy: 0.7778 Epoch 302/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3476 - accuracy: 0.8101 - val_loss: 0.6520 - val_accuracy: 0.7778 Epoch 303/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3101 - accuracy: 0.8715 - val_loss: 0.6525 - val_accuracy: 0.7778 Epoch 304/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3547 - accuracy: 0.8101 - val_loss: 0.6504 - val_accuracy: 0.7778 Epoch 305/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3510 - accuracy: 0.8492 - val_loss: 0.6459 - val_accuracy: 0.7778 Epoch 306/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3876 - accuracy: 0.7821 - val_loss: 0.6452 - val_accuracy: 0.7778 Epoch 307/500 6/6 [==============================] - 0s 3ms/step - loss: 0.3585 - accuracy: 0.8156 - val_loss: 0.6431 - val_accuracy: 0.7778 Epoch 308/500 6/6 [==============================] - 0s 6ms/step - loss: 0.3746 - accuracy: 0.7933 - val_loss: 0.6427 - val_accuracy: 0.7778 Epoch 309/500 6/6 [==============================] - 0s 7ms/step - loss: 0.3184 - accuracy: 0.8436 - val_loss: 0.6413 - val_accuracy: 0.7778 Epoch 310/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3785 - accuracy: 0.8101 - val_loss: 0.6415 - val_accuracy: 0.7778 Epoch 311/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3320 - accuracy: 0.8212 - val_loss: 0.6424 - val_accuracy: 0.7778 Epoch 312/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3235 - accuracy: 0.8436 - val_loss: 0.6438 - val_accuracy: 0.7778 Epoch 313/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3788 - accuracy: 0.7933 - val_loss: 0.6438 - val_accuracy: 0.7778 Epoch 314/500 6/6 [==============================] - 0s 3ms/step - loss: 0.3259 - accuracy: 0.8492 - val_loss: 0.6426 - val_accuracy: 0.7778 Epoch 315/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3357 - accuracy: 0.8212 - val_loss: 0.6476 - val_accuracy: 0.8000 Epoch 316/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3445 - accuracy: 0.8547 - val_loss: 0.6523 - val_accuracy: 0.8000 Epoch 317/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3071 - accuracy: 0.8212 - val_loss: 0.6559 - val_accuracy: 0.8000 Epoch 318/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3792 - accuracy: 0.7877 - val_loss: 0.6490 - val_accuracy: 0.8000 Epoch 319/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3560 - accuracy: 0.8268 - val_loss: 0.6469 - val_accuracy: 0.7778 Epoch 320/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3611 - accuracy: 0.7933 - val_loss: 0.6506 - val_accuracy: 0.7778 Epoch 321/500 6/6 [==============================] - 0s 6ms/step - loss: 0.3620 - accuracy: 0.7877 - val_loss: 0.6546 - val_accuracy: 0.7778 Epoch 322/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3053 - accuracy: 0.8492 - val_loss: 0.6578 - val_accuracy: 0.7778 Epoch 323/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3048 - accuracy: 0.8603 - val_loss: 0.6589 - val_accuracy: 0.7778 Epoch 324/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3653 - accuracy: 0.8212 - val_loss: 0.6521 - val_accuracy: 0.8000 Epoch 325/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3278 - accuracy: 0.8436 - val_loss: 0.6558 - val_accuracy: 0.8000 Epoch 326/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3335 - accuracy: 0.8045 - val_loss: 0.6586 - val_accuracy: 0.8000 Epoch 327/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3409 - accuracy: 0.8045 - val_loss: 0.6636 - val_accuracy: 0.8000 Epoch 328/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2788 - accuracy: 0.8715 - val_loss: 0.6651 - val_accuracy: 0.8000 Epoch 329/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3585 - accuracy: 0.8101 - val_loss: 0.6642 - val_accuracy: 0.8000 Epoch 330/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3564 - accuracy: 0.8324 - val_loss: 0.6684 - val_accuracy: 0.8000 Epoch 331/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3216 - accuracy: 0.8603 - val_loss: 0.6743 - val_accuracy: 0.8000 Epoch 332/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3283 - accuracy: 0.8492 - val_loss: 0.6788 - val_accuracy: 0.8000 Epoch 333/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3359 - accuracy: 0.8212 - val_loss: 0.6848 - val_accuracy: 0.8000 Epoch 334/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3434 - accuracy: 0.8268 - val_loss: 0.6849 - val_accuracy: 0.8000 Epoch 335/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3037 - accuracy: 0.8659 - val_loss: 0.6838 - val_accuracy: 0.8000 Epoch 336/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3205 - accuracy: 0.8212 - val_loss: 0.6824 - val_accuracy: 0.8000 Epoch 337/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3496 - accuracy: 0.8045 - val_loss: 0.6831 - val_accuracy: 0.8000 Epoch 338/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3370 - accuracy: 0.7989 - val_loss: 0.6878 - val_accuracy: 0.8000 Epoch 339/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3417 - accuracy: 0.8492 - val_loss: 0.6919 - val_accuracy: 0.8000 Epoch 340/500 6/6 [==============================] - 0s 9ms/step - loss: 0.3483 - accuracy: 0.8045 - val_loss: 0.6942 - val_accuracy: 0.8000 Epoch 341/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3157 - accuracy: 0.8603 - val_loss: 0.6941 - val_accuracy: 0.8000 Epoch 342/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3371 - accuracy: 0.8101 - val_loss: 0.6891 - val_accuracy: 0.8000 Epoch 343/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2903 - accuracy: 0.8101 - val_loss: 0.6899 - val_accuracy: 0.8000 Epoch 344/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2851 - accuracy: 0.8771 - val_loss: 0.6897 - val_accuracy: 0.8000 Epoch 345/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3424 - accuracy: 0.8268 - val_loss: 0.6953 - val_accuracy: 0.8000 Epoch 346/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2907 - accuracy: 0.8883 - val_loss: 0.6982 - val_accuracy: 0.8000 Epoch 347/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3276 - accuracy: 0.8603 - val_loss: 0.6976 - val_accuracy: 0.8000 Epoch 348/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3539 - accuracy: 0.7933 - val_loss: 0.6958 - val_accuracy: 0.8000 Epoch 349/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3545 - accuracy: 0.8436 - val_loss: 0.7011 - val_accuracy: 0.8000 Epoch 350/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3260 - accuracy: 0.8827 - val_loss: 0.7089 - val_accuracy: 0.8000 Epoch 351/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3666 - accuracy: 0.7821 - val_loss: 0.7149 - val_accuracy: 0.8000 Epoch 352/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3174 - accuracy: 0.7877 - val_loss: 0.7122 - val_accuracy: 0.8000 Epoch 353/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2967 - accuracy: 0.8436 - val_loss: 0.7117 - val_accuracy: 0.8000 Epoch 354/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3049 - accuracy: 0.8436 - val_loss: 0.7200 - val_accuracy: 0.8000 Epoch 355/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3091 - accuracy: 0.8324 - val_loss: 0.7254 - val_accuracy: 0.8000 Epoch 356/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2883 - accuracy: 0.8715 - val_loss: 0.7272 - val_accuracy: 0.8000 Epoch 357/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3418 - accuracy: 0.8380 - val_loss: 0.7301 - val_accuracy: 0.8000 Epoch 358/500 6/6 [==============================] - 0s 6ms/step - loss: 0.3231 - accuracy: 0.8436 - val_loss: 0.7356 - val_accuracy: 0.8000 Epoch 359/500 6/6 [==============================] - 0s 7ms/step - loss: 0.3120 - accuracy: 0.8603 - val_loss: 0.7313 - val_accuracy: 0.8000 Epoch 360/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2750 - accuracy: 0.8771 - val_loss: 0.7319 - val_accuracy: 0.8000 Epoch 361/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3130 - accuracy: 0.8268 - val_loss: 0.7337 - val_accuracy: 0.8000 Epoch 362/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2985 - accuracy: 0.8827 - val_loss: 0.7448 - val_accuracy: 0.8000 Epoch 363/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2880 - accuracy: 0.8380 - val_loss: 0.7525 - val_accuracy: 0.8000 Epoch 364/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3011 - accuracy: 0.8324 - val_loss: 0.7487 - val_accuracy: 0.8000 Epoch 365/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3290 - accuracy: 0.8380 - val_loss: 0.7462 - val_accuracy: 0.8000 Epoch 366/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3145 - accuracy: 0.8771 - val_loss: 0.7444 - val_accuracy: 0.8000 Epoch 367/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3270 - accuracy: 0.8212 - val_loss: 0.7489 - val_accuracy: 0.8000 Epoch 368/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3071 - accuracy: 0.7989 - val_loss: 0.7519 - val_accuracy: 0.8000 Epoch 369/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3253 - accuracy: 0.8324 - val_loss: 0.7566 - val_accuracy: 0.8000 Epoch 370/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3028 - accuracy: 0.8324 - val_loss: 0.7636 - val_accuracy: 0.8000 Epoch 371/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3133 - accuracy: 0.8156 - val_loss: 0.7662 - val_accuracy: 0.8000 Epoch 372/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3350 - accuracy: 0.8268 - val_loss: 0.7673 - val_accuracy: 0.8000 Epoch 373/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3048 - accuracy: 0.8603 - val_loss: 0.7653 - val_accuracy: 0.8000 Epoch 374/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3274 - accuracy: 0.8324 - val_loss: 0.7697 - val_accuracy: 0.8000 Epoch 375/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3067 - accuracy: 0.8603 - val_loss: 0.7761 - val_accuracy: 0.8000 Epoch 376/500 6/6 [==============================] - 0s 7ms/step - loss: 0.3316 - accuracy: 0.7933 - val_loss: 0.7811 - val_accuracy: 0.8000 Epoch 377/500 6/6 [==============================] - 0s 7ms/step - loss: 0.2948 - accuracy: 0.8603 - val_loss: 0.7935 - val_accuracy: 0.8000 Epoch 378/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2846 - accuracy: 0.8715 - val_loss: 0.7973 - val_accuracy: 0.8000 Epoch 379/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2759 - accuracy: 0.8492 - val_loss: 0.7991 - val_accuracy: 0.8000 Epoch 380/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3631 - accuracy: 0.7821 - val_loss: 0.7928 - val_accuracy: 0.8000 Epoch 381/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3236 - accuracy: 0.8380 - val_loss: 0.7877 - val_accuracy: 0.8000 Epoch 382/500 6/6 [==============================] - 0s 3ms/step - loss: 0.3076 - accuracy: 0.8436 - val_loss: 0.7847 - val_accuracy: 0.8000 Epoch 383/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3019 - accuracy: 0.8436 - val_loss: 0.7888 - val_accuracy: 0.8000 Epoch 384/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2827 - accuracy: 0.8436 - val_loss: 0.7920 - val_accuracy: 0.8000 Epoch 385/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2948 - accuracy: 0.8492 - val_loss: 0.7967 - val_accuracy: 0.8000 Epoch 386/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3050 - accuracy: 0.8380 - val_loss: 0.7876 - val_accuracy: 0.8000 Epoch 387/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2812 - accuracy: 0.8715 - val_loss: 0.7837 - val_accuracy: 0.8222 Epoch 388/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2797 - accuracy: 0.8547 - val_loss: 0.7894 - val_accuracy: 0.8222 Epoch 389/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2787 - accuracy: 0.8492 - val_loss: 0.7869 - val_accuracy: 0.8222 Epoch 390/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3471 - accuracy: 0.7877 - val_loss: 0.7811 - val_accuracy: 0.8222 Epoch 391/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3145 - accuracy: 0.8045 - val_loss: 0.7844 - val_accuracy: 0.8222 Epoch 392/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3116 - accuracy: 0.8268 - val_loss: 0.7885 - val_accuracy: 0.8222 Epoch 393/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3168 - accuracy: 0.8492 - val_loss: 0.7934 - val_accuracy: 0.8222 Epoch 394/500 6/6 [==============================] - 0s 6ms/step - loss: 0.3346 - accuracy: 0.7989 - val_loss: 0.8018 - val_accuracy: 0.8222 Epoch 395/500 6/6 [==============================] - 0s 7ms/step - loss: 0.3655 - accuracy: 0.7877 - val_loss: 0.8095 - val_accuracy: 0.8000 Epoch 396/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2802 - accuracy: 0.8715 - val_loss: 0.8097 - val_accuracy: 0.8222 Epoch 397/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2578 - accuracy: 0.8883 - val_loss: 0.8109 - val_accuracy: 0.8222 Epoch 398/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3327 - accuracy: 0.7821 - val_loss: 0.8131 - val_accuracy: 0.8222 Epoch 399/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2826 - accuracy: 0.8380 - val_loss: 0.8171 - val_accuracy: 0.8222 Epoch 400/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3271 - accuracy: 0.7877 - val_loss: 0.8191 - val_accuracy: 0.8222 Epoch 401/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2731 - accuracy: 0.8883 - val_loss: 0.8151 - val_accuracy: 0.8222 Epoch 402/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2886 - accuracy: 0.8547 - val_loss: 0.8155 - val_accuracy: 0.8222 Epoch 403/500 6/6 [==============================] - 0s 3ms/step - loss: 0.2990 - accuracy: 0.8380 - val_loss: 0.8202 - val_accuracy: 0.8222 Epoch 404/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3092 - accuracy: 0.8492 - val_loss: 0.8227 - val_accuracy: 0.8000 Epoch 405/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2970 - accuracy: 0.8380 - val_loss: 0.8299 - val_accuracy: 0.8000 Epoch 406/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3384 - accuracy: 0.8436 - val_loss: 0.8403 - val_accuracy: 0.8000 Epoch 407/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3142 - accuracy: 0.8212 - val_loss: 0.8497 - val_accuracy: 0.8000 Epoch 408/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2298 - accuracy: 0.9162 - val_loss: 0.8603 - val_accuracy: 0.8000 Epoch 409/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2957 - accuracy: 0.8212 - val_loss: 0.8615 - val_accuracy: 0.8000 Epoch 410/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2949 - accuracy: 0.8380 - val_loss: 0.8595 - val_accuracy: 0.8000 Epoch 411/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2885 - accuracy: 0.8436 - val_loss: 0.8554 - val_accuracy: 0.8000 Epoch 412/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2555 - accuracy: 0.8715 - val_loss: 0.8664 - val_accuracy: 0.8000 Epoch 413/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2568 - accuracy: 0.8771 - val_loss: 0.8701 - val_accuracy: 0.8000 Epoch 414/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2807 - accuracy: 0.8324 - val_loss: 0.8653 - val_accuracy: 0.8000 Epoch 415/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3000 - accuracy: 0.8268 - val_loss: 0.8612 - val_accuracy: 0.8000 Epoch 416/500 6/6 [==============================] - 0s 5ms/step - loss: 0.3426 - accuracy: 0.8101 - val_loss: 0.8601 - val_accuracy: 0.8000 Epoch 417/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3116 - accuracy: 0.8101 - val_loss: 0.8702 - val_accuracy: 0.8000 Epoch 418/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2750 - accuracy: 0.8659 - val_loss: 0.8792 - val_accuracy: 0.8000 Epoch 419/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2822 - accuracy: 0.8268 - val_loss: 0.8712 - val_accuracy: 0.8000 Epoch 420/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2855 - accuracy: 0.8212 - val_loss: 0.8691 - val_accuracy: 0.8000 Epoch 421/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3128 - accuracy: 0.8045 - val_loss: 0.8752 - val_accuracy: 0.8000 Epoch 422/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2750 - accuracy: 0.8380 - val_loss: 0.8893 - val_accuracy: 0.8000 Epoch 423/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2693 - accuracy: 0.8939 - val_loss: 0.8987 - val_accuracy: 0.8000 Epoch 424/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2804 - accuracy: 0.8436 - val_loss: 0.9046 - val_accuracy: 0.8000 Epoch 425/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2777 - accuracy: 0.8492 - val_loss: 0.9050 - val_accuracy: 0.8000 Epoch 426/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2976 - accuracy: 0.8380 - val_loss: 0.8977 - val_accuracy: 0.8000 Epoch 427/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2816 - accuracy: 0.8715 - val_loss: 0.9020 - val_accuracy: 0.8000 Epoch 428/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2523 - accuracy: 0.8547 - val_loss: 0.9118 - val_accuracy: 0.8000 Epoch 429/500 6/6 [==============================] - 0s 3ms/step - loss: 0.3126 - accuracy: 0.8324 - val_loss: 0.9061 - val_accuracy: 0.8000 Epoch 430/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3219 - accuracy: 0.8212 - val_loss: 0.8968 - val_accuracy: 0.8000 Epoch 431/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3007 - accuracy: 0.8212 - val_loss: 0.8874 - val_accuracy: 0.8000 Epoch 432/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3149 - accuracy: 0.7989 - val_loss: 0.8838 - val_accuracy: 0.8000 Epoch 433/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3036 - accuracy: 0.8156 - val_loss: 0.8922 - val_accuracy: 0.8000 Epoch 434/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2961 - accuracy: 0.8212 - val_loss: 0.9059 - val_accuracy: 0.8000 Epoch 435/500 6/6 [==============================] - 0s 6ms/step - loss: 0.2976 - accuracy: 0.8212 - val_loss: 0.9146 - val_accuracy: 0.8000 Epoch 436/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3004 - accuracy: 0.8603 - val_loss: 0.9252 - val_accuracy: 0.8000 Epoch 437/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3228 - accuracy: 0.8436 - val_loss: 0.9232 - val_accuracy: 0.8000 Epoch 438/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2785 - accuracy: 0.8268 - val_loss: 0.9207 - val_accuracy: 0.8000 Epoch 439/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3216 - accuracy: 0.8101 - val_loss: 0.9208 - val_accuracy: 0.8000 Epoch 440/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2812 - accuracy: 0.8659 - val_loss: 0.9261 - val_accuracy: 0.8000 Epoch 441/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2919 - accuracy: 0.8324 - val_loss: 0.9273 - val_accuracy: 0.8000 Epoch 442/500 6/6 [==============================] - 0s 3ms/step - loss: 0.2956 - accuracy: 0.8380 - val_loss: 0.9119 - val_accuracy: 0.8000 Epoch 443/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2567 - accuracy: 0.8939 - val_loss: 0.9132 - val_accuracy: 0.8000 Epoch 444/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3015 - accuracy: 0.8436 - val_loss: 0.9235 - val_accuracy: 0.8000 Epoch 445/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2631 - accuracy: 0.8436 - val_loss: 0.9324 - val_accuracy: 0.8000 Epoch 446/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3041 - accuracy: 0.8156 - val_loss: 0.9372 - val_accuracy: 0.8000 Epoch 447/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2737 - accuracy: 0.8715 - val_loss: 0.9452 - val_accuracy: 0.8000 Epoch 448/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3146 - accuracy: 0.8436 - val_loss: 0.9564 - val_accuracy: 0.8000 Epoch 449/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2519 - accuracy: 0.8603 - val_loss: 0.9666 - val_accuracy: 0.8000 Epoch 450/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2818 - accuracy: 0.8380 - val_loss: 0.9534 - val_accuracy: 0.8000 Epoch 451/500 6/6 [==============================] - 0s 3ms/step - loss: 0.3084 - accuracy: 0.8268 - val_loss: 0.9456 - val_accuracy: 0.8000 Epoch 452/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2530 - accuracy: 0.8603 - val_loss: 0.9473 - val_accuracy: 0.8000 Epoch 453/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2664 - accuracy: 0.8659 - val_loss: 0.9523 - val_accuracy: 0.8000 Epoch 454/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2689 - accuracy: 0.8771 - val_loss: 0.9621 - val_accuracy: 0.8000 Epoch 455/500 6/6 [==============================] - 0s 5ms/step - loss: 0.2677 - accuracy: 0.8547 - val_loss: 0.9716 - val_accuracy: 0.8000 Epoch 456/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2866 - accuracy: 0.8492 - val_loss: 0.9667 - val_accuracy: 0.8000 Epoch 457/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2903 - accuracy: 0.8603 - val_loss: 0.9660 - val_accuracy: 0.8000 Epoch 458/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2819 - accuracy: 0.8547 - val_loss: 0.9744 - val_accuracy: 0.8000 Epoch 459/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2899 - accuracy: 0.8547 - val_loss: 0.9785 - val_accuracy: 0.7778 Epoch 460/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2073 - accuracy: 0.9274 - val_loss: 0.9871 - val_accuracy: 0.7778 Epoch 461/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3198 - accuracy: 0.8045 - val_loss: 1.0026 - val_accuracy: 0.8000 Epoch 462/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2670 - accuracy: 0.8547 - val_loss: 1.0124 - val_accuracy: 0.8000 Epoch 463/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2745 - accuracy: 0.8659 - val_loss: 1.0094 - val_accuracy: 0.8000 Epoch 464/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2805 - accuracy: 0.8492 - val_loss: 0.9925 - val_accuracy: 0.8000 Epoch 465/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3154 - accuracy: 0.8324 - val_loss: 0.9870 - val_accuracy: 0.8000 Epoch 466/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2851 - accuracy: 0.8547 - val_loss: 0.9864 - val_accuracy: 0.8000 Epoch 467/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2851 - accuracy: 0.8547 - val_loss: 0.9943 - val_accuracy: 0.8000 Epoch 468/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2863 - accuracy: 0.8380 - val_loss: 1.0032 - val_accuracy: 0.8000 Epoch 469/500 6/6 [==============================] - 0s 3ms/step - loss: 0.2559 - accuracy: 0.8547 - val_loss: 1.0073 - val_accuracy: 0.8000 Epoch 470/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2352 - accuracy: 0.8715 - val_loss: 1.0072 - val_accuracy: 0.8000 Epoch 471/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2748 - accuracy: 0.8492 - val_loss: 0.9994 - val_accuracy: 0.8000 Epoch 472/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2985 - accuracy: 0.8436 - val_loss: 0.9916 - val_accuracy: 0.8000 Epoch 473/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2988 - accuracy: 0.8492 - val_loss: 0.9954 - val_accuracy: 0.8000 Epoch 474/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2994 - accuracy: 0.8268 - val_loss: 1.0109 - val_accuracy: 0.8000 Epoch 475/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2308 - accuracy: 0.8939 - val_loss: 1.0136 - val_accuracy: 0.8000 Epoch 476/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2639 - accuracy: 0.8547 - val_loss: 0.9885 - val_accuracy: 0.8000 Epoch 477/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2835 - accuracy: 0.8380 - val_loss: 0.9789 - val_accuracy: 0.8000 Epoch 478/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2868 - accuracy: 0.8436 - val_loss: 0.9815 - val_accuracy: 0.8000 Epoch 479/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2700 - accuracy: 0.8268 - val_loss: 0.9890 - val_accuracy: 0.8000 Epoch 480/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2936 - accuracy: 0.8268 - val_loss: 0.9994 - val_accuracy: 0.8000 Epoch 481/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2943 - accuracy: 0.8212 - val_loss: 1.0131 - val_accuracy: 0.8000 Epoch 482/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2635 - accuracy: 0.8603 - val_loss: 1.0221 - val_accuracy: 0.8000 Epoch 483/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2715 - accuracy: 0.8436 - val_loss: 1.0171 - val_accuracy: 0.8000 Epoch 484/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3166 - accuracy: 0.7989 - val_loss: 1.0033 - val_accuracy: 0.8000 Epoch 485/500 6/6 [==============================] - 0s 3ms/step - loss: 0.2602 - accuracy: 0.8268 - val_loss: 0.9988 - val_accuracy: 0.8000 Epoch 486/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2707 - accuracy: 0.8939 - val_loss: 1.0088 - val_accuracy: 0.8000 Epoch 487/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2292 - accuracy: 0.9106 - val_loss: 1.0247 - val_accuracy: 0.8000 Epoch 488/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3064 - accuracy: 0.8324 - val_loss: 1.0442 - val_accuracy: 0.8000 Epoch 489/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2386 - accuracy: 0.8883 - val_loss: 1.0420 - val_accuracy: 0.8000 Epoch 490/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2771 - accuracy: 0.8659 - val_loss: 1.0393 - val_accuracy: 0.8000 Epoch 491/500 6/6 [==============================] - 0s 4ms/step - loss: 0.3239 - accuracy: 0.8045 - val_loss: 1.0436 - val_accuracy: 0.8000 Epoch 492/500 6/6 [==============================] - 0s 3ms/step - loss: 0.2987 - accuracy: 0.8268 - val_loss: 1.0475 - val_accuracy: 0.8000 Epoch 493/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2980 - accuracy: 0.8268 - val_loss: 1.0431 - val_accuracy: 0.8000 Epoch 494/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2384 - accuracy: 0.8771 - val_loss: 1.0396 - val_accuracy: 0.8000 Epoch 495/500 6/6 [==============================] - 0s 5ms/step - loss: 0.2721 - accuracy: 0.8547 - val_loss: 1.0377 - val_accuracy: 0.8000 Epoch 496/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2154 - accuracy: 0.8827 - val_loss: 1.0369 - val_accuracy: 0.8000 Epoch 497/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2815 - accuracy: 0.8268 - val_loss: 1.0419 - val_accuracy: 0.8000 Epoch 498/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2632 - accuracy: 0.8436 - val_loss: 1.0445 - val_accuracy: 0.8000 Epoch 499/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2937 - accuracy: 0.8380 - val_loss: 1.0470 - val_accuracy: 0.8000 Epoch 500/500 6/6 [==============================] - 0s 4ms/step - loss: 0.2742 - accuracy: 0.8603 - val_loss: 1.0506 - val_accuracy: 0.8000
In [24]:
val_accuracy = np.mean(history.history['val_accuracy'])
print("\n%s: %.2f%%" % ('val_accuracy', val_accuracy*100))
val_accuracy: 79.81%
In [ ]:
model.summary()
In [25]:
history_df = pd.DataFrame(history.history)
plt.plot(history_df.loc[:, ['loss']], "#6daa9f", label='Training loss')
plt.plot(history_df.loc[:, ['val_loss']],"#774571", label='Validation loss')
plt.title('Training and Validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend(loc="best")
plt.show()
Plotting training and validation accuracy over epochs¶
In [26]:
history_df = pd.DataFrame(history.history)
plt.plot(history_df.loc[:, ['accuracy']], "#6daa9f", label='Training accuracy')
plt.plot(history_df.loc[:, ['val_accuracy']], "#774571", label='Validation accuracy')
plt.title('Training and Validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()
In [27]:
# Predicting the test set results
y_pred = model.predict(X_test)
y_pred = (y_pred > 0.5)
np.set_printoptions()
In [28]:
# confusion matrix
cmap1 = sns.diverging_palette(275,150, s=40, l=65, n=6)
plt.subplots(figsize=(12,8))
cf_matrix = confusion_matrix(y_test, y_pred)
sns.heatmap(cf_matrix/np.sum(cf_matrix), cmap = cmap1, annot = True, annot_kws = {'size':15})
Out[28]:
<AxesSubplot:>
In [29]:
print(classification_report(y_test, y_pred))
precision recall f1-score support
0 0.83 0.88 0.85 57
1 0.53 0.44 0.48 18
accuracy 0.77 75
macro avg 0.68 0.66 0.67 75
weighted avg 0.76 0.77 0.77 75
Saving the model¶
In [30]:
model.save('heart.h5')
deep CC¶
In [31]:
!deepCC heart.h5
[INFO] Reading [keras model] 'heart.h5' [SUCCESS] Saved 'heart_deepC/heart.onnx' [INFO] Reading [onnx model] 'heart_deepC/heart.onnx' [INFO] Model info: ir_vesion : 4 doc : [WARNING] [ONNX]: terminal (input/output) dense_4_input's shape is less than 1. Changing it to 1. [WARNING] [ONNX]: terminal (input/output) dense_7's shape is less than 1. Changing it to 1. WARN (GRAPH): found operator node with the same name (dense_7) as io node. [INFO] Running DNNC graph sanity check ... [SUCCESS] Passed sanity check. [INFO] Writing C++ file 'heart_deepC/heart.cpp' [INFO] deepSea model files are ready in 'heart_deepC/' [RUNNING COMMAND] g++ -std=c++11 -O3 -fno-rtti -fno-exceptions -I. -I/opt/tljh/user/lib/python3.7/site-packages/deepC-0.13-py3.7-linux-x86_64.egg/deepC/include -isystem /opt/tljh/user/lib/python3.7/site-packages/deepC-0.13-py3.7-linux-x86_64.egg/deepC/packages/eigen-eigen-323c052e1731 "heart_deepC/heart.cpp" -D_AITS_MAIN -o "heart_deepC/heart.exe" [RUNNING COMMAND] size "heart_deepC/heart.exe" text data bss dec hex filename 121259 2968 760 124987 1e83b heart_deepC/heart.exe [SUCCESS] Saved model as executable "heart_deepC/heart.exe"