在本次作业中,你将使用LSTM实现乐曲生成模型。你可以在作业结束时试听自己创作的音乐。
你将学习:
from __future__ import print_function
import IPython
import sys
from music21 import *
import numpy as np
from grammar import *
from qa import *
from preprocess import *
from music_utils import *
from data_utils import *
from keras.models import load_model, Model
from keras.layers import Dense, Activation, Dropout, Input, LSTM, Reshape, Lambda, RepeatVector
from keras.initializers import glorot_uniform
from keras.utils import to_categorical
from keras.optimizers import Adam
from keras import backend as K
Using TensorFlow backend.
你向专门为你朋友的生日创作一首爵士乐曲。但是,你不了解任何乐器或音乐作品。幸运的是,你懂得深度学习并且可以使用LSTM网络来尝试解决此问题。
你将训练一个网络,根据已表演作品的风格生成新颖的爵士小歌。
你将在爵士乐曲语料库上训练算法。运行下面的单元格以试听训练集中的音频片段:
IPython.display.Audio('./data/30s_seq.mp3')
由于CSDN无法展示音乐,博主就不在此展示了。
我们已经对音乐数据进行了预处理,以根据音乐“value
”呈现音乐数据。你可以将每个“值”视为一个音符,其中包括一个音调和一个持续时间。例如,如果你按下特定的钢琴键0.5秒钟,则你刚刚演奏了一个音符。在音乐理论中,“值”实际上比这复杂得多。具体来说,它还捕获同时演奏多个音符所需的信息。例如,演奏音乐作品时,你可以同时按下两个钢琴键(同时演奏多个音符会产生所谓的“和弦”)。但是我们不需要讨论音乐理论的过多细节。出于此作业的目的,你需要知道的是,我们将获取值的数据集,并将学习RNN模型以生成值序列。
我们的音乐生成系统将使用78个唯一值。运行以下代码以加载原始音乐数据并将其预处理为值。这可能需要几分钟。
X, Y, n_values, indices_values = load_music_utils()
print('shape of X:', X.shape)
print('number of training examples:', X.shape[0])
print('Tx (length of sequence):', X.shape[1])
print('total # of unique values:', n_values)
print('Shape of Y:', Y.shape)
shape of X: (60, 30, 78)
number of training examples: 60
Tx (length of sequence): 30
total # of unique values: 78
Shape of Y: (30, 60, 78)
你刚刚加载了以下内容:
X
:这是维度为
(
m
,
T
x
,
78
)
(m,T_x,78)
(m,Tx,78)的数组。我们有
m
m
m个训练示例,每个训练示例都是
T
x
=
30
T_x=30
Tx=30音乐值的摘要。在每个时间步,输入都是78个不同的可能值之一,表示为one-hot向量。因此,例如,X[i,t,:]
是一个one-hot向量,表示在时间t处第i个示例的值。Y
:本质上与X
相同,但是向左(过去)移了一步。与恐龙作业相似,我们对使用先前值预测下一个值的网络感兴趣,因此,给定
x
⟨
1
⟩
,
…
,
x
⟨
t
⟩
x^{\langle 1\rangle}, \ldots, x^{\langle t \rangle}
x⟨1⟩,…,x⟨t⟩时,我们的序列模型将尝试预测
y
⟨
t
⟩
y^{\langle t \rangle}
y⟨t⟩,然而,"Y"中的数据被重新排序为
(
T
y
,
m
,
78
)
(T_y,m,78)
(Ty,m,78)的维度,其中
T
y
=
T
x
T_y=T_x
Ty=Tx,以方便之后输入到LSTM。n_values
:该数据集中不同值的数量。即78。indices_values
:python字典,映射为0-77的音乐值。这是我们将使用的模型结构。这与你在上一个笔记本中使用的恐龙模型相似,不同之处在于你将用Keras实现它。架构如下:
我们将在更长的音乐片段中随机抽取30个值的片段来训练模型。因此不必费心设置第一个输入 x ⟨ 1 ⟩ = 0 ⃗ x^{\langle 1 \rangle} = \vec{0} x⟨1⟩=0,因为现在大部分代码段都用它来表示恐龙名称的开头。音频开始于一段音乐的中间。我们将每个片段设置为相同的长度 T x = 30 T_x = 30 Tx=30,使得向量化更加容易。
在这一部分中,你将构建和训练一个音乐学习模型。为此,你将需要构建一个模型,该模型采用维度为
(
m
,
T
x
,
78
)
(m,T_x,78)
(m,Tx,78)的X和维度为
(
T
y
,
m
,
78
)
(T_y,m,78)
(Ty,m,78)的Y。我们将使用具有64维隐藏状态的LSTM,设置n_a = 64
。
n_a = 64
这是创建具有多个输入和输出的Keras模型的方法。如果你要构建RNN,即使在测试阶段,整个输入序列 x ⟨ 1 ⟩ , x ⟨ 2 ⟩ , … , x ⟨ T x ⟩ x^{\langle 1 \rangle}, x^{\langle 2 \rangle}, \ldots, x^{\langle T_x \rangle} x⟨1⟩,x⟨2⟩,…,x⟨Tx⟩都是预先给定。例如,如果输入是单词,而输出是标签,则Keras具有简单的内置函数来构建模型。但是,对于序列生成,在测试时我们并不预先知道 x ⟨ t ⟩ x^{\langle t\rangle} x⟨t⟩的所有值;相反,我们使用 x ⟨ t ⟩ = y ⟨ t − 1 ⟩ x^{\langle t\rangle} = y^{\langle t-1 \rangle} x⟨t⟩=y⟨t−1⟩一次生成一个。因此,代码将更加复杂,并且你将需要实现自己的for循环来迭代不同的时间步。
函数djmodel()
将使用for循环调用LSTM层
T
x
T_x
Tx次,并且所有
T
x
T_x
Tx副本都具有相同的权重。即不应该每次都重新初始化权重,
T
x
T_x
Tx步应该具有共享的权重。在Keras中实现可共享权重的网络层的关键步骤是:
我们已经将你需要的层对象定义为全局变量。请运行下一个单元格以创建它们。查看Keras文档以确保你了解这些层是什么:Reshape(), LSTM(), Dense()。
reshapor = Reshape((1, 78)) # Used in Step 2.B of djmodel(), below
LSTM_cell = LSTM(n_a, return_state = True) # Used in Step 2.C
densor = Dense(n_values, activation='softmax') # Used in Step 2.D
现在,reshapor
, LSTM_cell
和 densor
都是层对象,你可以使用它们来实现djmodel()
。为了通过这些层传播Keras张量对象X,使用layer_object(X)
(如果需要多个输入,则使用layer_object([X,Y])
)。例如,reshapor(X)
将通过上面定义的Reshape((1,78))
层传播X。
练习:实现djmodel()
,你需要执行2个步骤:
x = Lambda(lambda x: X[:,t,:])(X)
查看Keras文档以了解其作用。它正在创建一个"临时"或"未命名"函数(lambda函数就是该函数),以提取适当的one-hot向量,并将该函数作为Keras的Layer
对象应用于X。
+ 将x重塑为(1,78)。你可能会发现`reshapor()`层(在下面定义)很有用。
+ 运行x通过LSTM_cell的一个步骤。记住要使用上一步的隐藏状态$a$和单元状态$c$初始化`LSTM_cell`。使用以下格式:
a, _, c = LSTM_cell(input_x, initial_state=[以前的隐藏状态, 以前的单元状态])
+ 使用"densor"通过dense+softmax层传播LSTM输出的激活值。
+ 将预测值添加到"output"列表中
def djmodel(Tx, n_a, n_values):
"""
实现这个模型
参数:
Tx -- 语料库的长度
n_a -- 激活值的数量
n_values -- 音乐数据中唯一数据的数量
返回:
model -- Keras模型实体
"""
# 定义输入数据的维度
X = Input((Tx, n_values))
# 定义a0, 初始化隐藏状态
a0 = Input(shape=(n_a,),name="a0")
c0 = Input(shape=(n_a,),name="c0")
a = a0
c = c0
# 第一步:创建一个空的outputs列表来保存LSTM的所有时间步的输出。
outputs = []
# 第二步:循环
for t in range(Tx):
## 2.A:从X中选择第“t”个时间步向量
x = Lambda(lambda x:X[:, t, :])(X)
## 2.B:使用reshapor来对x进行重构为(1, n_values)
x = reshapor(x)
## 2.C:单步传播
a, _, c = LSTM_cell(x, initial_state=[a, c])
## 2.D:使用densor()应用于LSTM_Cell的隐藏状态输出
out = densor(a)
## 2.E:把预测值添加到"outputs"列表中
outputs.append(out)
# 第三步:创建模型实体
model = Model(inputs=[X, a0, c0], outputs=outputs)
return model
运行以下单元格以定义模型。我们将使用Tx=30
, n_a=64
(LSTM激活的维数)和n_values=78
。该单元可能需要几秒钟才能运行。
model = djmodel(Tx = 30 , n_a = 64, n_values = 78)
WARNING:tensorflow:From d:\vr\virtual_environment\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
现在,你需要编译模型以进行训练。我们将使用Adam优化器和交叉熵熵损失。
opt = Adam(lr=0.01, beta_1=0.9, beta_2=0.999, decay=0.01)
model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
最后,将LSTM的初始状态a0
和c0
初始化为零。
m = 60
a0 = np.zeros((m, n_a))
c0 = np.zeros((m, n_a))
现在让我们拟合模型!由于损失函数希望以每个时间步一个列表项的格式提供“Y”,因此我们需要将“Y”转换为列表。list(Y)
是一个包含30个项的列表,其中每个列表项的维度均为(60,78)。让我们训练100个epoch。这将需要几分钟。
model.fit([X, a0, c0], list(Y), epochs=100)
WARNING:tensorflow:From d:\vr\virtual_environment\lib\site-packages\keras\backend\tensorflow_backend.py:422: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.
Epoch 1/100
60/60 [==============================] - 7s 119ms/step - loss: 125.8104 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0000e+00 - dense_1_accuracy_1: 0.0500 - dense_1_accuracy_2: 0.0333 - dense_1_accuracy_3: 0.0000e+00 - dense_1_accuracy_4: 0.0500 - dense_1_accuracy_5: 0.0500 - dense_1_accuracy_6: 0.0667 - dense_1_accuracy_7: 0.0500 - dense_1_accuracy_8: 0.1167 - dense_1_accuracy_9: 0.1167 - dense_1_accuracy_10: 0.0500 - dense_1_accuracy_11: 0.0500 - dense_1_accuracy_12: 0.0667 - dense_1_accuracy_13: 0.1000 - dense_1_accuracy_14: 0.0500 - dense_1_accuracy_15: 0.0833 - dense_1_accuracy_16: 0.0667 - dense_1_accuracy_17: 0.0000e+00 - dense_1_accuracy_18: 0.0833 - dense_1_accuracy_19: 0.0167 - dense_1_accuracy_20: 0.0500 - dense_1_accuracy_21: 0.0667 - dense_1_accuracy_22: 0.0000e+00 - dense_1_accuracy_23: 0.0667 - dense_1_accuracy_24: 0.0167 - dense_1_accuracy_25: 0.0667 - dense_1_accuracy_26: 0.0167 - dense_1_accuracy_27: 0.0500 - dense_1_accuracy_28: 0.0667 - dense_1_accuracy_29: 0.0000e+00
Epoch 2/100
60/60 [==============================] - 0s 1ms/step - loss: 121.4338 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.1333 - dense_1_accuracy_2: 0.1667 - dense_1_accuracy_3: 0.1333 - dense_1_accuracy_4: 0.1167 - dense_1_accuracy_5: 0.1000 - dense_1_accuracy_6: 0.1000 - dense_1_accuracy_7: 0.0667 - dense_1_accuracy_8: 0.1500 - dense_1_accuracy_9: 0.1000 - dense_1_accuracy_10: 0.0667 - dense_1_accuracy_11: 0.0167 - dense_1_accuracy_12: 0.0833 - dense_1_accuracy_13: 0.0833 - dense_1_accuracy_14: 0.0500 - dense_1_accuracy_15: 0.0833 - dense_1_accuracy_16: 0.1000 - dense_1_accuracy_17: 0.0167 - dense_1_accuracy_18: 0.1000 - dense_1_accuracy_19: 0.0667 - dense_1_accuracy_20: 0.0667 - dense_1_accuracy_21: 0.0500 - dense_1_accuracy_22: 0.0833 - dense_1_accuracy_23: 0.0833 - dense_1_accuracy_24: 0.0167 - dense_1_accuracy_25: 0.1167 - dense_1_accuracy_26: 0.0500 - dense_1_accuracy_27: 0.0667 - dense_1_accuracy_28: 0.0333 - dense_1_accuracy_29: 0.0000e+00
Epoch 3/100
60/60 [==============================] - 0s 1ms/step - loss: 116.7514 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.1333 - dense_1_accuracy_2: 0.1500 - dense_1_accuracy_3: 0.1167 - dense_1_accuracy_4: 0.0833 - dense_1_accuracy_5: 0.0667 - dense_1_accuracy_6: 0.0833 - dense_1_accuracy_7: 0.0667 - dense_1_accuracy_8: 0.1167 - dense_1_accuracy_9: 0.1000 - dense_1_accuracy_10: 0.0667 - dense_1_accuracy_11: 0.0167 - dense_1_accuracy_12: 0.0833 - dense_1_accuracy_13: 0.0833 - dense_1_accuracy_14: 0.0500 - dense_1_accuracy_15: 0.0833 - dense_1_accuracy_16: 0.1000 - dense_1_accuracy_17: 0.0167 - dense_1_accuracy_18: 0.1000 - dense_1_accuracy_19: 0.0667 - dense_1_accuracy_20: 0.0667 - dense_1_accuracy_21: 0.0500 - dense_1_accuracy_22: 0.0833 - dense_1_accuracy_23: 0.0833 - dense_1_accuracy_24: 0.0167 - dense_1_accuracy_25: 0.1167 - dense_1_accuracy_26: 0.0500 - dense_1_accuracy_27: 0.0667 - dense_1_accuracy_28: 0.0333 - dense_1_accuracy_29: 0.0000e+00
Epoch 4/100
60/60 [==============================] - 0s 1ms/step - loss: 112.9043 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0833 - dense_1_accuracy_1: 0.1667 - dense_1_accuracy_2: 0.2000 - dense_1_accuracy_3: 0.1833 - dense_1_accuracy_4: 0.1667 - dense_1_accuracy_5: 0.1167 - dense_1_accuracy_6: 0.1167 - dense_1_accuracy_7: 0.1833 - dense_1_accuracy_8: 0.1167 - dense_1_accuracy_9: 0.1167 - dense_1_accuracy_10: 0.1167 - dense_1_accuracy_11: 0.1000 - dense_1_accuracy_12: 0.0833 - dense_1_accuracy_13: 0.0833 - dense_1_accuracy_14: 0.0667 - dense_1_accuracy_15: 0.1000 - dense_1_accuracy_16: 0.1333 - dense_1_accuracy_17: 0.0833 - dense_1_accuracy_18: 0.0500 - dense_1_accuracy_19: 0.1000 - dense_1_accuracy_20: 0.0833 - dense_1_accuracy_21: 0.0500 - dense_1_accuracy_22: 0.0333 - dense_1_accuracy_23: 0.0167 - dense_1_accuracy_24: 0.1167 - dense_1_accuracy_25: 0.1500 - dense_1_accuracy_26: 0.0500 - dense_1_accuracy_27: 0.1000 - dense_1_accuracy_28: 0.1167 - dense_1_accuracy_29: 0.0000e+00
Epoch 5/100
60/60 [==============================] - 0s 1ms/step - loss: 110.5019 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.1000 - dense_1_accuracy_2: 0.1500 - dense_1_accuracy_3: 0.2167 - dense_1_accuracy_4: 0.2333 - dense_1_accuracy_5: 0.1167 - dense_1_accuracy_6: 0.1000 - dense_1_accuracy_7: 0.2333 - dense_1_accuracy_8: 0.0500 - dense_1_accuracy_9: 0.0333 - dense_1_accuracy_10: 0.1000 - dense_1_accuracy_11: 0.1167 - dense_1_accuracy_12: 0.1167 - dense_1_accuracy_13: 0.1500 - dense_1_accuracy_14: 0.1000 - dense_1_accuracy_15: 0.1000 - dense_1_accuracy_16: 0.1333 - dense_1_accuracy_17: 0.1500 - dense_1_accuracy_18: 0.1000 - dense_1_accuracy_19: 0.0667 - dense_1_accuracy_20: 0.1000 - dense_1_accuracy_21: 0.1000 - dense_1_accuracy_22: 0.0667 - dense_1_accuracy_23: 0.0500 - dense_1_accuracy_24: 0.0833 - dense_1_accuracy_25: 0.1500 - dense_1_accuracy_26: 0.0667 - dense_1_accuracy_27: 0.1500 - dense_1_accuracy_28: 0.1167 - dense_1_accuracy_29: 0.0000e+00
Epoch 6/100
60/60 [==============================] - 0s 1ms/step - loss: 107.8270 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.0667 - dense_1_accuracy_2: 0.1500 - dense_1_accuracy_3: 0.2000 - dense_1_accuracy_4: 0.2167 - dense_1_accuracy_5: 0.1000 - dense_1_accuracy_6: 0.1000 - dense_1_accuracy_7: 0.2167 - dense_1_accuracy_8: 0.0667 - dense_1_accuracy_9: 0.0333 - dense_1_accuracy_10: 0.1000 - dense_1_accuracy_11: 0.1167 - dense_1_accuracy_12: 0.1167 - dense_1_accuracy_13: 0.1333 - dense_1_accuracy_14: 0.1000 - dense_1_accuracy_15: 0.1000 - dense_1_accuracy_16: 0.1000 - dense_1_accuracy_17: 0.1333 - dense_1_accuracy_18: 0.0833 - dense_1_accuracy_19: 0.0667 - dense_1_accuracy_20: 0.0833 - dense_1_accuracy_21: 0.1000 - dense_1_accuracy_22: 0.0500 - dense_1_accuracy_23: 0.1000 - dense_1_accuracy_24: 0.1000 - dense_1_accuracy_25: 0.1667 - dense_1_accuracy_26: 0.1000 - dense_1_accuracy_27: 0.1500 - dense_1_accuracy_28: 0.1667 - dense_1_accuracy_29: 0.0000e+00
Epoch 7/100
60/60 [==============================] - 0s 1ms/step - loss: 104.8190 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.0833 - dense_1_accuracy_2: 0.1667 - dense_1_accuracy_3: 0.2167 - dense_1_accuracy_4: 0.2167 - dense_1_accuracy_5: 0.1333 - dense_1_accuracy_6: 0.1167 - dense_1_accuracy_7: 0.2333 - dense_1_accuracy_8: 0.1000 - dense_1_accuracy_9: 0.0667 - dense_1_accuracy_10: 0.1667 - dense_1_accuracy_11: 0.1167 - dense_1_accuracy_12: 0.1167 - dense_1_accuracy_13: 0.2000 - dense_1_accuracy_14: 0.1167 - dense_1_accuracy_15: 0.1333 - dense_1_accuracy_16: 0.1500 - dense_1_accuracy_17: 0.2000 - dense_1_accuracy_18: 0.1500 - dense_1_accuracy_19: 0.1333 - dense_1_accuracy_20: 0.1333 - dense_1_accuracy_21: 0.1667 - dense_1_accuracy_22: 0.1000 - dense_1_accuracy_23: 0.1500 - dense_1_accuracy_24: 0.1000 - dense_1_accuracy_25: 0.2000 - dense_1_accuracy_26: 0.1333 - dense_1_accuracy_27: 0.1667 - dense_1_accuracy_28: 0.1667 - dense_1_accuracy_29: 0.0000e+00
Epoch 8/100
60/60 [==============================] - 0s 1ms/step - loss: 101.2496 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.0667 - dense_1_accuracy_2: 0.1667 - dense_1_accuracy_3: 0.2167 - dense_1_accuracy_4: 0.2167 - dense_1_accuracy_5: 0.1167 - dense_1_accuracy_6: 0.1333 - dense_1_accuracy_7: 0.2667 - dense_1_accuracy_8: 0.1333 - dense_1_accuracy_9: 0.1167 - dense_1_accuracy_10: 0.1833 - dense_1_accuracy_11: 0.0833 - dense_1_accuracy_12: 0.2833 - dense_1_accuracy_13: 0.2833 - dense_1_accuracy_14: 0.1333 - dense_1_accuracy_15: 0.1667 - dense_1_accuracy_16: 0.2167 - dense_1_accuracy_17: 0.1667 - dense_1_accuracy_18: 0.1667 - dense_1_accuracy_19: 0.1667 - dense_1_accuracy_20: 0.1167 - dense_1_accuracy_21: 0.1000 - dense_1_accuracy_22: 0.1333 - dense_1_accuracy_23: 0.1833 - dense_1_accuracy_24: 0.1167 - dense_1_accuracy_25: 0.1000 - dense_1_accuracy_26: 0.1833 - dense_1_accuracy_27: 0.2500 - dense_1_accuracy_28: 0.1167 - dense_1_accuracy_29: 0.0000e+00
Epoch 9/100
60/60 [==============================] - 0s 1ms/step - loss: 97.0479 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.1000 - dense_1_accuracy_2: 0.1833 - dense_1_accuracy_3: 0.2167 - dense_1_accuracy_4: 0.2167 - dense_1_accuracy_5: 0.1167 - dense_1_accuracy_6: 0.1167 - dense_1_accuracy_7: 0.2500 - dense_1_accuracy_8: 0.1167 - dense_1_accuracy_9: 0.1500 - dense_1_accuracy_10: 0.2000 - dense_1_accuracy_11: 0.1167 - dense_1_accuracy_12: 0.2333 - dense_1_accuracy_13: 0.2667 - dense_1_accuracy_14: 0.2167 - dense_1_accuracy_15: 0.1500 - dense_1_accuracy_16: 0.2333 - dense_1_accuracy_17: 0.1833 - dense_1_accuracy_18: 0.2333 - dense_1_accuracy_19: 0.1833 - dense_1_accuracy_20: 0.1500 - dense_1_accuracy_21: 0.1833 - dense_1_accuracy_22: 0.1667 - dense_1_accuracy_23: 0.2000 - dense_1_accuracy_24: 0.1667 - dense_1_accuracy_25: 0.2500 - dense_1_accuracy_26: 0.1833 - dense_1_accuracy_27: 0.3000 - dense_1_accuracy_28: 0.1167 - dense_1_accuracy_29: 0.0000e+00
Epoch 10/100
60/60 [==============================] - 0s 1ms/step - loss: 93.1729 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.1167 - dense_1_accuracy_2: 0.1667 - dense_1_accuracy_3: 0.2000 - dense_1_accuracy_4: 0.2167 - dense_1_accuracy_5: 0.1500 - dense_1_accuracy_6: 0.1167 - dense_1_accuracy_7: 0.2333 - dense_1_accuracy_8: 0.1667 - dense_1_accuracy_9: 0.1500 - dense_1_accuracy_10: 0.2333 - dense_1_accuracy_11: 0.1500 - dense_1_accuracy_12: 0.2667 - dense_1_accuracy_13: 0.3500 - dense_1_accuracy_14: 0.2500 - dense_1_accuracy_15: 0.1667 - dense_1_accuracy_16: 0.2333 - dense_1_accuracy_17: 0.2000 - dense_1_accuracy_18: 0.2333 - dense_1_accuracy_19: 0.1833 - dense_1_accuracy_20: 0.1500 - dense_1_accuracy_21: 0.2500 - dense_1_accuracy_22: 0.1500 - dense_1_accuracy_23: 0.1833 - dense_1_accuracy_24: 0.1500 - dense_1_accuracy_25: 0.2500 - dense_1_accuracy_26: 0.1833 - dense_1_accuracy_27: 0.2500 - dense_1_accuracy_28: 0.1667 - dense_1_accuracy_29: 0.0000e+00
Epoch 11/100
60/60 [==============================] - 0s 1ms/step - loss: 88.8382 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.1167 - dense_1_accuracy_2: 0.2000 - dense_1_accuracy_3: 0.1667 - dense_1_accuracy_4: 0.2167 - dense_1_accuracy_5: 0.1667 - dense_1_accuracy_6: 0.1500 - dense_1_accuracy_7: 0.2167 - dense_1_accuracy_8: 0.2000 - dense_1_accuracy_9: 0.1667 - dense_1_accuracy_10: 0.2167 - dense_1_accuracy_11: 0.1500 - dense_1_accuracy_12: 0.3167 - dense_1_accuracy_13: 0.3167 - dense_1_accuracy_14: 0.1833 - dense_1_accuracy_15: 0.1833 - dense_1_accuracy_16: 0.3000 - dense_1_accuracy_17: 0.1833 - dense_1_accuracy_18: 0.1667 - dense_1_accuracy_19: 0.2167 - dense_1_accuracy_20: 0.2333 - dense_1_accuracy_21: 0.2333 - dense_1_accuracy_22: 0.1833 - dense_1_accuracy_23: 0.2000 - dense_1_accuracy_24: 0.1333 - dense_1_accuracy_25: 0.2333 - dense_1_accuracy_26: 0.2167 - dense_1_accuracy_27: 0.2333 - dense_1_accuracy_28: 0.1333 - dense_1_accuracy_29: 0.0000e+00
Epoch 12/100
60/60 [==============================] - 0s 1ms/step - loss: 84.4568 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.1167 - dense_1_accuracy_2: 0.2167 - dense_1_accuracy_3: 0.1667 - dense_1_accuracy_4: 0.2167 - dense_1_accuracy_5: 0.1833 - dense_1_accuracy_6: 0.1667 - dense_1_accuracy_7: 0.2833 - dense_1_accuracy_8: 0.2333 - dense_1_accuracy_9: 0.1667 - dense_1_accuracy_10: 0.2667 - dense_1_accuracy_11: 0.1500 - dense_1_accuracy_12: 0.3000 - dense_1_accuracy_13: 0.3500 - dense_1_accuracy_14: 0.2333 - dense_1_accuracy_15: 0.1833 - dense_1_accuracy_16: 0.3000 - dense_1_accuracy_17: 0.1833 - dense_1_accuracy_18: 0.2333 - dense_1_accuracy_19: 0.2167 - dense_1_accuracy_20: 0.2333 - dense_1_accuracy_21: 0.2833 - dense_1_accuracy_22: 0.2667 - dense_1_accuracy_23: 0.1833 - dense_1_accuracy_24: 0.1000 - dense_1_accuracy_25: 0.2667 - dense_1_accuracy_26: 0.2500 - dense_1_accuracy_27: 0.1833 - dense_1_accuracy_28: 0.1833 - dense_1_accuracy_29: 0.0000e+00
Epoch 13/100
60/60 [==============================] - 0s 2ms/step - loss: 80.3870 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.0667 - dense_1_accuracy_1: 0.1500 - dense_1_accuracy_2: 0.2167 - dense_1_accuracy_3: 0.2167 - dense_1_accuracy_4: 0.2333 - dense_1_accuracy_5: 0.1667 - dense_1_accuracy_6: 0.2167 - dense_1_accuracy_7: 0.3167 - dense_1_accuracy_8: 0.2667 - dense_1_accuracy_9: 0.2667 - dense_1_accuracy_10: 0.2833 - dense_1_accuracy_11: 0.2667 - dense_1_accuracy_12: 0.3833 - dense_1_accuracy_13: 0.3833 - dense_1_accuracy_14: 0.2500 - dense_1_accuracy_15: 0.2667 - dense_1_accuracy_16: 0.3333 - dense_1_accuracy_17: 0.2833 - dense_1_accuracy_18: 0.2833 - dense_1_accuracy_19: 0.2667 - dense_1_accuracy_20: 0.2667 - dense_1_accuracy_21: 0.2667 - dense_1_accuracy_22: 0.2833 - dense_1_accuracy_23: 0.2833 - dense_1_accuracy_24: 0.1667 - dense_1_accuracy_25: 0.3333 - dense_1_accuracy_26: 0.1667 - dense_1_accuracy_27: 0.2333 - dense_1_accuracy_28: 0.2333 - dense_1_accuracy_29: 0.0000e+00
Epoch 14/100
60/60 [==============================] - 0s 1ms/step - loss: 76.0954 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.1500 - dense_1_accuracy_2: 0.2167 - dense_1_accuracy_3: 0.2333 - dense_1_accuracy_4: 0.2667 - dense_1_accuracy_5: 0.1500 - dense_1_accuracy_6: 0.2500 - dense_1_accuracy_7: 0.3000 - dense_1_accuracy_8: 0.3333 - dense_1_accuracy_9: 0.3833 - dense_1_accuracy_10: 0.2833 - dense_1_accuracy_11: 0.3000 - dense_1_accuracy_12: 0.4500 - dense_1_accuracy_13: 0.4833 - dense_1_accuracy_14: 0.2833 - dense_1_accuracy_15: 0.3500 - dense_1_accuracy_16: 0.3500 - dense_1_accuracy_17: 0.3000 - dense_1_accuracy_18: 0.3667 - dense_1_accuracy_19: 0.3333 - dense_1_accuracy_20: 0.3000 - dense_1_accuracy_21: 0.3833 - dense_1_accuracy_22: 0.2833 - dense_1_accuracy_23: 0.3667 - dense_1_accuracy_24: 0.2167 - dense_1_accuracy_25: 0.3167 - dense_1_accuracy_26: 0.2833 - dense_1_accuracy_27: 0.3667 - dense_1_accuracy_28: 0.2833 - dense_1_accuracy_29: 0.0000e+00
Epoch 15/100
60/60 [==============================] - 0s 1ms/step - loss: 72.4746 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.1833 - dense_1_accuracy_2: 0.2500 - dense_1_accuracy_3: 0.2333 - dense_1_accuracy_4: 0.2833 - dense_1_accuracy_5: 0.2000 - dense_1_accuracy_6: 0.2500 - dense_1_accuracy_7: 0.3167 - dense_1_accuracy_8: 0.4500 - dense_1_accuracy_9: 0.4500 - dense_1_accuracy_10: 0.3500 - dense_1_accuracy_11: 0.3833 - dense_1_accuracy_12: 0.4000 - dense_1_accuracy_13: 0.4667 - dense_1_accuracy_14: 0.2833 - dense_1_accuracy_15: 0.3667 - dense_1_accuracy_16: 0.3833 - dense_1_accuracy_17: 0.4000 - dense_1_accuracy_18: 0.4000 - dense_1_accuracy_19: 0.3167 - dense_1_accuracy_20: 0.3167 - dense_1_accuracy_21: 0.5000 - dense_1_accuracy_22: 0.3833 - dense_1_accuracy_23: 0.4500 - dense_1_accuracy_24: 0.3333 - dense_1_accuracy_25: 0.3667 - dense_1_accuracy_26: 0.4000 - dense_1_accuracy_27: 0.3833 - dense_1_accuracy_28: 0.3833 - dense_1_accuracy_29: 0.0000e+00
Epoch 16/100
60/60 [==============================] - 0s 1ms/step - loss: 68.5501 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.1833 - dense_1_accuracy_2: 0.2500 - dense_1_accuracy_3: 0.2667 - dense_1_accuracy_4: 0.3000 - dense_1_accuracy_5: 0.3000 - dense_1_accuracy_6: 0.2833 - dense_1_accuracy_7: 0.3333 - dense_1_accuracy_8: 0.4000 - dense_1_accuracy_9: 0.4000 - dense_1_accuracy_10: 0.3667 - dense_1_accuracy_11: 0.4333 - dense_1_accuracy_12: 0.4500 - dense_1_accuracy_13: 0.5667 - dense_1_accuracy_14: 0.2833 - dense_1_accuracy_15: 0.3500 - dense_1_accuracy_16: 0.4167 - dense_1_accuracy_17: 0.4500 - dense_1_accuracy_18: 0.5167 - dense_1_accuracy_19: 0.4333 - dense_1_accuracy_20: 0.3667 - dense_1_accuracy_21: 0.4833 - dense_1_accuracy_22: 0.4167 - dense_1_accuracy_23: 0.3500 - dense_1_accuracy_24: 0.3000 - dense_1_accuracy_25: 0.4333 - dense_1_accuracy_26: 0.3667 - dense_1_accuracy_27: 0.3500 - dense_1_accuracy_28: 0.3333 - dense_1_accuracy_29: 0.0000e+00
Epoch 17/100
60/60 [==============================] - 0s 1ms/step - loss: 65.0331 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.1833 - dense_1_accuracy_2: 0.2833 - dense_1_accuracy_3: 0.2833 - dense_1_accuracy_4: 0.3333 - dense_1_accuracy_5: 0.3333 - dense_1_accuracy_6: 0.3333 - dense_1_accuracy_7: 0.3333 - dense_1_accuracy_8: 0.4833 - dense_1_accuracy_9: 0.4333 - dense_1_accuracy_10: 0.4500 - dense_1_accuracy_11: 0.4333 - dense_1_accuracy_12: 0.4667 - dense_1_accuracy_13: 0.5667 - dense_1_accuracy_14: 0.4000 - dense_1_accuracy_15: 0.4000 - dense_1_accuracy_16: 0.5000 - dense_1_accuracy_17: 0.5000 - dense_1_accuracy_18: 0.4833 - dense_1_accuracy_19: 0.4500 - dense_1_accuracy_20: 0.4333 - dense_1_accuracy_21: 0.6000 - dense_1_accuracy_22: 0.4500 - dense_1_accuracy_23: 0.4333 - dense_1_accuracy_24: 0.3167 - dense_1_accuracy_25: 0.4500 - dense_1_accuracy_26: 0.4500 - dense_1_accuracy_27: 0.4667 - dense_1_accuracy_28: 0.4000 - dense_1_accuracy_29: 0.0000e+00
Epoch 18/100
60/60 [==============================] - 0s 1ms/step - loss: 61.6549 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.2000 - dense_1_accuracy_2: 0.3167 - dense_1_accuracy_3: 0.3000 - dense_1_accuracy_4: 0.3500 - dense_1_accuracy_5: 0.3833 - dense_1_accuracy_6: 0.3833 - dense_1_accuracy_7: 0.4500 - dense_1_accuracy_8: 0.4167 - dense_1_accuracy_9: 0.4500 - dense_1_accuracy_10: 0.4833 - dense_1_accuracy_11: 0.4333 - dense_1_accuracy_12: 0.4333 - dense_1_accuracy_13: 0.6000 - dense_1_accuracy_14: 0.3833 - dense_1_accuracy_15: 0.4667 - dense_1_accuracy_16: 0.4333 - dense_1_accuracy_17: 0.5000 - dense_1_accuracy_18: 0.5500 - dense_1_accuracy_19: 0.4833 - dense_1_accuracy_20: 0.4333 - dense_1_accuracy_21: 0.7167 - dense_1_accuracy_22: 0.5333 - dense_1_accuracy_23: 0.4667 - dense_1_accuracy_24: 0.3667 - dense_1_accuracy_25: 0.5000 - dense_1_accuracy_26: 0.4500 - dense_1_accuracy_27: 0.5333 - dense_1_accuracy_28: 0.5000 - dense_1_accuracy_29: 0.0000e+00
Epoch 19/100
60/60 [==============================] - 0s 1ms/step - loss: 58.4755 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.2000 - dense_1_accuracy_2: 0.3500 - dense_1_accuracy_3: 0.3333 - dense_1_accuracy_4: 0.3333 - dense_1_accuracy_5: 0.4000 - dense_1_accuracy_6: 0.5000 - dense_1_accuracy_7: 0.5167 - dense_1_accuracy_8: 0.5333 - dense_1_accuracy_9: 0.5833 - dense_1_accuracy_10: 0.5000 - dense_1_accuracy_11: 0.5333 - dense_1_accuracy_12: 0.5333 - dense_1_accuracy_13: 0.5833 - dense_1_accuracy_14: 0.4000 - dense_1_accuracy_15: 0.4500 - dense_1_accuracy_16: 0.4667 - dense_1_accuracy_17: 0.5333 - dense_1_accuracy_18: 0.5500 - dense_1_accuracy_19: 0.5333 - dense_1_accuracy_20: 0.5333 - dense_1_accuracy_21: 0.6667 - dense_1_accuracy_22: 0.4667 - dense_1_accuracy_23: 0.5333 - dense_1_accuracy_24: 0.4167 - dense_1_accuracy_25: 0.6333 - dense_1_accuracy_26: 0.5667 - dense_1_accuracy_27: 0.5833 - dense_1_accuracy_28: 0.6500 - dense_1_accuracy_29: 0.0000e+00
Epoch 20/100
60/60 [==============================] - 0s 1ms/step - loss: 55.3904 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.2167 - dense_1_accuracy_2: 0.3500 - dense_1_accuracy_3: 0.3333 - dense_1_accuracy_4: 0.3333 - dense_1_accuracy_5: 0.4833 - dense_1_accuracy_6: 0.5500 - dense_1_accuracy_7: 0.5333 - dense_1_accuracy_8: 0.6667 - dense_1_accuracy_9: 0.6000 - dense_1_accuracy_10: 0.5667 - dense_1_accuracy_11: 0.5500 - dense_1_accuracy_12: 0.6500 - dense_1_accuracy_13: 0.6333 - dense_1_accuracy_14: 0.4833 - dense_1_accuracy_15: 0.4833 - dense_1_accuracy_16: 0.5333 - dense_1_accuracy_17: 0.6333 - dense_1_accuracy_18: 0.5500 - dense_1_accuracy_19: 0.5333 - dense_1_accuracy_20: 0.5667 - dense_1_accuracy_21: 0.6333 - dense_1_accuracy_22: 0.5833 - dense_1_accuracy_23: 0.4333 - dense_1_accuracy_24: 0.4833 - dense_1_accuracy_25: 0.6167 - dense_1_accuracy_26: 0.5333 - dense_1_accuracy_27: 0.6000 - dense_1_accuracy_28: 0.6167 - dense_1_accuracy_29: 0.0000e+00
Epoch 21/100
60/60 [==============================] - 0s 1ms/step - loss: 52.4564 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.2667 - dense_1_accuracy_2: 0.3667 - dense_1_accuracy_3: 0.3000 - dense_1_accuracy_4: 0.3500 - dense_1_accuracy_5: 0.5500 - dense_1_accuracy_6: 0.6167 - dense_1_accuracy_7: 0.5833 - dense_1_accuracy_8: 0.6833 - dense_1_accuracy_9: 0.6833 - dense_1_accuracy_10: 0.6167 - dense_1_accuracy_11: 0.5833 - dense_1_accuracy_12: 0.6833 - dense_1_accuracy_13: 0.6167 - dense_1_accuracy_14: 0.5000 - dense_1_accuracy_15: 0.5000 - dense_1_accuracy_16: 0.5333 - dense_1_accuracy_17: 0.6000 - dense_1_accuracy_18: 0.5667 - dense_1_accuracy_19: 0.5667 - dense_1_accuracy_20: 0.7167 - dense_1_accuracy_21: 0.6833 - dense_1_accuracy_22: 0.6500 - dense_1_accuracy_23: 0.5833 - dense_1_accuracy_24: 0.5500 - dense_1_accuracy_25: 0.7000 - dense_1_accuracy_26: 0.5833 - dense_1_accuracy_27: 0.6667 - dense_1_accuracy_28: 0.7000 - dense_1_accuracy_29: 0.0000e+00
Epoch 22/100
60/60 [==============================] - 0s 1ms/step - loss: 49.6620 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.2833 - dense_1_accuracy_2: 0.3667 - dense_1_accuracy_3: 0.3167 - dense_1_accuracy_4: 0.3667 - dense_1_accuracy_5: 0.6167 - dense_1_accuracy_6: 0.6333 - dense_1_accuracy_7: 0.6000 - dense_1_accuracy_8: 0.7167 - dense_1_accuracy_9: 0.6667 - dense_1_accuracy_10: 0.6167 - dense_1_accuracy_11: 0.6667 - dense_1_accuracy_12: 0.7167 - dense_1_accuracy_13: 0.6500 - dense_1_accuracy_14: 0.5500 - dense_1_accuracy_15: 0.6333 - dense_1_accuracy_16: 0.6500 - dense_1_accuracy_17: 0.6333 - dense_1_accuracy_18: 0.7000 - dense_1_accuracy_19: 0.6667 - dense_1_accuracy_20: 0.6833 - dense_1_accuracy_21: 0.7167 - dense_1_accuracy_22: 0.6500 - dense_1_accuracy_23: 0.6667 - dense_1_accuracy_24: 0.5667 - dense_1_accuracy_25: 0.7167 - dense_1_accuracy_26: 0.6500 - dense_1_accuracy_27: 0.6833 - dense_1_accuracy_28: 0.7333 - dense_1_accuracy_29: 0.0000e+00
Epoch 23/100
60/60 [==============================] - 0s 1ms/step - loss: 46.9174 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3000 - dense_1_accuracy_2: 0.3667 - dense_1_accuracy_3: 0.3000 - dense_1_accuracy_4: 0.3833 - dense_1_accuracy_5: 0.5833 - dense_1_accuracy_6: 0.6500 - dense_1_accuracy_7: 0.6333 - dense_1_accuracy_8: 0.7333 - dense_1_accuracy_9: 0.7333 - dense_1_accuracy_10: 0.6667 - dense_1_accuracy_11: 0.7000 - dense_1_accuracy_12: 0.7667 - dense_1_accuracy_13: 0.6667 - dense_1_accuracy_14: 0.6000 - dense_1_accuracy_15: 0.6833 - dense_1_accuracy_16: 0.6667 - dense_1_accuracy_17: 0.7500 - dense_1_accuracy_18: 0.7167 - dense_1_accuracy_19: 0.6167 - dense_1_accuracy_20: 0.7000 - dense_1_accuracy_21: 0.7333 - dense_1_accuracy_22: 0.6500 - dense_1_accuracy_23: 0.7000 - dense_1_accuracy_24: 0.6000 - dense_1_accuracy_25: 0.7333 - dense_1_accuracy_26: 0.6500 - dense_1_accuracy_27: 0.7667 - dense_1_accuracy_28: 0.7333 - dense_1_accuracy_29: 0.0000e+00
Epoch 24/100
60/60 [==============================] - 0s 1ms/step - loss: 44.3451 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3500 - dense_1_accuracy_2: 0.3500 - dense_1_accuracy_3: 0.3167 - dense_1_accuracy_4: 0.4167 - dense_1_accuracy_5: 0.6500 - dense_1_accuracy_6: 0.7000 - dense_1_accuracy_7: 0.7000 - dense_1_accuracy_8: 0.7833 - dense_1_accuracy_9: 0.7333 - dense_1_accuracy_10: 0.6833 - dense_1_accuracy_11: 0.7333 - dense_1_accuracy_12: 0.7833 - dense_1_accuracy_13: 0.6667 - dense_1_accuracy_14: 0.6833 - dense_1_accuracy_15: 0.7167 - dense_1_accuracy_16: 0.7667 - dense_1_accuracy_17: 0.7667 - dense_1_accuracy_18: 0.7500 - dense_1_accuracy_19: 0.7000 - dense_1_accuracy_20: 0.7833 - dense_1_accuracy_21: 0.8000 - dense_1_accuracy_22: 0.8000 - dense_1_accuracy_23: 0.7333 - dense_1_accuracy_24: 0.6833 - dense_1_accuracy_25: 0.8167 - dense_1_accuracy_26: 0.7167 - dense_1_accuracy_27: 0.8000 - dense_1_accuracy_28: 0.7667 - dense_1_accuracy_29: 0.0000e+00
Epoch 25/100
60/60 [==============================] - 0s 1ms/step - loss: 41.9766 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3000 - dense_1_accuracy_2: 0.4167 - dense_1_accuracy_3: 0.3167 - dense_1_accuracy_4: 0.4833 - dense_1_accuracy_5: 0.6667 - dense_1_accuracy_6: 0.7167 - dense_1_accuracy_7: 0.7333 - dense_1_accuracy_8: 0.7833 - dense_1_accuracy_9: 0.7167 - dense_1_accuracy_10: 0.7000 - dense_1_accuracy_11: 0.7333 - dense_1_accuracy_12: 0.8333 - dense_1_accuracy_13: 0.8667 - dense_1_accuracy_14: 0.7333 - dense_1_accuracy_15: 0.7167 - dense_1_accuracy_16: 0.7667 - dense_1_accuracy_17: 0.8167 - dense_1_accuracy_18: 0.8000 - dense_1_accuracy_19: 0.7500 - dense_1_accuracy_20: 0.8333 - dense_1_accuracy_21: 0.7667 - dense_1_accuracy_22: 0.8000 - dense_1_accuracy_23: 0.7833 - dense_1_accuracy_24: 0.7833 - dense_1_accuracy_25: 0.8167 - dense_1_accuracy_26: 0.6833 - dense_1_accuracy_27: 0.8667 - dense_1_accuracy_28: 0.8333 - dense_1_accuracy_29: 0.0000e+00
Epoch 26/100
60/60 [==============================] - 0s 1ms/step - loss: 39.5593 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3167 - dense_1_accuracy_2: 0.4333 - dense_1_accuracy_3: 0.3833 - dense_1_accuracy_4: 0.5000 - dense_1_accuracy_5: 0.7000 - dense_1_accuracy_6: 0.8500 - dense_1_accuracy_7: 0.7167 - dense_1_accuracy_8: 0.7833 - dense_1_accuracy_9: 0.7833 - dense_1_accuracy_10: 0.7333 - dense_1_accuracy_11: 0.7500 - dense_1_accuracy_12: 0.8667 - dense_1_accuracy_13: 0.9000 - dense_1_accuracy_14: 0.8000 - dense_1_accuracy_15: 0.7833 - dense_1_accuracy_16: 0.8833 - dense_1_accuracy_17: 0.8000 - dense_1_accuracy_18: 0.8500 - dense_1_accuracy_19: 0.8500 - dense_1_accuracy_20: 0.9000 - dense_1_accuracy_21: 0.8333 - dense_1_accuracy_22: 0.8500 - dense_1_accuracy_23: 0.8167 - dense_1_accuracy_24: 0.8167 - dense_1_accuracy_25: 0.8333 - dense_1_accuracy_26: 0.7833 - dense_1_accuracy_27: 0.8833 - dense_1_accuracy_28: 0.8333 - dense_1_accuracy_29: 0.0000e+00
Epoch 27/100
60/60 [==============================] - 0s 1ms/step - loss: 37.3176 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3333 - dense_1_accuracy_2: 0.4833 - dense_1_accuracy_3: 0.4167 - dense_1_accuracy_4: 0.5833 - dense_1_accuracy_5: 0.7500 - dense_1_accuracy_6: 0.8500 - dense_1_accuracy_7: 0.7167 - dense_1_accuracy_8: 0.8000 - dense_1_accuracy_9: 0.8333 - dense_1_accuracy_10: 0.7667 - dense_1_accuracy_11: 0.7833 - dense_1_accuracy_12: 0.9000 - dense_1_accuracy_13: 0.9333 - dense_1_accuracy_14: 0.8667 - dense_1_accuracy_15: 0.8500 - dense_1_accuracy_16: 0.9000 - dense_1_accuracy_17: 0.8833 - dense_1_accuracy_18: 0.8333 - dense_1_accuracy_19: 0.8500 - dense_1_accuracy_20: 0.9167 - dense_1_accuracy_21: 0.9000 - dense_1_accuracy_22: 0.9000 - dense_1_accuracy_23: 0.8333 - dense_1_accuracy_24: 0.8500 - dense_1_accuracy_25: 0.8167 - dense_1_accuracy_26: 0.8000 - dense_1_accuracy_27: 0.9000 - dense_1_accuracy_28: 0.8667 - dense_1_accuracy_29: 0.0000e+00
Epoch 28/100
60/60 [==============================] - 0s 1ms/step - loss: 35.2965 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3333 - dense_1_accuracy_2: 0.5000 - dense_1_accuracy_3: 0.4500 - dense_1_accuracy_4: 0.5833 - dense_1_accuracy_5: 0.7667 - dense_1_accuracy_6: 0.8500 - dense_1_accuracy_7: 0.7167 - dense_1_accuracy_8: 0.8167 - dense_1_accuracy_9: 0.8667 - dense_1_accuracy_10: 0.8000 - dense_1_accuracy_11: 0.8333 - dense_1_accuracy_12: 0.9167 - dense_1_accuracy_13: 0.9500 - dense_1_accuracy_14: 0.9000 - dense_1_accuracy_15: 0.8833 - dense_1_accuracy_16: 0.9500 - dense_1_accuracy_17: 0.9000 - dense_1_accuracy_18: 0.8500 - dense_1_accuracy_19: 0.8667 - dense_1_accuracy_20: 0.9167 - dense_1_accuracy_21: 0.9167 - dense_1_accuracy_22: 0.9167 - dense_1_accuracy_23: 0.8833 - dense_1_accuracy_24: 0.8833 - dense_1_accuracy_25: 0.8500 - dense_1_accuracy_26: 0.8167 - dense_1_accuracy_27: 0.9333 - dense_1_accuracy_28: 0.8833 - dense_1_accuracy_29: 0.0000e+00
Epoch 29/100
60/60 [==============================] - 0s 1ms/step - loss: 33.1478 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3333 - dense_1_accuracy_2: 0.5000 - dense_1_accuracy_3: 0.4500 - dense_1_accuracy_4: 0.6833 - dense_1_accuracy_5: 0.8167 - dense_1_accuracy_6: 0.8667 - dense_1_accuracy_7: 0.7167 - dense_1_accuracy_8: 0.8833 - dense_1_accuracy_9: 0.9167 - dense_1_accuracy_10: 0.9333 - dense_1_accuracy_11: 0.8833 - dense_1_accuracy_12: 0.9500 - dense_1_accuracy_13: 0.9667 - dense_1_accuracy_14: 0.8667 - dense_1_accuracy_15: 0.8833 - dense_1_accuracy_16: 0.9667 - dense_1_accuracy_17: 0.9500 - dense_1_accuracy_18: 0.9167 - dense_1_accuracy_19: 0.9500 - dense_1_accuracy_20: 0.9333 - dense_1_accuracy_21: 0.9667 - dense_1_accuracy_22: 0.9167 - dense_1_accuracy_23: 0.9667 - dense_1_accuracy_24: 0.9833 - dense_1_accuracy_25: 0.9000 - dense_1_accuracy_26: 0.9500 - dense_1_accuracy_27: 0.9500 - dense_1_accuracy_28: 0.9333 - dense_1_accuracy_29: 0.0000e+00
Epoch 30/100
60/60 [==============================] - 0s 1ms/step - loss: 31.2518 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3333 - dense_1_accuracy_2: 0.5167 - dense_1_accuracy_3: 0.5000 - dense_1_accuracy_4: 0.6833 - dense_1_accuracy_5: 0.8833 - dense_1_accuracy_6: 0.9000 - dense_1_accuracy_7: 0.7833 - dense_1_accuracy_8: 0.9000 - dense_1_accuracy_9: 0.9500 - dense_1_accuracy_10: 0.9500 - dense_1_accuracy_11: 0.9167 - dense_1_accuracy_12: 0.9833 - dense_1_accuracy_13: 0.9833 - dense_1_accuracy_14: 0.9500 - dense_1_accuracy_15: 0.9500 - dense_1_accuracy_16: 0.9833 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 0.9667 - dense_1_accuracy_19: 0.9833 - dense_1_accuracy_20: 0.9333 - dense_1_accuracy_21: 0.9667 - dense_1_accuracy_22: 0.9333 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 0.9833 - dense_1_accuracy_25: 0.9500 - dense_1_accuracy_26: 0.9500 - dense_1_accuracy_27: 0.9667 - dense_1_accuracy_28: 0.9500 - dense_1_accuracy_29: 0.0000e+00
Epoch 31/100
60/60 [==============================] - 0s 1ms/step - loss: 29.4504 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3333 - dense_1_accuracy_2: 0.5500 - dense_1_accuracy_3: 0.5500 - dense_1_accuracy_4: 0.7000 - dense_1_accuracy_5: 0.9000 - dense_1_accuracy_6: 0.9167 - dense_1_accuracy_7: 0.8667 - dense_1_accuracy_8: 0.9000 - dense_1_accuracy_9: 0.9333 - dense_1_accuracy_10: 0.9500 - dense_1_accuracy_11: 0.9500 - dense_1_accuracy_12: 0.9833 - dense_1_accuracy_13: 0.9667 - dense_1_accuracy_14: 0.9333 - dense_1_accuracy_15: 0.9667 - dense_1_accuracy_16: 0.9833 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 0.9667 - dense_1_accuracy_19: 0.9833 - dense_1_accuracy_20: 0.9500 - dense_1_accuracy_21: 0.9667 - dense_1_accuracy_22: 0.9833 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 0.9500 - dense_1_accuracy_26: 0.9500 - dense_1_accuracy_27: 0.9667 - dense_1_accuracy_28: 0.9667 - dense_1_accuracy_29: 0.0000e+00
Epoch 32/100
60/60 [==============================] - 0s 1ms/step - loss: 27.6794 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.3667 - dense_1_accuracy_2: 0.5667 - dense_1_accuracy_3: 0.5833 - dense_1_accuracy_4: 0.7333 - dense_1_accuracy_5: 0.9000 - dense_1_accuracy_6: 0.9333 - dense_1_accuracy_7: 0.8833 - dense_1_accuracy_8: 0.9333 - dense_1_accuracy_9: 0.9500 - dense_1_accuracy_10: 0.9500 - dense_1_accuracy_11: 0.9667 - dense_1_accuracy_12: 0.9833 - dense_1_accuracy_13: 0.9833 - dense_1_accuracy_14: 0.9500 - dense_1_accuracy_15: 0.9667 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 0.9833 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 0.9833 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 0.9833 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 0.9833 - dense_1_accuracy_25: 0.9667 - dense_1_accuracy_26: 0.9500 - dense_1_accuracy_27: 0.9667 - dense_1_accuracy_28: 0.9500 - dense_1_accuracy_29: 0.0000e+00
Epoch 33/100
60/60 [==============================] - 0s 1ms/step - loss: 26.0487 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.4000 - dense_1_accuracy_2: 0.6167 - dense_1_accuracy_3: 0.6667 - dense_1_accuracy_4: 0.7833 - dense_1_accuracy_5: 0.9167 - dense_1_accuracy_6: 0.9500 - dense_1_accuracy_7: 0.9000 - dense_1_accuracy_8: 0.9500 - dense_1_accuracy_9: 0.9667 - dense_1_accuracy_10: 0.9833 - dense_1_accuracy_11: 0.9667 - dense_1_accuracy_12: 0.9833 - dense_1_accuracy_13: 0.9833 - dense_1_accuracy_14: 0.9500 - dense_1_accuracy_15: 0.9667 - dense_1_accuracy_16: 0.9833 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 0.9833 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 0.9667 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 0.9833 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 0.9667 - dense_1_accuracy_26: 0.9333 - dense_1_accuracy_27: 0.9667 - dense_1_accuracy_28: 0.9667 - dense_1_accuracy_29: 0.0000e+00
Epoch 34/100
60/60 [==============================] - 0s 1ms/step - loss: 24.5103 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.4000 - dense_1_accuracy_2: 0.6333 - dense_1_accuracy_3: 0.7000 - dense_1_accuracy_4: 0.7833 - dense_1_accuracy_5: 0.9333 - dense_1_accuracy_6: 0.9500 - dense_1_accuracy_7: 0.9167 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 0.9833 - dense_1_accuracy_11: 0.9833 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 0.9833 - dense_1_accuracy_14: 0.9833 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 0.9833 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 0.9833 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 0.9833 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 0.9833 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 0.9833 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9667 - dense_1_accuracy_29: 0.0000e+00
Epoch 35/100
60/60 [==============================] - 0s 1ms/step - loss: 23.1215 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.4333 - dense_1_accuracy_2: 0.7000 - dense_1_accuracy_3: 0.7000 - dense_1_accuracy_4: 0.8500 - dense_1_accuracy_5: 0.9500 - dense_1_accuracy_6: 0.9667 - dense_1_accuracy_7: 0.9333 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 0.9833 - dense_1_accuracy_11: 0.9833 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 0.9833 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 0.9833 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9667 - dense_1_accuracy_29: 0.0000e+00
Epoch 36/100
60/60 [==============================] - 0s 1ms/step - loss: 21.7918 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.4333 - dense_1_accuracy_2: 0.7333 - dense_1_accuracy_3: 0.7167 - dense_1_accuracy_4: 0.8667 - dense_1_accuracy_5: 0.9667 - dense_1_accuracy_6: 0.9500 - dense_1_accuracy_7: 0.9500 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 0.9833 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 0.9833 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9667 - dense_1_accuracy_29: 0.0000e+00
Epoch 37/100
60/60 [==============================] - 0s 1ms/step - loss: 20.5974 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.4167 - dense_1_accuracy_2: 0.7333 - dense_1_accuracy_3: 0.7333 - dense_1_accuracy_4: 0.8833 - dense_1_accuracy_5: 0.9667 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 0.9667 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 0.9833 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 0.9833 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9667 - dense_1_accuracy_29: 0.0000e+00
Epoch 38/100
60/60 [==============================] - 0s 1ms/step - loss: 19.4903 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.4833 - dense_1_accuracy_2: 0.7333 - dense_1_accuracy_3: 0.7333 - dense_1_accuracy_4: 0.8833 - dense_1_accuracy_5: 0.9667 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 0.9833 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 0.9833 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9667 - dense_1_accuracy_29: 0.0000e+00
Epoch 39/100
60/60 [==============================] - 0s 1ms/step - loss: 18.4846 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5000 - dense_1_accuracy_2: 0.7833 - dense_1_accuracy_3: 0.7833 - dense_1_accuracy_4: 0.8833 - dense_1_accuracy_5: 0.9667 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 0.9833 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 0.9833 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9667 - dense_1_accuracy_29: 0.0000e+00
Epoch 40/100
60/60 [==============================] - 0s 1ms/step - loss: 17.5442 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5000 - dense_1_accuracy_2: 0.8000 - dense_1_accuracy_3: 0.8000 - dense_1_accuracy_4: 0.8833 - dense_1_accuracy_5: 0.9833 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 0.9833 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 41/100
60/60 [==============================] - 0s 1ms/step - loss: 16.6850 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5000 - dense_1_accuracy_2: 0.8000 - dense_1_accuracy_3: 0.8000 - dense_1_accuracy_4: 0.9167 - dense_1_accuracy_5: 0.9833 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 0.9833 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 42/100
60/60 [==============================] - 0s 1ms/step - loss: 15.9531 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5000 - dense_1_accuracy_2: 0.8333 - dense_1_accuracy_3: 0.8167 - dense_1_accuracy_4: 0.9333 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 0.9833 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 43/100
60/60 [==============================] - 0s 1ms/step - loss: 15.2606 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5167 - dense_1_accuracy_2: 0.8333 - dense_1_accuracy_3: 0.8500 - dense_1_accuracy_4: 0.9500 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 0.9833 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 44/100
60/60 [==============================] - 0s 1ms/step - loss: 14.6169 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5333 - dense_1_accuracy_2: 0.8333 - dense_1_accuracy_3: 0.8500 - dense_1_accuracy_4: 0.9667 - dense_1_accuracy_5: 0.9833 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 45/100
60/60 [==============================] - 0s 1ms/step - loss: 14.0359 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5333 - dense_1_accuracy_2: 0.8333 - dense_1_accuracy_3: 0.8500 - dense_1_accuracy_4: 0.9667 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 46/100
60/60 [==============================] - 0s 1ms/step - loss: 13.5365 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5333 - dense_1_accuracy_2: 0.8333 - dense_1_accuracy_3: 0.8500 - dense_1_accuracy_4: 0.9667 - dense_1_accuracy_5: 0.9833 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 47/100
60/60 [==============================] - 0s 1ms/step - loss: 13.0739 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5333 - dense_1_accuracy_2: 0.8333 - dense_1_accuracy_3: 0.8500 - dense_1_accuracy_4: 0.9667 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 48/100
60/60 [==============================] - 0s 1ms/step - loss: 12.6324 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5333 - dense_1_accuracy_2: 0.8333 - dense_1_accuracy_3: 0.8667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 49/100
60/60 [==============================] - 0s 1ms/step - loss: 12.2587 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5500 - dense_1_accuracy_2: 0.8333 - dense_1_accuracy_3: 0.8667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 50/100
60/60 [==============================] - 0s 1ms/step - loss: 11.9156 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5500 - dense_1_accuracy_2: 0.8500 - dense_1_accuracy_3: 0.8667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 0.9833 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 51/100
60/60 [==============================] - 0s 1ms/step - loss: 11.6561 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5500 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9000 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 0.9833 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 52/100
60/60 [==============================] - 0s 1ms/step - loss: 11.3376 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5500 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9000 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 53/100
60/60 [==============================] - 0s 1ms/step - loss: 11.0278 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5500 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9000 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 54/100
60/60 [==============================] - 0s 1ms/step - loss: 10.7868 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5500 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9333 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 55/100
60/60 [==============================] - 0s 1ms/step - loss: 10.6172 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.5500 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9333 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 0.9833 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 56/100
60/60 [==============================] - 0s 1ms/step - loss: 10.3823 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6000 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9333 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 57/100
60/60 [==============================] - 0s 1ms/step - loss: 10.1989 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6000 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9500 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 58/100
60/60 [==============================] - 0s 1ms/step - loss: 10.0857 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6000 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9500 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 59/100
60/60 [==============================] - 0s 1ms/step - loss: 9.9101 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6000 - dense_1_accuracy_2: 0.8667 - dense_1_accuracy_3: 0.9667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 60/100
60/60 [==============================] - 0s 1ms/step - loss: 9.7498 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6000 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 61/100
60/60 [==============================] - 0s 1ms/step - loss: 9.5569 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6000 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 62/100
60/60 [==============================] - 0s 1ms/step - loss: 9.5195 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6000 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 63/100
60/60 [==============================] - 0s 1ms/step - loss: 9.3869 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6167 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 64/100
60/60 [==============================] - 0s 1ms/step - loss: 9.2721 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6167 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9667 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 65/100
60/60 [==============================] - 0s 1ms/step - loss: 9.1552 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6167 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 66/100
60/60 [==============================] - 0s 1ms/step - loss: 9.0480 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6167 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 67/100
60/60 [==============================] - 0s 1ms/step - loss: 8.9713 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6167 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 68/100
60/60 [==============================] - 0s 1ms/step - loss: 8.8916 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6167 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 69/100
60/60 [==============================] - 0s 1ms/step - loss: 8.8817 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6167 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 70/100
60/60 [==============================] - 0s 1ms/step - loss: 8.7221 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6167 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 71/100
60/60 [==============================] - 0s 1ms/step - loss: 8.5989 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 72/100
60/60 [==============================] - 0s 1ms/step - loss: 8.6101 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 73/100
60/60 [==============================] - 0s 1ms/step - loss: 8.4869 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 74/100
60/60 [==============================] - 0s 1ms/step - loss: 8.6417 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.8833 - dense_1_accuracy_3: 0.9833 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 0.9833 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 75/100
60/60 [==============================] - 0s 1ms/step - loss: 8.3961 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9000 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 76/100
60/60 [==============================] - 0s 1ms/step - loss: 8.4834 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9000 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 77/100
60/60 [==============================] - 0s 1ms/step - loss: 8.3441 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9000 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 78/100
60/60 [==============================] - 0s 1ms/step - loss: 8.1681 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9000 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 0.9833 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 79/100
60/60 [==============================] - 0s 1ms/step - loss: 8.2874 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9000 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 80/100
60/60 [==============================] - 0s 1ms/step - loss: 8.1880 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9000 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 81/100
60/60 [==============================] - 0s 1ms/step - loss: 8.1446 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9000 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 82/100
60/60 [==============================] - 0s 1ms/step - loss: 8.0556 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9000 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 83/100
60/60 [==============================] - 0s 1ms/step - loss: 7.9504 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 84/100
60/60 [==============================] - 0s 1ms/step - loss: 7.8864 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 85/100
60/60 [==============================] - 0s 1ms/step - loss: 7.8184 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 86/100
60/60 [==============================] - 0s 1ms/step - loss: 8.2067 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6333 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 0.9667 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 87/100
60/60 [==============================] - 0s 1ms/step - loss: 7.6905 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6500 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 88/100
60/60 [==============================] - 0s 1ms/step - loss: 8.3132 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6500 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 0.9833 - dense_1_accuracy_25: 0.9667 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 0.9833 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 89/100
60/60 [==============================] - 0s 1ms/step - loss: 7.8230 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6500 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 90/100
60/60 [==============================] - 0s 1ms/step - loss: 8.0172 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6500 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 91/100
60/60 [==============================] - 0s 1ms/step - loss: 7.5494 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6500 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 0.9833 - dense_1_accuracy_29: 0.0000e+00
Epoch 92/100
60/60 [==============================] - 0s 1ms/step - loss: 8.0109 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6500 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 93/100
60/60 [==============================] - 0s 1ms/step - loss: 7.7035 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6500 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 94/100
60/60 [==============================] - 0s 1ms/step - loss: 7.4847 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6833 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 95/100
60/60 [==============================] - 0s 1ms/step - loss: 7.7454 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6833 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 96/100
60/60 [==============================] - 0s 1ms/step - loss: 7.4569 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6833 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 97/100
60/60 [==============================] - 0s 1ms/step - loss: 7.4972 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6667 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 98/100
60/60 [==============================] - 0s 1ms/step - loss: 7.6047 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6667 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 99/100
60/60 [==============================] - 0s 1ms/step - loss: 7.3447 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.6833 - dense_1_accuracy_2: 0.9167 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
Epoch 100/100
60/60 [==============================] - 0s 1ms/step - loss: 7.4536 - dense_1_loss: 0.0000e+00 - dense_1_accuracy: 0.1000 - dense_1_accuracy_1: 0.7000 - dense_1_accuracy_2: 0.9333 - dense_1_accuracy_3: 1.0000 - dense_1_accuracy_4: 1.0000 - dense_1_accuracy_5: 1.0000 - dense_1_accuracy_6: 1.0000 - dense_1_accuracy_7: 1.0000 - dense_1_accuracy_8: 1.0000 - dense_1_accuracy_9: 1.0000 - dense_1_accuracy_10: 1.0000 - dense_1_accuracy_11: 1.0000 - dense_1_accuracy_12: 1.0000 - dense_1_accuracy_13: 1.0000 - dense_1_accuracy_14: 1.0000 - dense_1_accuracy_15: 1.0000 - dense_1_accuracy_16: 1.0000 - dense_1_accuracy_17: 1.0000 - dense_1_accuracy_18: 1.0000 - dense_1_accuracy_19: 1.0000 - dense_1_accuracy_20: 1.0000 - dense_1_accuracy_21: 1.0000 - dense_1_accuracy_22: 1.0000 - dense_1_accuracy_23: 1.0000 - dense_1_accuracy_24: 1.0000 - dense_1_accuracy_25: 1.0000 - dense_1_accuracy_26: 1.0000 - dense_1_accuracy_27: 1.0000 - dense_1_accuracy_28: 1.0000 - dense_1_accuracy_29: 0.0000e+00
你可以看到模型的损失逐渐减少。现在你已经训练好了一个模型,让我们继续最后一部分以实现推理算法并生成一些乐曲!
你现在拥有一个训练好的模型,该模型已经学习了许多爵士独奏。现在让我们使用此模型来合成新音乐。
在采样的每个步骤中,你将以LSTM先前状态的激活“a”和单元状态“c”作为输入,向前传播一步,并获得新的输出激活以及单元状态。然后,和之前一样使用densor通过新的激活a来生成输出。
首先,我们将初始化x0以及LSTM激活,并将单元值a0和c0初始化为零。
你将要构建一个函数来为你进行此推断。你的函数将采用你先前的模型以及你要采样的时间步长“Ty”。它将返回一个可以为你生成序列的keras模型。此外,该函数包含78个单位的密集层和激活函数。
练习:实现以下函数以采样一系列音乐值。这是在for循环内生成 T y T_y Ty输出字符需要实现的一些关键步骤:
LSTM_Cell
,它输入上一步的“c
”和“a
”来生成当前步骤的“c
”和“a
”。densor
(先前定义)在“a
”上计算softmax,以获取当前步骤的输出。outputs
中并保存。x = Lambda(one_hot)(out)
[说明:这行代码实际上不是使用out
中的概率对值进行随机采样,而是在每个步骤中使用argmax选择最可能的单个注释。]
def music_inference_model(LSTM_cell, densor, n_values = 78, n_a = 64, Ty = 100):
"""
参数:
LSTM_cell -- 来自model()的训练过后的LSTM单元,是keras层对象。
densor -- 来自model()的训练过后的"densor",是keras层对象
n_values -- 整数,唯一值的数量
n_a -- LSTM单元的数量
Ty -- 整数,生成的是时间步的数量
返回:
inference_model -- Kears模型实体
"""
# 定义模型输入的维度
x0 = Input(shape=(1,n_values))
# 定义s0,初始化隐藏状态
a0 = Input(shape=(n_a,),name="a0")
c0 = Input(shape=(n_a,),name="c0")
a = a0
c = c0
x = x0
# 步骤1:创建一个空的outputs列表来保存预测值。
outputs = []
# 步骤2:遍历Ty,生成所有时间步的输出
for t in range(Ty):
# 步骤2.A:在LSTM中单步传播
a, _, c = LSTM_cell(x, initial_state=[a, c])
# 步骤2.B:使用densor()应用于LSTM_Cell的隐藏状态输出
out = densor(a)
# 步骤2.C:预测值添加到"outputs"列表中
outputs.append(out)
# 根据“out”选择下一个值,并将“x”设置为所选值的一个独热编码,
# 该值将在下一步作为输入传递给LSTM_cell。我们已经提供了执行此操作所需的代码
x = Lambda(one_hot)(out)
# 创建模型实体
inference_model = Model(inputs=[x0, a0, c0], outputs=outputs)
return inference_model
# 获取模型实体,模型被硬编码以产生50个值
inference_model = music_inference_model(LSTM_cell, densor, n_values = 78, n_a = 64, Ty = 50)
#创建用于初始化x和LSTM状态变量a和c的零向量。
x_initializer = np.zeros((1, 1, 78))
a_initializer = np.zeros((1, n_a))
c_initializer = np.zeros((1, n_a))
练习:实现predict_and_sample()
。此函数接受许多参数,包括输入[x_initializer, a_initializer, c_initializer]。为了预测与此输入相对应的输出,你将需要执行3个步骤:
pred
应该是长度为20的列表,其中每个元素都是一个形状为
(
T
y
,
n
_
v
a
l
u
e
s
)
(T_y,n\_values)
(Ty,n_values)的numpy数组。pred
转换为
T
y
T_y
Ty索引的numpy数组。通过使用pred
列表中元素的argmax
来计算每个对应的索引。Hintdef predict_and_sample(inference_model, x_initializer = x_initializer, a_initializer = a_initializer,
c_initializer = c_initializer):
"""
使用模型预测当前值的下一个值。
参数:
inference_model -- keras的实体模型
x_initializer -- 初始化的独热编码,维度为(1, 1, 78)
a_initializer -- LSTM单元的隐藏状态初始化,维度为(1, n_a)
c_initializer -- LSTM单元的状态初始化,维度为(1, n_a)
返回:
results -- 生成值的独热编码向量,维度为(Ty, 78)
indices -- 所生成值的索引矩阵,维度为(Ty, 1)
"""
# 步骤1:模型来预测给定x_initializer, a_initializer and c_initializer的输出序列
pred = inference_model.predict([x_initializer, a_initializer, c_initializer])
# 步骤2:将“pred”转换为具有最大概率的索引数组np.array()。
indices = np.argmax(pred, axis=-1)
# 步骤3:将索引转换为它们的一个独热编码。
results = to_categorical(indices, num_classes=78)
return results, indices
results, indices = predict_and_sample(inference_model, x_initializer, a_initializer, c_initializer)
print("np.argmax(results[12]) =", np.argmax(results[12]))
print("np.argmax(results[17]) =", np.argmax(results[17]))
print("list(indices[12:18]) =", list(indices[12:18]))
np.argmax(results[12]) = 62
np.argmax(results[17]) = 30
list(indices[12:18]) = [array([62], dtype=int64), array([30], dtype=int64), array([64], dtype=int64), array([33], dtype=int64), array([62], dtype=int64), array([30], dtype=int64)]
最后,你准备好生成音乐了。你的RNN会生成一个值序列。以下代码首先通过调用你的predict_and_sample()
函数来生成音乐。然后,将这些值后期处理为和弦(意味着可以同时演奏多个值或音符)。
大多数计算音乐算法都使用某些后期处理,因为没有这种后期处理很难生成听起来不错的音乐。后期处理通过诸如确保相同的声音不会重复太多,两个连续的音符彼此之间的音高相距不远等来处理生成的音频。可能有人争辩说,这些后期处理步骤中有很多都是黑客。同样,很多音乐生成文学也集中于手工制作后处理器,并且许多输出质量取决于后期处理的质量,而不仅仅是RNN的质量。但是这种后期处理的确有很大的不同,因此在我们的实现中也试着使用它。
让我们开始尝试制作音乐吧!
运行以下单元格来生成音乐并将其记录到你的out_stream
中。这可能需要几分钟。
out_stream = generate_music(inference_model)
Predicting new values for different set of chords.
Generated 50 sounds using the predicted values for the set of chords ("1") and after pruning
Generated 50 sounds using the predicted values for the set of chords ("2") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("3") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("4") and after pruning
Generated 51 sounds using the predicted values for the set of chords ("5") and after pruning
Your generated music is saved in output/my_music.midi
要试听音乐,请单击File->Open…,然后转到"output/" 并下载 “my_music.midi”。你可以使用可读取Midi文件的应用程序在计算机上播放该文件,也可以使用免费在线转换工具"MIDI to mp3"将其转换为mp3。
作为参考,下面我们使用此算法生成的30秒音频剪辑。
IPython.display.Audio('./data/30s_trained_model.mp3')
由于CSDN无法展示音乐,博主就不在此展示了。
这是你应该记住的: