杰jie
杰jie

【哈工大版】动态ReLU：Adaptively Parametric ReLU（调参记录14）

Adaptively Parametric ReLU是一种动态ReLU（Dynamic ReLU），在2019年5月3日投稿至IEEE Transactions on Industrial Electronics，2020年1月24日录用， 2020年2月13日在IEEE官网公布。

这次再尝试解决过拟合，把残差模块的数量减少到2个，Adaptively Parametric ReLU里面第一个全连接层的权重数量，减少为之前的1/8，批量大小设置为1000（主要是为了省时间）。

Adaptively Parametric ReLU激活函数的基本原理如下：
【哈工大版】动态ReLU：Adaptively Parametric ReLU（调参记录14）_第1张图片

Keras程序如下：

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Apr 14 04:17:45 2020
Implemented using TensorFlow 1.0.1 and Keras 2.2.1

Minghang Zhao, Shisheng Zhong, Xuyun Fu, Baoping Tang, Shaojiang Dong, Michael Pecht,
Deep Residual Networks with Adaptively Parametric Rectifier Linear Units for Fault Diagnosis, 
IEEE Transactions on Industrial Electronics, 2020, DOI: 10.1109/TIE.2020.2972458,
Date of Publication: 13 February 2020

@author: Minghang Zhao
"""

from __future__ import print_function
import keras
import numpy as np
from keras.datasets import cifar10
from keras.layers import Dense, Conv2D, BatchNormalization, Activation, Minimum
from keras.layers import AveragePooling2D, Input, GlobalAveragePooling2D, Concatenate, Reshape
from keras.regularizers import l2
from keras import backend as K
from keras.models import Model
from keras import optimizers
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import LearningRateScheduler
K.set_learning_phase(1)

# The data, split between train and test sets
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_test = x_test-np.mean(x_train)
x_train = x_train-np.mean(x_train)
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, 10)
y_test = keras.utils.to_categorical(y_test, 10)

# Schedule the learning rate, multiply 0.1 every 1500 epoches
def scheduler(epoch):
    if epoch % 1500 == 0 and epoch != 0:
        lr = K.get_value(model.optimizer.lr)
        K.set_value(model.optimizer.lr, lr * 0.1)
        print("lr changed to {}".format(lr * 0.1))
    return K.get_value(model.optimizer.lr)

# An adaptively parametric rectifier linear unit (APReLU)
def aprelu(inputs):
    # get the number of channels
    channels = inputs.get_shape().as_list()[-1]
    # get a zero feature map
    zeros_input = keras.layers.subtract([inputs, inputs])
    # get a feature map with only positive features
    pos_input = Activation('relu')(inputs)
    # get a feature map with only negative features
    neg_input = Minimum()([inputs,zeros_input])
    # define a network to obtain the scaling coefficients
    scales_p = GlobalAveragePooling2D()(pos_input)
    scales_n = GlobalAveragePooling2D()(neg_input)
    scales = Concatenate()([scales_n, scales_p])
    scales = Dense(channels//8, activation='linear', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(scales)
    scales = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(scales)
    scales = Activation('relu')(scales)
    scales = Dense(channels, activation='linear', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(scales)
    scales = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(scales)
    scales = Activation('sigmoid')(scales)
    scales = Reshape((1,1,channels))(scales)
    # apply a paramtetric relu
    neg_part = keras.layers.multiply([scales, neg_input])
    return keras.layers.add([pos_input, neg_part])

# Residual Block
def residual_block(incoming, nb_blocks, out_channels, downsample=False,
                   downsample_strides=2):
    
    residual = incoming
    in_channels = incoming.get_shape().as_list()[-1]
    
    for i in range(nb_blocks):
        
        identity = residual
        
        if not downsample:
            downsample_strides = 1
        
        residual = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(residual)
        residual = aprelu(residual)
        residual = Conv2D(out_channels, 3, strides=(downsample_strides, downsample_strides), 
                          padding='same', kernel_initializer='he_normal', 
                          kernel_regularizer=l2(1e-4))(residual)
        
        residual = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(residual)
        residual = aprelu(residual)
        residual = Conv2D(out_channels, 3, padding='same', kernel_initializer='he_normal', 
                          kernel_regularizer=l2(1e-4))(residual)
        
        # Downsampling
        if downsample_strides > 1:
            identity = AveragePooling2D(pool_size=(1,1), strides=(2,2))(identity)
            
        # Zero_padding to match channels
        if in_channels != out_channels:
            zeros_identity = keras.layers.subtract([identity, identity])
            identity = keras.layers.concatenate([identity, zeros_identity])
            in_channels = out_channels
        
        residual = keras.layers.add([residual, identity])
    
    return residual


# define and train a model
inputs = Input(shape=(32, 32, 3))
net = Conv2D(16, 3, padding='same', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(inputs)
# net = residual_block(net, 3, 16, downsample=False)
net = residual_block(net, 1, 32, downsample=True)
# net = residual_block(net, 2, 32, downsample=False)
net = residual_block(net, 1, 64, downsample=True)
# net = residual_block(net, 2, 64, downsample=False)
net = BatchNormalization(momentum=0.9, gamma_regularizer=l2(1e-4))(net)
net = Activation('relu')(net)
net = GlobalAveragePooling2D()(net)
outputs = Dense(10, activation='softmax', kernel_initializer='he_normal', kernel_regularizer=l2(1e-4))(net)
model = Model(inputs=inputs, outputs=outputs)
sgd = optimizers.SGD(lr=0.1, decay=0., momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])

# data augmentation
datagen = ImageDataGenerator(
    # randomly rotate images in the range (deg 0 to 180)
    rotation_range=30,
    # Range for random zoom
    zoom_range = 0.2,
    # shear angle in counter-clockwise direction in degrees
    shear_range = 30,
    # randomly flip images
    horizontal_flip=True,
    # randomly shift images horizontally
    width_shift_range=0.125,
    # randomly shift images vertically
    height_shift_range=0.125)

reduce_lr = LearningRateScheduler(scheduler)
# fit the model on the batches generated by datagen.flow().
model.fit_generator(datagen.flow(x_train, y_train, batch_size=1000),
                    validation_data=(x_test, y_test), epochs=5000, 
                    verbose=1, callbacks=[reduce_lr], workers=4)

# get results
K.set_learning_phase(0)
DRSN_train_score = model.evaluate(x_train, y_train, batch_size=1000, verbose=0)
print('Train loss:', DRSN_train_score[0])
print('Train accuracy:', DRSN_train_score[1])
DRSN_test_score = model.evaluate(x_test, y_test, batch_size=1000, verbose=0)
print('Test loss:', DRSN_test_score[0])
print('Test accuracy:', DRSN_test_score[1])

实验结果如下（为了方便看，删掉了一部分等号）：

Epoch 2000/5000
10s 191ms/step - loss: 0.5083 - acc: 0.8658 - val_loss: 0.5190 - val_acc: 0.8644
Epoch 2001/5000
10s 194ms/step - loss: 0.5102 - acc: 0.8651 - val_loss: 0.5203 - val_acc: 0.8656
Epoch 2002/5000
10s 192ms/step - loss: 0.5073 - acc: 0.8659 - val_loss: 0.5245 - val_acc: 0.8612
Epoch 2003/5000
10s 190ms/step - loss: 0.5105 - acc: 0.8646 - val_loss: 0.5181 - val_acc: 0.8636
Epoch 2004/5000
9s 186ms/step - loss: 0.5080 - acc: 0.8661 - val_loss: 0.5217 - val_acc: 0.8631
Epoch 2005/5000
9s 186ms/step - loss: 0.5074 - acc: 0.8641 - val_loss: 0.5237 - val_acc: 0.8614
Epoch 2006/5000
9s 186ms/step - loss: 0.5060 - acc: 0.8651 - val_loss: 0.5241 - val_acc: 0.8641
Epoch 2007/5000
10s 190ms/step - loss: 0.5096 - acc: 0.8651 - val_loss: 0.5185 - val_acc: 0.8660
Epoch 2008/5000
9s 190ms/step - loss: 0.5053 - acc: 0.8686 - val_loss: 0.5186 - val_acc: 0.8624
Epoch 2009/5000
10s 191ms/step - loss: 0.5057 - acc: 0.8670 - val_loss: 0.5208 - val_acc: 0.8636
Epoch 2010/5000
10s 190ms/step - loss: 0.5102 - acc: 0.8653 - val_loss: 0.5214 - val_acc: 0.8614
Epoch 2011/5000
9s 188ms/step - loss: 0.5091 - acc: 0.8651 - val_loss: 0.5211 - val_acc: 0.8629
Epoch 2012/5000
9s 187ms/step - loss: 0.5069 - acc: 0.8672 - val_loss: 0.5221 - val_acc: 0.8616
Epoch 2013/5000
9s 184ms/step - loss: 0.5098 - acc: 0.8652 - val_loss: 0.5241 - val_acc: 0.8625
Epoch 2014/5000
9s 187ms/step - loss: 0.5056 - acc: 0.8666 - val_loss: 0.5188 - val_acc: 0.8623
Epoch 2015/5000
9s 189ms/step - loss: 0.5050 - acc: 0.8672 - val_loss: 0.5237 - val_acc: 0.8621
Epoch 2016/5000
10s 193ms/step - loss: 0.5057 - acc: 0.8667 - val_loss: 0.5207 - val_acc: 0.8607
Epoch 2017/5000
10s 192ms/step - loss: 0.5092 - acc: 0.8642 - val_loss: 0.5172 - val_acc: 0.8637
Epoch 2018/5000
9s 190ms/step - loss: 0.5062 - acc: 0.8671 - val_loss: 0.5265 - val_acc: 0.8612
Epoch 2019/5000
9s 188ms/step - loss: 0.5112 - acc: 0.8648 - val_loss: 0.5256 - val_acc: 0.8617
Epoch 2020/5000
9s 185ms/step - loss: 0.5071 - acc: 0.8663 - val_loss: 0.5241 - val_acc: 0.8622
Epoch 2021/5000
9s 186ms/step - loss: 0.5079 - acc: 0.8660 - val_loss: 0.5212 - val_acc: 0.8627
Epoch 2022/5000
9s 185ms/step - loss: 0.5058 - acc: 0.8667 - val_loss: 0.5227 - val_acc: 0.8600
Epoch 2023/5000
9s 189ms/step - loss: 0.5070 - acc: 0.8661 - val_loss: 0.5259 - val_acc: 0.8608
Epoch 2024/5000
10s 193ms/step - loss: 0.5053 - acc: 0.8663 - val_loss: 0.5219 - val_acc: 0.8606
Epoch 2025/5000
10s 191ms/step - loss: 0.5106 - acc: 0.8655 - val_loss: 0.5205 - val_acc: 0.8625
Epoch 2026/5000
10s 191ms/step - loss: 0.5090 - acc: 0.8649 - val_loss: 0.5221 - val_acc: 0.8610
Epoch 2027/5000
9s 189ms/step - loss: 0.5103 - acc: 0.8648 - val_loss: 0.5242 - val_acc: 0.8631
Epoch 2028/5000
9s 189ms/step - loss: 0.5051 - acc: 0.8663 - val_loss: 0.5253 - val_acc: 0.8596
Epoch 2029/5000
9s 185ms/step - loss: 0.5091 - acc: 0.8654 - val_loss: 0.5237 - val_acc: 0.8612
Epoch 2030/5000
9s 189ms/step - loss: 0.5076 - acc: 0.8654 - val_loss: 0.5197 - val_acc: 0.8627
Epoch 2031/5000
9s 189ms/step - loss: 0.5058 - acc: 0.8657 - val_loss: 0.5226 - val_acc: 0.8625
Epoch 2032/5000
10s 194ms/step - loss: 0.5078 - acc: 0.8669 - val_loss: 0.5225 - val_acc: 0.8639
Epoch 2033/5000
10s 193ms/step - loss: 0.5101 - acc: 0.8643 - val_loss: 0.5195 - val_acc: 0.8632
Epoch 2034/5000
10s 191ms/step - loss: 0.5088 - acc: 0.8665 - val_loss: 0.5237 - val_acc: 0.8634
Epoch 2035/5000
10s 191ms/step - loss: 0.5091 - acc: 0.8644 - val_loss: 0.5182 - val_acc: 0.8652
Epoch 2036/5000
9s 186ms/step - loss: 0.5090 - acc: 0.8658 - val_loss: 0.5199 - val_acc: 0.8615
Epoch 2037/5000
9s 187ms/step - loss: 0.5056 - acc: 0.8670 - val_loss: 0.5256 - val_acc: 0.8600
Epoch 2038/5000
9s 187ms/step - loss: 0.5057 - acc: 0.8665 - val_loss: 0.5261 - val_acc: 0.8600
Epoch 2039/5000
9s 190ms/step - loss: 0.5088 - acc: 0.8647 - val_loss: 0.5242 - val_acc: 0.8625
Epoch 2040/5000
10s 192ms/step - loss: 0.5068 - acc: 0.8662 - val_loss: 0.5223 - val_acc: 0.8620
Epoch 2041/5000
10s 191ms/step - loss: 0.5068 - acc: 0.8655 - val_loss: 0.5189 - val_acc: 0.8594
Epoch 2042/5000
10s 191ms/step - loss: 0.5070 - acc: 0.8661 - val_loss: 0.5244 - val_acc: 0.8613
Epoch 2043/5000
9s 187ms/step - loss: 0.5008 - acc: 0.8683 - val_loss: 0.5238 - val_acc: 0.8603
Epoch 2044/5000
9s 189ms/step - loss: 0.5100 - acc: 0.8652 - val_loss: 0.5233 - val_acc: 0.8609
Epoch 2045/5000
9s 186ms/step - loss: 0.5007 - acc: 0.8692 - val_loss: 0.5206 - val_acc: 0.8651
Epoch 2046/5000
9s 188ms/step - loss: 0.5043 - acc: 0.8662 - val_loss: 0.5246 - val_acc: 0.8623
Epoch 2047/5000
10s 190ms/step - loss: 0.5084 - acc: 0.8644 - val_loss: 0.5211 - val_acc: 0.8620
Epoch 2048/5000
10s 192ms/step - loss: 0.5068 - acc: 0.8658 - val_loss: 0.5206 - val_acc: 0.8635
Epoch 2049/5000
10s 194ms/step - loss: 0.5033 - acc: 0.8669 - val_loss: 0.5230 - val_acc: 0.8589
Epoch 2050/5000
10s 192ms/step - loss: 0.5096 - acc: 0.8653 - val_loss: 0.5217 - val_acc: 0.8610
Epoch 2051/5000
10s 191ms/step - loss: 0.5081 - acc: 0.8651 - val_loss: 0.5238 - val_acc: 0.8600
Epoch 2052/5000
9s 186ms/step - loss: 0.5061 - acc: 0.8665 - val_loss: 0.5258 - val_acc: 0.8617
Epoch 2053/5000
9s 187ms/step - loss: 0.5036 - acc: 0.8683 - val_loss: 0.5233 - val_acc: 0.8606
Epoch 2054/5000
9s 187ms/step - loss: 0.5075 - acc: 0.8652 - val_loss: 0.5242 - val_acc: 0.8599
Epoch 2055/5000
9s 189ms/step - loss: 0.5105 - acc: 0.8656 - val_loss: 0.5201 - val_acc: 0.8621
Epoch 2056/5000
10s 191ms/step - loss: 0.5064 - acc: 0.8664 - val_loss: 0.5264 - val_acc: 0.8586
Epoch 2057/5000
10s 192ms/step - loss: 0.5049 - acc: 0.8655 - val_loss: 0.5225 - val_acc: 0.8621
Epoch 2058/5000
10s 190ms/step - loss: 0.5083 - acc: 0.8657 - val_loss: 0.5218 - val_acc: 0.8648
Epoch 2059/5000
9s 188ms/step - loss: 0.5118 - acc: 0.8657 - val_loss: 0.5233 - val_acc: 0.8627
Epoch 2060/5000
9s 187ms/step - loss: 0.5037 - acc: 0.8668 - val_loss: 0.5183 - val_acc: 0.8618
Epoch 2061/5000
9s 185ms/step - loss: 0.5092 - acc: 0.8661 - val_loss: 0.5207 - val_acc: 0.8642
Epoch 2062/5000
9s 188ms/step - loss: 0.5089 - acc: 0.8649 - val_loss: 0.5175 - val_acc: 0.8625
Epoch 2063/5000
10s 190ms/step - loss: 0.5056 - acc: 0.8667 - val_loss: 0.5175 - val_acc: 0.8635
Epoch 2064/5000
10s 192ms/step - loss: 0.5078 - acc: 0.8659 - val_loss: 0.5217 - val_acc: 0.8602
Epoch 2065/5000
10s 192ms/step - loss: 0.5065 - acc: 0.8685 - val_loss: 0.5195 - val_acc: 0.8627
Epoch 2066/5000
10s 190ms/step - loss: 0.5099 - acc: 0.8660 - val_loss: 0.5223 - val_acc: 0.8608
Epoch 2067/5000
10s 190ms/step - loss: 0.5048 - acc: 0.8663 - val_loss: 0.5188 - val_acc: 0.8629
Epoch 2068/5000
9s 187ms/step - loss: 0.5047 - acc: 0.8659 - val_loss: 0.5176 - val_acc: 0.8611
Epoch 2069/5000
9s 185ms/step - loss: 0.5055 - acc: 0.8680 - val_loss: 0.5182 - val_acc: 0.8636
Epoch 2070/5000
9s 186ms/step - loss: 0.5076 - acc: 0.8659 - val_loss: 0.5235 - val_acc: 0.8619
Epoch 2071/5000
9s 189ms/step - loss: 0.5100 - acc: 0.8664 - val_loss: 0.5185 - val_acc: 0.8630
Epoch 2072/5000
10s 192ms/step - loss: 0.5052 - acc: 0.8663 - val_loss: 0.5214 - val_acc: 0.8611
Epoch 2073/5000
10s 192ms/step - loss: 0.5052 - acc: 0.8662 - val_loss: 0.5250 - val_acc: 0.8630
Epoch 2074/5000
10s 193ms/step - loss: 0.5054 - acc: 0.8668 - val_loss: 0.5162 - val_acc: 0.8650
Epoch 2075/5000
9s 189ms/step - loss: 0.5081 - acc: 0.8647 - val_loss: 0.5238 - val_acc: 0.8598
Epoch 2076/5000
9s 189ms/step - loss: 0.5075 - acc: 0.8647 - val_loss: 0.5237 - val_acc: 0.8609
Epoch 2077/5000
9s 185ms/step - loss: 0.5127 - acc: 0.8642 - val_loss: 0.5209 - val_acc: 0.8662
Epoch 2078/5000
9s 186ms/step - loss: 0.5063 - acc: 0.8655 - val_loss: 0.5192 - val_acc: 0.8639
Epoch 2079/5000
9s 189ms/step - loss: 0.5113 - acc: 0.8650 - val_loss: 0.5193 - val_acc: 0.8613
Epoch 2080/5000
10s 191ms/step - loss: 0.5087 - acc: 0.8660 - val_loss: 0.5199 - val_acc: 0.8623
Epoch 2081/5000
10s 191ms/step - loss: 0.5097 - acc: 0.8648 - val_loss: 0.5187 - val_acc: 0.8611
Epoch 2082/5000
10s 191ms/step - loss: 0.5059 - acc: 0.8674 - val_loss: 0.5229 - val_acc: 0.8608
Epoch 2083/5000
10s 191ms/step - loss: 0.5100 - acc: 0.8641 - val_loss: 0.5251 - val_acc: 0.8599
Epoch 2084/5000
9s 187ms/step - loss: 0.5098 - acc: 0.8645 - val_loss: 0.5195 - val_acc: 0.8631
Epoch 2085/5000
9s 187ms/step - loss: 0.5023 - acc: 0.8680 - val_loss: 0.5185 - val_acc: 0.8638
Epoch 2086/5000
9s 187ms/step - loss: 0.5077 - acc: 0.8660 - val_loss: 0.5249 - val_acc: 0.8628
Epoch 2087/5000
9s 189ms/step - loss: 0.5076 - acc: 0.8645 - val_loss: 0.5219 - val_acc: 0.8599
Epoch 2088/5000
9s 189ms/step - loss: 0.5074 - acc: 0.8665 - val_loss: 0.5228 - val_acc: 0.8633
Epoch 2089/5000
10s 191ms/step - loss: 0.5064 - acc: 0.8658 - val_loss: 0.5219 - val_acc: 0.8626
Epoch 2090/5000
10s 191ms/step - loss: 0.5064 - acc: 0.8673 - val_loss: 0.5207 - val_acc: 0.8626
Epoch 2091/5000
9s 188ms/step - loss: 0.5064 - acc: 0.8673 - val_loss: 0.5229 - val_acc: 0.8616
Epoch 2092/5000
9s 190ms/step - loss: 0.5055 - acc: 0.8670 - val_loss: 0.5236 - val_acc: 0.8613
Epoch 2093/5000
9s 187ms/step - loss: 0.5075 - acc: 0.8657 - val_loss: 0.5197 - val_acc: 0.8627
Epoch 2094/5000
9s 186ms/step - loss: 0.5082 - acc: 0.8664 - val_loss: 0.5228 - val_acc: 0.8602
Epoch 2095/5000
9s 189ms/step - loss: 0.5072 - acc: 0.8672 - val_loss: 0.5258 - val_acc: 0.8618
Epoch 2096/5000
10s 192ms/step - loss: 0.5099 - acc: 0.8641 - val_loss: 0.5190 - val_acc: 0.8631
Epoch 2097/5000
10s 192ms/step - loss: 0.5069 - acc: 0.8662 - val_loss: 0.5212 - val_acc: 0.8603
Epoch 2098/5000
10s 191ms/step - loss: 0.5080 - acc: 0.8656 - val_loss: 0.5203 - val_acc: 0.8611
Epoch 2099/5000
10s 192ms/step - loss: 0.5051 - acc: 0.8663 - val_loss: 0.5177 - val_acc: 0.8604
Epoch 2100/5000
9s 186ms/step - loss: 0.5059 - acc: 0.8643 - val_loss: 0.5206 - val_acc: 0.8633
Epoch 2101/5000
9s 186ms/step - loss: 0.5081 - acc: 0.8651 - val_loss: 0.5215 - val_acc: 0.8622
Epoch 2102/5000
9s 188ms/step - loss: 0.5060 - acc: 0.8655 - val_loss: 0.5183 - val_acc: 0.8645
Epoch 2103/5000
10s 190ms/step - loss: 0.5062 - acc: 0.8650 - val_loss: 0.5229 - val_acc: 0.8610
Epoch 2104/5000
10s 192ms/step - loss: 0.5060 - acc: 0.8664 - val_loss: 0.5250 - val_acc: 0.8595
Epoch 2105/5000
10s 194ms/step - loss: 0.5072 - acc: 0.8653 - val_loss: 0.5233 - val_acc: 0.8634
Epoch 2106/5000
10s 193ms/step - loss: 0.5073 - acc: 0.8645 - val_loss: 0.5187 - val_acc: 0.8626
Epoch 2107/5000
9s 187ms/step - loss: 0.5070 - acc: 0.8644 - val_loss: 0.5202 - val_acc: 0.8636
Epoch 2108/5000
9s 186ms/step - loss: 0.5075 - acc: 0.8648 - val_loss: 0.5222 - val_acc: 0.8609
Epoch 2109/5000
9s 186ms/step - loss: 0.5049 - acc: 0.8649 - val_loss: 0.5200 - val_acc: 0.8623
Epoch 2110/5000
9s 188ms/step - loss: 0.5025 - acc: 0.8691 - val_loss: 0.5246 - val_acc: 0.8613
Epoch 2111/5000
10s 190ms/step - loss: 0.5086 - acc: 0.8646 - val_loss: 0.5212 - val_acc: 0.8598
Epoch 2112/5000
10s 191ms/step - loss: 0.5071 - acc: 0.8658 - val_loss: 0.5213 - val_acc: 0.8636
Epoch 2113/5000
10s 193ms/step - loss: 0.5063 - acc: 0.8657 - val_loss: 0.5229 - val_acc: 0.8599
Epoch 2114/5000
9s 190ms/step - loss: 0.5070 - acc: 0.8652 - val_loss: 0.5194 - val_acc: 0.8629
Epoch 2115/5000
10s 191ms/step - loss: 0.5089 - acc: 0.8648 - val_loss: 0.5208 - val_acc: 0.8608
Epoch 2116/5000
9s 188ms/step - loss: 0.5021 - acc: 0.8666 - val_loss: 0.5199 - val_acc: 0.8595
Epoch 2117/5000
9s 188ms/step - loss: 0.5027 - acc: 0.8682 - val_loss: 0.5228 - val_acc: 0.8613
Epoch 2118/5000
9s 186ms/step - loss: 0.5099 - acc: 0.8648 - val_loss: 0.5247 - val_acc: 0.8596
Epoch 2119/5000
10s 190ms/step - loss: 0.5082 - acc: 0.8667 - val_loss: 0.5223 - val_acc: 0.8598
Epoch 2120/5000
10s 191ms/step - loss: 0.5107 - acc: 0.8639 - val_loss: 0.5200 - val_acc: 0.8608
Epoch 2121/5000
10s 191ms/step - loss: 0.5075 - acc: 0.8651 - val_loss: 0.5216 - val_acc: 0.8601
Epoch 2122/5000
10s 191ms/step - loss: 0.5030 - acc: 0.8646 - val_loss: 0.5156 - val_acc: 0.8647
Epoch 2123/5000
9s 187ms/step - loss: 0.5031 - acc: 0.8668 - val_loss: 0.5280 - val_acc: 0.8588
Epoch 2124/5000
9s 187ms/step - loss: 0.5066 - acc: 0.8663 - val_loss: 0.5184 - val_acc: 0.8622
Epoch 2125/5000
9s 187ms/step - loss: 0.5025 - acc: 0.8660 - val_loss: 0.5189 - val_acc: 0.8624
Epoch 2126/5000
9s 189ms/step - loss: 0.5038 - acc: 0.8676 - val_loss: 0.5244 - val_acc: 0.8605
Epoch 2127/5000
10s 191ms/step - loss: 0.5106 - acc: 0.8634 - val_loss: 0.5201 - val_acc: 0.8634
Epoch 2128/5000
10s 193ms/step - loss: 0.5068 - acc: 0.8653 - val_loss: 0.5264 - val_acc: 0.8617
Epoch 2129/5000
10s 193ms/step - loss: 0.5054 - acc: 0.8635 - val_loss: 0.5238 - val_acc: 0.8604
Epoch 2130/5000
9s 189ms/step - loss: 0.5082 - acc: 0.8652 - val_loss: 0.5238 - val_acc: 0.8599
Epoch 2131/5000
10s 191ms/step - loss: 0.5055 - acc: 0.8659 - val_loss: 0.5204 - val_acc: 0.8627
Epoch 2132/5000
9s 186ms/step - loss: 0.5059 - acc: 0.8656 - val_loss: 0.5225 - val_acc: 0.8619
Epoch 2133/5000
9s 189ms/step - loss: 0.5044 - acc: 0.8671 - val_loss: 0.5210 - val_acc: 0.8617
Epoch 2134/5000
9s 187ms/step - loss: 0.5066 - acc: 0.8676 - val_loss: 0.5216 - val_acc: 0.8609
Epoch 2135/5000
10s 191ms/step - loss: 0.5031 - acc: 0.8667 - val_loss: 0.5206 - val_acc: 0.8612
Epoch 2136/5000
10s 190ms/step - loss: 0.5058 - acc: 0.8651 - val_loss: 0.5200 - val_acc: 0.8621
Epoch 2137/5000
10s 192ms/step - loss: 0.5065 - acc: 0.8653 - val_loss: 0.5189 - val_acc: 0.8634
Epoch 2138/5000
10s 191ms/step - loss: 0.5080 - acc: 0.8654 - val_loss: 0.5173 - val_acc: 0.8638
Epoch 2139/5000
9s 188ms/step - loss: 0.5008 - acc: 0.8676 - val_loss: 0.5229 - val_acc: 0.8609
Epoch 2140/5000
9s 188ms/step - loss: 0.5061 - acc: 0.8642 - val_loss: 0.5203 - val_acc: 0.8622
Epoch 2141/5000
9s 186ms/step - loss: 0.5077 - acc: 0.8655 - val_loss: 0.5212 - val_acc: 0.8614
Epoch 2142/5000
9s 187ms/step - loss: 0.5080 - acc: 0.8662 - val_loss: 0.5197 - val_acc: 0.8609
Epoch 2143/5000
9s 189ms/step - loss: 0.5042 - acc: 0.8669 - val_loss: 0.5261 - val_acc: 0.8592
Epoch 2144/5000
10s 192ms/step - loss: 0.5115 - acc: 0.8645 - val_loss: 0.5163 - val_acc: 0.8638
Epoch 2145/5000
10s 193ms/step - loss: 0.5032 - acc: 0.8663 - val_loss: 0.5202 - val_acc: 0.8608
Epoch 2146/5000
10s 192ms/step - loss: 0.5061 - acc: 0.8647 - val_loss: 0.5189 - val_acc: 0.8614
Epoch 2147/5000
10s 191ms/step - loss: 0.5073 - acc: 0.8665 - val_loss: 0.5224 - val_acc: 0.8612
Epoch 2148/5000
9s 186ms/step - loss: 0.5074 - acc: 0.8647 - val_loss: 0.5217 - val_acc: 0.8605
Epoch 2149/5000
9s 186ms/step - loss: 0.5077 - acc: 0.8646 - val_loss: 0.5221 - val_acc: 0.8611
Epoch 2150/5000
9s 186ms/step - loss: 0.5079 - acc: 0.8641 - val_loss: 0.5205 - val_acc: 0.8609
Epoch 2151/5000
10s 191ms/step - loss: 0.5036 - acc: 0.8665 - val_loss: 0.5173 - val_acc: 0.8648
Epoch 2152/5000
10s 193ms/step - loss: 0.5104 - acc: 0.8642 - val_loss: 0.5295 - val_acc: 0.8571
Epoch 2153/5000
10s 192ms/step - loss: 0.5030 - acc: 0.8656 - val_loss: 0.5240 - val_acc: 0.8589
Epoch 2154/5000
10s 192ms/step - loss: 0.5046 - acc: 0.8664 - val_loss: 0.5217 - val_acc: 0.8620
Epoch 2155/5000
9s 188ms/step - loss: 0.5104 - acc: 0.8644 - val_loss: 0.5199 - val_acc: 0.8598
Epoch 2156/5000
9s 187ms/step - loss: 0.5042 - acc: 0.8657 - val_loss: 0.5159 - val_acc: 0.8643
Epoch 2157/5000
9s 185ms/step - loss: 0.5019 - acc: 0.8681 - val_loss: 0.5242 - val_acc: 0.8617
Epoch 2158/5000
9s 188ms/step - loss: 0.5101 - acc: 0.8635 - val_loss: 0.5187 - val_acc: 0.8628
Epoch 2159/5000
9s 190ms/step - loss: 0.5064 - acc: 0.8645 - val_loss: 0.5147 - val_acc: 0.8623
Epoch 2160/5000
10s 191ms/step - loss: 0.5034 - acc: 0.8663 - val_loss: 0.5175 - val_acc: 0.8623
Epoch 2161/5000
10s 191ms/step - loss: 0.5051 - acc: 0.8670 - val_loss: 0.5236 - val_acc: 0.8593
Epoch 2162/5000
9s 189ms/step - loss: 0.5020 - acc: 0.8666 - val_loss: 0.5165 - val_acc: 0.8641
Epoch 2163/5000
9s 189ms/step - loss: 0.5059 - acc: 0.8657 - val_loss: 0.5250 - val_acc: 0.8592
Epoch 2164/5000
9s 186ms/step - loss: 0.5047 - acc: 0.8649 - val_loss: 0.5237 - val_acc: 0.8613
Epoch 2165/5000
9s 186ms/step - loss: 0.5071 - acc: 0.8654 - val_loss: 0.5203 - val_acc: 0.8624
Epoch 2166/5000
9s 185ms/step - loss: 0.5001 - acc: 0.8673 - val_loss: 0.5168 - val_acc: 0.8634
Epoch 2167/5000
9s 188ms/step - loss: 0.5043 - acc: 0.8654 - val_loss: 0.5185 - val_acc: 0.8608
Epoch 2168/5000
10s 193ms/step - loss: 0.5071 - acc: 0.8649 - val_loss: 0.5225 - val_acc: 0.8629
Epoch 2169/5000
10s 192ms/step - loss: 0.5060 - acc: 0.8655 - val_loss: 0.5231 - val_acc: 0.8597
Epoch 2170/5000
10s 191ms/step - loss: 0.5072 - acc: 0.8665 - val_loss: 0.5236 - val_acc: 0.8621
Epoch 2171/5000
9s 187ms/step - loss: 0.5050 - acc: 0.8676 - val_loss: 0.5193 - val_acc: 0.8618
Epoch 2172/5000
9s 187ms/step - loss: 0.5016 - acc: 0.8674 - val_loss: 0.5173 - val_acc: 0.8625
Epoch 2173/5000
9s 184ms/step - loss: 0.5027 - acc: 0.8657 - val_loss: 0.5197 - val_acc: 0.8621
Epoch 2174/5000
9s 185ms/step - loss: 0.5039 - acc: 0.8668 - val_loss: 0.5183 - val_acc: 0.8637
Epoch 2175/5000
9s 186ms/step - loss: 0.5056 - acc: 0.8670 - val_loss: 0.5257 - val_acc: 0.8614
Epoch 2176/5000
9s 189ms/step - loss: 0.5045 - acc: 0.8651 - val_loss: 0.5171 - val_acc: 0.8641
Epoch 2177/5000
9s 190ms/step - loss: 0.5045 - acc: 0.8661 - val_loss: 0.5215 - val_acc: 0.8637
Epoch 2178/5000
9s 190ms/step - loss: 0.5073 - acc: 0.8629 - val_loss: 0.5189 - val_acc: 0.8600
Epoch 2179/5000
9s 190ms/step - loss: 0.5054 - acc: 0.8658 - val_loss: 0.5240 - val_acc: 0.8620
Epoch 2180/5000
9s 185ms/step - loss: 0.5089 - acc: 0.8648 - val_loss: 0.5281 - val_acc: 0.8587
Epoch 2181/5000
9s 185ms/step - loss: 0.5047 - acc: 0.8660 - val_loss: 0.5253 - val_acc: 0.8614
Epoch 2182/5000
9s 185ms/step - loss: 0.5057 - acc: 0.8654 - val_loss: 0.5213 - val_acc: 0.8594
Epoch 2183/5000
9s 188ms/step - loss: 0.5088 - acc: 0.8657 - val_loss: 0.5214 - val_acc: 0.8608
Epoch 2184/5000
9s 189ms/step - loss: 0.5038 - acc: 0.8663 - val_loss: 0.5253 - val_acc: 0.8584
Epoch 2185/5000
9s 190ms/step - loss: 0.5070 - acc: 0.8658 - val_loss: 0.5223 - val_acc: 0.8584
Epoch 2186/5000
10s 190ms/step - loss: 0.5065 - acc: 0.8650 - val_loss: 0.5250 - val_acc: 0.8602
Epoch 2187/5000
9s 185ms/step - loss: 0.5032 - acc: 0.8669 - val_loss: 0.5148 - val_acc: 0.8636
Epoch 2188/5000
9s 184ms/step - loss: 0.5025 - acc: 0.8668 - val_loss: 0.5234 - val_acc: 0.8595
Epoch 2189/5000
9s 184ms/step - loss: 0.5077 - acc: 0.8638 - val_loss: 0.5249 - val_acc: 0.8600
Epoch 2190/5000
9s 185ms/step - loss: 0.5090 - acc: 0.8635 - val_loss: 0.5256 - val_acc: 0.8606
Epoch 2191/5000
9s 188ms/step - loss: 0.5072 - acc: 0.8648 - val_loss: 0.5211 - val_acc: 0.8605
Epoch 2192/5000
9s 187ms/step - loss: 0.5054 - acc: 0.8649 - val_loss: 0.5203 - val_acc: 0.8608
Epoch 2193/5000
9s 189ms/step - loss: 0.5024 - acc: 0.8666 - val_loss: 0.5207 - val_acc: 0.8618
Epoch 2194/5000
9s 190ms/step - loss: 0.5049 - acc: 0.8652 - val_loss: 0.5231 - val_acc: 0.8608
Epoch 2195/5000
9s 188ms/step - loss: 0.5061 - acc: 0.8658 - val_loss: 0.5225 - val_acc: 0.8606
Epoch 2196/5000
9s 185ms/step - loss: 0.5104 - acc: 0.8637 - val_loss: 0.5259 - val_acc: 0.8589
Epoch 2197/5000
9s 184ms/step - loss: 0.5042 - acc: 0.8657 - val_loss: 0.5193 - val_acc: 0.8633
Epoch 2198/5000
9s 185ms/step - loss: 0.5036 - acc: 0.8664 - val_loss: 0.5178 - val_acc: 0.8663
Epoch 2199/5000
9s 187ms/step - loss: 0.5066 - acc: 0.8675 - val_loss: 0.5172 - val_acc: 0.8633
Epoch 2200/5000
9s 188ms/step - loss: 0.5095 - acc: 0.8641 - val_loss: 0.5165 - val_acc: 0.8624
Epoch 2201/5000
10s 190ms/step - loss: 0.5089 - acc: 0.8634 - val_loss: 0.5183 - val_acc: 0.8635
Epoch 2202/5000
9s 189ms/step - loss: 0.5069 - acc: 0.8649 - val_loss: 0.5179 - val_acc: 0.8624
Epoch 2203/5000
9s 184ms/step - loss: 0.5116 - acc: 0.8632 - val_loss: 0.5259 - val_acc: 0.8591
Epoch 2204/5000
9s 187ms/step - loss: 0.5066 - acc: 0.8659 - val_loss: 0.5187 - val_acc: 0.8611
Epoch 2205/5000
9s 181ms/step - loss: 0.5052 - acc: 0.8655 - val_loss: 0.5187 - val_acc: 0.8618
Epoch 2206/5000
9s 186ms/step - loss: 0.5067 - acc: 0.8650 - val_loss: 0.5182 - val_acc: 0.8619
Epoch 2207/5000
9s 185ms/step - loss: 0.5091 - acc: 0.8644 - val_loss: 0.5177 - val_acc: 0.8624
Epoch 2208/5000
10s 192ms/step - loss: 0.5038 - acc: 0.8661 - val_loss: 0.5194 - val_acc: 0.8607
Epoch 2209/5000
10s 190ms/step - loss: 0.5070 - acc: 0.8640 - val_loss: 0.5176 - val_acc: 0.8623
Epoch 2210/5000
10s 190ms/step - loss: 0.5076 - acc: 0.8637 - val_loss: 0.5210 - val_acc: 0.8609
Epoch 2211/5000
9s 189ms/step - loss: 0.5018 - acc: 0.8666 - val_loss: 0.5191 - val_acc: 0.8606
Epoch 2212/5000
9s 186ms/step - loss: 0.5055 - acc: 0.8661 - val_loss: 0.5209 - val_acc: 0.8609
Epoch 2213/5000
9s 185ms/step - loss: 0.5056 - acc: 0.8640 - val_loss: 0.5210 - val_acc: 0.8596
Epoch 2214/5000
9s 184ms/step - loss: 0.5034 - acc: 0.8672 - val_loss: 0.5182 - val_acc: 0.8618
Epoch 2215/5000
9s 187ms/step - loss: 0.5066 - acc: 0.8649 - val_loss: 0.5201 - val_acc: 0.8603
Epoch 2216/5000
9s 189ms/step - loss: 0.5060 - acc: 0.8652 - val_loss: 0.5190 - val_acc: 0.8597
Epoch 2217/5000
10s 190ms/step - loss: 0.5062 - acc: 0.8649 - val_loss: 0.5234 - val_acc: 0.8583
Epoch 2218/5000
10s 192ms/step - loss: 0.5044 - acc: 0.8663 - val_loss: 0.5167 - val_acc: 0.8638
Epoch 2219/5000
9s 185ms/step - loss: 0.5063 - acc: 0.8647 - val_loss: 0.5253 - val_acc: 0.8575
Epoch 2220/5000
9s 186ms/step - loss: 0.5096 - acc: 0.8649 - val_loss: 0.5245 - val_acc: 0.8585
Epoch 2221/5000
9s 184ms/step - loss: 0.5083 - acc: 0.8634 - val_loss: 0.5212 - val_acc: 0.8588
Epoch 2222/5000
9s 187ms/step - loss: 0.5060 - acc: 0.8656 - val_loss: 0.5202 - val_acc: 0.8603
Epoch 2223/5000
9s 188ms/step - loss: 0.5032 - acc: 0.8669 - val_loss: 0.5179 - val_acc: 0.8603
Epoch 2224/5000
9s 190ms/step - loss: 0.5051 - acc: 0.8658 - val_loss: 0.5224 - val_acc: 0.8608
Epoch 2225/5000
10s 191ms/step - loss: 0.5022 - acc: 0.8663 - val_loss: 0.5204 - val_acc: 0.8615
Epoch 2226/5000
9s 189ms/step - loss: 0.5044 - acc: 0.8668 - val_loss: 0.5194 - val_acc: 0.8603
Epoch 2227/5000
9s 188ms/step - loss: 0.5066 - acc: 0.8658 - val_loss: 0.5194 - val_acc: 0.8612
Epoch 2228/5000
9s 183ms/step - loss: 0.5091 - acc: 0.8642 - val_loss: 0.5199 - val_acc: 0.8590
Epoch 2229/5000
9s 185ms/step - loss: 0.5023 - acc: 0.8648 - val_loss: 0.5202 - val_acc: 0.8637
Epoch 2230/5000
9s 185ms/step - loss: 0.5041 - acc: 0.8646 - val_loss: 0.5196 - val_acc: 0.8622
Epoch 2231/5000
9s 189ms/step - loss: 0.5014 - acc: 0.8668 - val_loss: 0.5193 - val_acc: 0.8612
Epoch 2232/5000
9s 188ms/step - loss: 0.5031 - acc: 0.8663 - val_loss: 0.5227 - val_acc: 0.8614
Epoch 2233/5000
10s 192ms/step - loss: 0.5037 - acc: 0.8661 - val_loss: 0.5181 - val_acc: 0.8610
Epoch 2234/5000
10s 192ms/step - loss: 0.5067 - acc: 0.8666 - val_loss: 0.5257 - val_acc: 0.8587
Epoch 2235/5000
9s 186ms/step - loss: 0.5068 - acc: 0.8649 - val_loss: 0.5163 - val_acc: 0.8618
Epoch 2236/5000
9s 186ms/step - loss: 0.5071 - acc: 0.8639 - val_loss: 0.5234 - val_acc: 0.8599
Epoch 2237/5000
9s 185ms/step - loss: 0.5042 - acc: 0.8648 - val_loss: 0.5147 - val_acc: 0.8623
Epoch 2238/5000
9s 185ms/step - loss: 0.5053 - acc: 0.8652 - val_loss: 0.5217 - val_acc: 0.8588
Epoch 2239/5000
9s 186ms/step - loss: 0.5070 - acc: 0.8636 - val_loss: 0.5205 - val_acc: 0.8624
Epoch 2240/5000
10s 192ms/step - loss: 0.5024 - acc: 0.8658 - val_loss: 0.5219 - val_acc: 0.8639
Epoch 2241/5000
10s 191ms/step - loss: 0.5069 - acc: 0.8651 - val_loss: 0.5211 - val_acc: 0.8619
Epoch 2242/5000
9s 188ms/step - loss: 0.5040 - acc: 0.8658 - val_loss: 0.5152 - val_acc: 0.8622
Epoch 2243/5000
9s 188ms/step - loss: 0.5036 - acc: 0.8651 - val_loss: 0.5222 - val_acc: 0.8599
Epoch 2244/5000
9s 185ms/step - loss: 0.5068 - acc: 0.8635 - val_loss: 0.5177 - val_acc: 0.8611
Epoch 2245/5000
9s 186ms/step - loss: 0.5059 - acc: 0.8650 - val_loss: 0.5247 - val_acc: 0.8600
Epoch 2246/5000
9s 184ms/step - loss: 0.5041 - acc: 0.8661 - val_loss: 0.5194 - val_acc: 0.8609
Epoch 2247/5000
9s 188ms/step - loss: 0.5058 - acc: 0.8652 - val_loss: 0.5250 - val_acc: 0.8607
Epoch 2248/5000
10s 191ms/step - loss: 0.5072 - acc: 0.8649 - val_loss: 0.5225 - val_acc: 0.8623
Epoch 2249/5000
10s 191ms/step - loss: 0.5071 - acc: 0.8650 - val_loss: 0.5214 - val_acc: 0.8609
Epoch 2250/5000
10s 192ms/step - loss: 0.5040 - acc: 0.8660 - val_loss: 0.5235 - val_acc: 0.8594
Epoch 2251/5000
9s 188ms/step - loss: 0.5052 - acc: 0.8667 - val_loss: 0.5213 - val_acc: 0.8615
Epoch 2252/5000
9s 187ms/step - loss: 0.5055 - acc: 0.8664 - val_loss: 0.5178 - val_acc: 0.8604
Epoch 2253/5000
9s 184ms/step - loss: 0.5074 - acc: 0.8666 - val_loss: 0.5228 - val_acc: 0.8605
Epoch 2254/5000
9s 187ms/step - loss: 0.5065 - acc: 0.8657 - val_loss: 0.5181 - val_acc: 0.8640
Epoch 2255/5000
9s 187ms/step - loss: 0.5033 - acc: 0.8668 - val_loss: 0.5194 - val_acc: 0.8625
Epoch 2256/5000
9s 190ms/step - loss: 0.5065 - acc: 0.8644 - val_loss: 0.5209 - val_acc: 0.8599
Epoch 2257/5000
9s 190ms/step - loss: 0.5064 - acc: 0.8645 - val_loss: 0.5248 - val_acc: 0.8588
Epoch 2258/5000
9s 188ms/step - loss: 0.5070 - acc: 0.8645 - val_loss: 0.5210 - val_acc: 0.8633
Epoch 2259/5000
9s 189ms/step - loss: 0.5039 - acc: 0.8642 - val_loss: 0.5231 - val_acc: 0.8633
Epoch 2260/5000
9s 185ms/step - loss: 0.5078 - acc: 0.8641 - val_loss: 0.5208 - val_acc: 0.8609
Epoch 2261/5000
9s 185ms/step - loss: 0.5001 - acc: 0.8675 - val_loss: 0.5218 - val_acc: 0.8633
Epoch 2262/5000
9s 186ms/step - loss: 0.5063 - acc: 0.8653 - val_loss: 0.5183 - val_acc: 0.8602
Epoch 2263/5000
9s 186ms/step - loss: 0.5039 - acc: 0.8665 - val_loss: 0.5264 - val_acc: 0.8582
Epoch 2264/5000
10s 190ms/step - loss: 0.5058 - acc: 0.8660 - val_loss: 0.5223 - val_acc: 0.8605
Epoch 2265/5000
9s 190ms/step - loss: 0.5027 - acc: 0.8659 - val_loss: 0.5194 - val_acc: 0.8629
Epoch 2266/5000
9s 189ms/step - loss: 0.5042 - acc: 0.8663 - val_loss: 0.5171 - val_acc: 0.8610
Epoch 2267/5000
9s 185ms/step - loss: 0.5032 - acc: 0.8662 - val_loss: 0.5224 - val_acc: 0.8594
Epoch 2268/5000
9s 186ms/step - loss: 0.5089 - acc: 0.8636 - val_loss: 0.5156 - val_acc: 0.8617
Epoch 2269/5000
9s 183ms/step - loss: 0.5065 - acc: 0.8629 - val_loss: 0.5170 - val_acc: 0.8615
Epoch 2270/5000
9s 185ms/step - loss: 0.5052 - acc: 0.8653 - val_loss: 0.5179 - val_acc: 0.8612
Epoch 2271/5000
9s 187ms/step - loss: 0.5058 - acc: 0.8646 - val_loss: 0.5214 - val_acc: 0.8610
Epoch 2272/5000
9s 188ms/step - loss: 0.5054 - acc: 0.8655 - val_loss: 0.5210 - val_acc: 0.8616
Epoch 2273/5000
10s 196ms/step - loss: 0.5026 - acc: 0.8650 - val_loss: 0.5182 - val_acc: 0.8612
Epoch 2274/5000
10s 194ms/step - loss: 0.5045 - acc: 0.8653 - val_loss: 0.5181 - val_acc: 0.8621
Epoch 2275/5000
9s 187ms/step - loss: 0.5019 - acc: 0.8674 - val_loss: 0.5220 - val_acc: 0.8617
Epoch 2276/5000
9s 185ms/step - loss: 0.5060 - acc: 0.8633 - val_loss: 0.5245 - val_acc: 0.8592
Epoch 2277/5000
9s 182ms/step - loss: 0.5051 - acc: 0.8664 - val_loss: 0.5211 - val_acc: 0.8593
Epoch 2278/5000
9s 186ms/step - loss: 0.5048 - acc: 0.8640 - val_loss: 0.5253 - val_acc: 0.8605
Epoch 2279/5000
9s 189ms/step - loss: 0.5082 - acc: 0.8631 - val_loss: 0.5198 - val_acc: 0.8642
Epoch 2280/5000
10s 192ms/step - loss: 0.5044 - acc: 0.8660 - val_loss: 0.5190 - val_acc: 0.8618
Epoch 2281/5000
10s 192ms/step - loss: 0.5053 - acc: 0.8660 - val_loss: 0.5215 - val_acc: 0.8586
Epoch 2282/5000
10s 191ms/step - loss: 0.5032 - acc: 0.8647 - val_loss: 0.5280 - val_acc: 0.8604
Epoch 2283/5000
9s 186ms/step - loss: 0.5086 - acc: 0.8635 - val_loss: 0.5234 - val_acc: 0.8564
Epoch 2284/5000
9s 187ms/step - loss: 0.5015 - acc: 0.8669 - val_loss: 0.5199 - val_acc: 0.8601
Epoch 2285/5000
9s 183ms/step - loss: 0.5049 - acc: 0.8642 - val_loss: 0.5206 - val_acc: 0.8607
Epoch 2286/5000
9s 187ms/step - loss: 0.5046 - acc: 0.8644 - val_loss: 0.5229 - val_acc: 0.8590
Epoch 2287/5000
9s 186ms/step - loss: 0.5042 - acc: 0.8663 - val_loss: 0.5194 - val_acc: 0.8618
Epoch 2288/5000
9s 188ms/step - loss: 0.5001 - acc: 0.8680 - val_loss: 0.5266 - val_acc: 0.8598
Epoch 2289/5000
10s 191ms/step - loss: 0.5044 - acc: 0.8660 - val_loss: 0.5180 - val_acc: 0.8626
Epoch 2290/5000
9s 189ms/step - loss: 0.5053 - acc: 0.8638 - val_loss: 0.5227 - val_acc: 0.8600
Epoch 2291/5000
9s 189ms/step - loss: 0.5054 - acc: 0.8645 - val_loss: 0.5171 - val_acc: 0.8617
Epoch 2292/5000
9s 182ms/step - loss: 0.5035 - acc: 0.8667 - val_loss: 0.5225 - val_acc: 0.8587
Epoch 2293/5000
9s 186ms/step - loss: 0.5067 - acc: 0.8657 - val_loss: 0.5227 - val_acc: 0.8621
Epoch 2294/5000
9s 185ms/step - loss: 0.4980 - acc: 0.8681 - val_loss: 0.5199 - val_acc: 0.8593
Epoch 2295/5000
9s 188ms/step - loss: 0.5036 - acc: 0.8653 - val_loss: 0.5232 - val_acc: 0.8627
Epoch 2296/5000
10s 190ms/step - loss: 0.5046 - acc: 0.8648 - val_loss: 0.5222 - val_acc: 0.8598
Epoch 2297/5000
10s 191ms/step - loss: 0.5052 - acc: 0.8657 - val_loss: 0.5163 - val_acc: 0.8621
Epoch 2298/5000
9s 189ms/step - loss: 0.5079 - acc: 0.8636 - val_loss: 0.5138 - val_acc: 0.8651
Epoch 2299/5000
9s 189ms/step - loss: 0.5021 - acc: 0.8646 - val_loss: 0.5184 - val_acc: 0.8637
Epoch 2300/5000
9s 186ms/step - loss: 0.5071 - acc: 0.8634 - val_loss: 0.5206 - val_acc: 0.8629
Epoch 2301/5000
9s 182ms/step - loss: 0.5054 - acc: 0.8657 - val_loss: 0.5240 - val_acc: 0.8620
Epoch 2302/5000
9s 185ms/step - loss: 0.5034 - acc: 0.8658 - val_loss: 0.5235 - val_acc: 0.8608
Epoch 2303/5000
9s 187ms/step - loss: 0.5092 - acc: 0.8627 - val_loss: 0.5228 - val_acc: 0.8604
Epoch 2304/5000
10s 191ms/step - loss: 0.5026 - acc: 0.8664 - val_loss: 0.5142 - val_acc: 0.8619
Epoch 2305/5000
9s 190ms/step - loss: 0.5031 - acc: 0.8655 - val_loss: 0.5167 - val_acc: 0.8627
Epoch 2306/5000
9s 188ms/step - loss: 0.5065 - acc: 0.8655 - val_loss: 0.5212 - val_acc: 0.8631
Epoch 2307/5000
9s 190ms/step - loss: 0.5036 - acc: 0.8675 - val_loss: 0.5190 - val_acc: 0.8609
Epoch 2308/5000
9s 184ms/step - loss: 0.5017 - acc: 0.8668 - val_loss: 0.5247 - val_acc: 0.8598
Epoch 2309/5000
9s 186ms/step - loss: 0.5043 - acc: 0.8639 - val_loss: 0.5142 - val_acc: 0.8641
Epoch 2310/5000
9s 185ms/step - loss: 0.5070 - acc: 0.8637 - val_loss: 0.5193 - val_acc: 0.8622
Epoch 2311/5000
9s 188ms/step - loss: 0.5043 - acc: 0.8650 - val_loss: 0.5229 - val_acc: 0.8637
Epoch 2312/5000
9s 189ms/step - loss: 0.5068 - acc: 0.8645 - val_loss: 0.5190 - val_acc: 0.8607
Epoch 2313/5000
10s 190ms/step - loss: 0.5041 - acc: 0.8653 - val_loss: 0.5195 - val_acc: 0.8620
Epoch 2314/5000
10s 191ms/step - loss: 0.5037 - acc: 0.8640 - val_loss: 0.5208 - val_acc: 0.8613
Epoch 2315/5000
9s 186ms/step - loss: 0.5041 - acc: 0.8652 - val_loss: 0.5194 - val_acc: 0.8625
Epoch 2316/5000
9s 186ms/step - loss: 0.5075 - acc: 0.8632 - val_loss: 0.5149 - val_acc: 0.8620
Epoch 2317/5000
9s 185ms/step - loss: 0.5038 - acc: 0.8657 - val_loss: 0.5223 - val_acc: 0.8617
Epoch 2318/5000
9s 186ms/step - loss: 0.5053 - acc: 0.8643 - val_loss: 0.5190 - val_acc: 0.8634
Epoch 2319/5000
9s 187ms/step - loss: 0.5028 - acc: 0.8662 - val_loss: 0.5242 - val_acc: 0.8596
Epoch 2320/5000
9s 189ms/step - loss: 0.5017 - acc: 0.8669 - val_loss: 0.5195 - val_acc: 0.8606
Epoch 2321/5000
10s 191ms/step - loss: 0.5055 - acc: 0.8646 - val_loss: 0.5220 - val_acc: 0.8609
Epoch 2322/5000
10s 190ms/step - loss: 0.5034 - acc: 0.8655 - val_loss: 0.5179 - val_acc: 0.8606
Epoch 2323/5000
9s 189ms/step - loss: 0.5033 - acc: 0.8668 - val_loss: 0.5193 - val_acc: 0.8605
Epoch 2324/5000
9s 183ms/step - loss: 0.5032 - acc: 0.8663 - val_loss: 0.5221 - val_acc: 0.8610
Epoch 2325/5000
9s 183ms/step - loss: 0.5066 - acc: 0.8649 - val_loss: 0.5202 - val_acc: 0.8610
Epoch 2326/5000
9s 184ms/step - loss: 0.5042 - acc: 0.8660 - val_loss: 0.5222 - val_acc: 0.8597
Epoch 2327/5000
9s 187ms/step - loss: 0.5091 - acc: 0.8655 - val_loss: 0.5203 - val_acc: 0.8598
Epoch 2328/5000
9s 188ms/step - loss: 0.5090 - acc: 0.8636 - val_loss: 0.5196 - val_acc: 0.8603
Epoch 2329/5000
10s 192ms/step - loss: 0.5030 - acc: 0.8658 - val_loss: 0.5255 - val_acc: 0.8602
Epoch 2330/5000
9s 188ms/step - loss: 0.5063 - acc: 0.8650 - val_loss: 0.5205 - val_acc: 0.8606
Epoch 2331/5000
9s 188ms/step - loss: 0.5038 - acc: 0.8659 - val_loss: 0.5256 - val_acc: 0.8584
Epoch 2332/5000
9s 186ms/step - loss: 0.5077 - acc: 0.8642 - val_loss: 0.5186 - val_acc: 0.8618
Epoch 2333/5000
9s 183ms/step - loss: 0.5051 - acc: 0.8643 - val_loss: 0.5204 - val_acc: 0.8586
Epoch 2334/5000
9s 187ms/step - loss: 0.5008 - acc: 0.8670 - val_loss: 0.5186 - val_acc: 0.8607
Epoch 2335/5000
9s 185ms/step - loss: 0.5044 - acc: 0.8664 - val_loss: 0.5204 - val_acc: 0.8623
Epoch 2336/5000
10s 191ms/step - loss: 0.5059 - acc: 0.8646 - val_loss: 0.5191 - val_acc: 0.8616
Epoch 2337/5000
10s 191ms/step - loss: 0.5013 - acc: 0.8675 - val_loss: 0.5189 - val_acc: 0.8629
Epoch 2338/5000
9s 189ms/step - loss: 0.5069 - acc: 0.8645 - val_loss: 0.5244 - val_acc: 0.8630
Epoch 2339/5000
10s 190ms/step - loss: 0.5085 - acc: 0.8638 - val_loss: 0.5189 - val_acc: 0.8609
Epoch 2340/5000
9s 184ms/step - loss: 0.5009 - acc: 0.8653 - val_loss: 0.5210 - val_acc: 0.8609
Epoch 2341/5000
9s 187ms/step - loss: 0.5008 - acc: 0.8657 - val_loss: 0.5144 - val_acc: 0.8628
Epoch 2342/5000
9s 184ms/step - loss: 0.5017 - acc: 0.8661 - val_loss: 0.5251 - val_acc: 0.8606
Epoch 2343/5000
9s 186ms/step - loss: 0.5069 - acc: 0.8646 - val_loss: 0.5204 - val_acc: 0.8608
Epoch 2344/5000
9s 189ms/step - loss: 0.4997 - acc: 0.8675 - val_loss: 0.5203 - val_acc: 0.8651
Epoch 2345/5000
9s 189ms/step - loss: 0.5015 - acc: 0.8672 - val_loss: 0.5220 - val_acc: 0.8610
Epoch 2346/5000
10s 192ms/step - loss: 0.5005 - acc: 0.8656 - val_loss: 0.5200 - val_acc: 0.8620
Epoch 2347/5000
9s 186ms/step - loss: 0.5070 - acc: 0.8636 - val_loss: 0.5230 - val_acc: 0.8607
Epoch 2348/5000
9s 189ms/step - loss: 0.5018 - acc: 0.8657 - val_loss: 0.5175 - val_acc: 0.8611
Epoch 2349/5000
9s 182ms/step - loss: 0.5042 - acc: 0.8656 - val_loss: 0.5244 - val_acc: 0.8603
Epoch 2350/5000
9s 187ms/step - loss: 0.5062 - acc: 0.8656 - val_loss: 0.5182 - val_acc: 0.8614
Epoch 2351/5000
9s 184ms/step - loss: 0.5053 - acc: 0.8642 - val_loss: 0.5183 - val_acc: 0.8611
Epoch 2352/5000
10s 192ms/step - loss: 0.5094 - acc: 0.8640 - val_loss: 0.5202 - val_acc: 0.8589
Epoch 2353/5000
10s 191ms/step - loss: 0.5077 - acc: 0.8648 - val_loss: 0.5176 - val_acc: 0.8630
Epoch 2354/5000
9s 189ms/step - loss: 0.5082 - acc: 0.8635 - val_loss: 0.5217 - val_acc: 0.8620
Epoch 2355/5000
9s 189ms/step - loss: 0.5024 - acc: 0.8656 - val_loss: 0.5174 - val_acc: 0.8627
Epoch 2356/5000
9s 185ms/step - loss: 0.5014 - acc: 0.8653 - val_loss: 0.5185 - val_acc: 0.8615
Epoch 2357/5000
9s 183ms/step - loss: 0.5070 - acc: 0.8650 - val_loss: 0.5207 - val_acc: 0.8630
Epoch 2358/5000
9s 182ms/step - loss: 0.5031 - acc: 0.8648 - val_loss: 0.5190 - val_acc: 0.8649
Epoch 2359/5000
9s 186ms/step - loss: 0.5080 - acc: 0.8630 - val_loss: 0.5172 - val_acc: 0.8636
Epoch 2360/5000
9s 189ms/step - loss: 0.5041 - acc: 0.8661 - val_loss: 0.5220 - val_acc: 0.8597
Epoch 2361/5000
10s 191ms/step - loss: 0.5029 - acc: 0.8654 - val_loss: 0.5226 - val_acc: 0.8602
Epoch 2362/5000
9s 188ms/step - loss: 0.4963 - acc: 0.8706 - val_loss: 0.5257 - val_acc: 0.8605
Epoch 2363/5000
9s 189ms/step - loss: 0.4999 - acc: 0.8673 - val_loss: 0.5233 - val_acc: 0.8563
Epoch 2364/5000
9s 184ms/step - loss: 0.5031 - acc: 0.8658 - val_loss: 0.5160 - val_acc: 0.8612
Epoch 2365/5000
9s 184ms/step - loss: 0.5002 - acc: 0.8673 - val_loss: 0.5206 - val_acc: 0.8605
Epoch 2366/5000
9s 185ms/step - loss: 0.5039 - acc: 0.8649 - val_loss: 0.5190 - val_acc: 0.8608
Epoch 2367/5000
9s 185ms/step - loss: 0.5082 - acc: 0.8639 - val_loss: 0.5184 - val_acc: 0.8623
Epoch 2368/5000
9s 189ms/step - loss: 0.5051 - acc: 0.8658 - val_loss: 0.5175 - val_acc: 0.8611
Epoch 2369/5000
10s 191ms/step - loss: 0.5079 - acc: 0.8635 - val_loss: 0.5172 - val_acc: 0.8612
Epoch 2370/5000
9s 189ms/step - loss: 0.5056 - acc: 0.8647 - val_loss: 0.5243 - val_acc: 0.8609
Epoch 2371/5000
9s 186ms/step - loss: 0.5034 - acc: 0.8654 - val_loss: 0.5149 - val_acc: 0.8632
Epoch 2372/5000
9s 185ms/step - loss: 0.5055 - acc: 0.8625 - val_loss: 0.5204 - val_acc: 0.8613
Epoch 2373/5000
9s 183ms/step - loss: 0.5015 - acc: 0.8663 - val_loss: 0.5233 - val_acc: 0.8620
Epoch 2374/5000
9s 185ms/step - loss: 0.5034 - acc: 0.8649 - val_loss: 0.5199 - val_acc: 0.8624
Epoch 2375/5000
9s 186ms/step - loss: 0.5043 - acc: 0.8667 - val_loss: 0.5198 - val_acc: 0.8643
Epoch 2376/5000
10s 190ms/step - loss: 0.5060 - acc: 0.8655 - val_loss: 0.5159 - val_acc: 0.8641
Epoch 2377/5000
10s 190ms/step - loss: 0.5025 - acc: 0.8661 - val_loss: 0.5171 - val_acc: 0.8600
Epoch 2378/5000
9s 190ms/step - loss: 0.5058 - acc: 0.8643 - val_loss: 0.5229 - val_acc: 0.8596
Epoch 2379/5000
9s 186ms/step - loss: 0.5067 - acc: 0.8649 - val_loss: 0.5204 - val_acc: 0.8585
Epoch 2380/5000
9s 185ms/step - loss: 0.5039 - acc: 0.8648 - val_loss: 0.5211 - val_acc: 0.8616
Epoch 2381/5000
9s 186ms/step - loss: 0.5031 - acc: 0.8650 - val_loss: 0.5184 - val_acc: 0.8609
Epoch 2382/5000
9s 185ms/step - loss: 0.5069 - acc: 0.8644 - val_loss: 0.5213 - val_acc: 0.8594
Epoch 2383/5000
9s 189ms/step - loss: 0.5071 - acc: 0.8639 - val_loss: 0.5227 - val_acc: 0.8589
Epoch 2384/5000
9s 189ms/step - loss: 0.5073 - acc: 0.8663 - val_loss: 0.5190 - val_acc: 0.8623
Epoch 2385/5000
10s 193ms/step - loss: 0.5056 - acc: 0.8662 - val_loss: 0.5171 - val_acc: 0.8633
Epoch 2386/5000
9s 188ms/step - loss: 0.5086 - acc: 0.8638 - val_loss: 0.5144 - val_acc: 0.8637
Epoch 2387/5000
9s 188ms/step - loss: 0.4997 - acc: 0.8667 - val_loss: 0.5166 - val_acc: 0.8624
Epoch 2388/5000
9s 184ms/step - loss: 0.4999 - acc: 0.8663 - val_loss: 0.5198 - val_acc: 0.8641
Epoch 2389/5000
9s 185ms/step - loss: 0.5057 - acc: 0.8638 - val_loss: 0.5206 - val_acc: 0.8614
Epoch 2390/5000
9s 185ms/step - loss: 0.5030 - acc: 0.8666 - val_loss: 0.5173 - val_acc: 0.8608
Epoch 2391/5000
9s 188ms/step - loss: 0.5021 - acc: 0.8650 - val_loss: 0.5237 - val_acc: 0.8592
Epoch 2392/5000
9s 190ms/step - loss: 0.5059 - acc: 0.8660 - val_loss: 0.5201 - val_acc: 0.8632
Epoch 2393/5000
10s 192ms/step - loss: 0.5029 - acc: 0.8650 - val_loss: 0.5208 - val_acc: 0.8596
Epoch 2394/5000
10s 191ms/step - loss: 0.5014 - acc: 0.8664 - val_loss: 0.5260 - val_acc: 0.8575
Epoch 2395/5000
9s 185ms/step - loss: 0.5004 - acc: 0.8677 - val_loss: 0.5158 - val_acc: 0.8635
Epoch 2396/5000
9s 187ms/step - loss: 0.5001 - acc: 0.8665 - val_loss: 0.5234 - val_acc: 0.8596
Epoch 2397/5000
9s 182ms/step - loss: 0.5038 - acc: 0.8644 - val_loss: 0.5157 - val_acc: 0.8631
Epoch 2398/5000
9s 187ms/step - loss: 0.5047 - acc: 0.8655 - val_loss: 0.5172 - val_acc: 0.8619
Epoch 2399/5000
9s 190ms/step - loss: 0.5061 - acc: 0.8647 - val_loss: 0.5225 - val_acc: 0.8602
Epoch 2400/5000
10s 191ms/step - loss: 0.5054 - acc: 0.8632 - val_loss: 0.5205 - val_acc: 0.8616
Epoch 2401/5000
10s 193ms/step - loss: 0.5061 - acc: 0.8649 - val_loss: 0.5271 - val_acc: 0.8580

程序还没运行完，看这样子，估计是欠拟合了。

Minghang Zhao, Shisheng Zhong, Xuyun Fu, Baoping Tang, Shaojiang Dong, Michael Pecht, Deep Residual Networks with Adaptively Parametric Rectifier Linear Units for Fault Diagnosis, IEEE Transactions on Industrial Electronics, 2020, DOI: 10.1109/TIE.2020.2972458, Date of Publication: 13 February 2020

https://ieeexplore.ieee.org/d...

你可能感兴趣的:(机器学习,人工智能,深度学习,tensorflow,神经网络)

  • 机器学习与深度学习间关系与区别 ℒℴѵℯ心·动ꦿ໊ོ꫞ 人工智能学习深度学习python
    一、机器学习概述定义机器学习（MachineLearning,ML）是一种通过数据驱动的方法，利用统计学和计算算法来训练模型，使计算机能够从数据中学习并自动进行预测或决策。机器学习通过分析大量数据样本，识别其中的模式和规律，从而对新的数据进行判断。其核心在于通过训练过程，让模型不断优化和提升其预测准确性。主要类型1.监督学习（SupervisedLearning）监督学习是指在训练数据集中包含输入
  • 将cmd中命令输出保存为txt文本文件 落难Coder Windowscmdwindow
    最近深度学习本地的训练中我们常常要在命令行中运行自己的代码，无可厚非，我们有必要保存我们的炼丹结果，但是复制命令行输出到txt是非常麻烦的，其实Windows下的命令行为我们提供了相应的操作。其基本的调用格式就是：运行指令>输出到的文件名称或者具体保存路径测试下，我打开cmd并且ping一下百度：pingwww.baidu.com>./data.txt看下相同目录下data.txt的输出：如果你再
  • 探索OpenAI和LangChain的适配器集成：轻松切换模型提供商 nseejrukjhad langchaineasyui前端python
    #探索OpenAI和LangChain的适配器集成：轻松切换模型提供商##引言在人工智能和自然语言处理的世界中，OpenAI的模型提供了强大的能力。然而，随着技术的发展，许多人开始探索其他模型以满足特定需求。LangChain作为一个强大的工具，集成了多种模型提供商，通过提供适配器，简化了不同模型之间的转换。本篇文章将介绍如何使用LangChain的适配器与OpenAI集成，以便轻松切换模型提供商
  • 深入理解 MultiQueryRetriever：提升向量数据库检索效果的强大工具 nseejrukjhad 数据库python
    深入理解MultiQueryRetriever：提升向量数据库检索效果的强大工具引言在人工智能和自然语言处理领域，高效准确的信息检索一直是一个关键挑战。传统的基于距离的向量数据库检索方法虽然广泛应用，但仍存在一些局限性。本文将介绍一种创新的解决方案：MultiQueryRetriever，它通过自动生成多个查询视角来增强检索效果，提高结果的相关性和多样性。MultiQueryRetriever的工
  • 人工智能时代，程序员如何保持核心竞争力？ jmoych 人工智能
    随着AIGC（如chatgpt、midjourney、claude等）大语言模型接二连三的涌现，AI辅助编程工具日益普及，程序员的工作方式正在发生深刻变革。有人担心AI可能取代部分编程工作，也有人认为AI是提高效率的得力助手。面对这一趋势,程序员应该如何应对?是专注于某个领域深耕细作，还是广泛学习以适应快速变化的技术环境?又或者，我们是否应该将重点转向AI无法轻易替代的软技能？让我们一起探讨程序员
  • 数字里的世界17期：2021年全球10大顶级数据中心，中国移动榜首 张三叨
    你知道吗？2016年，全球的数据中心共计用电4160亿千瓦时，比整个英国的发电量还多40％！前言每天，我们都会创造超过250万TB的数据。并且随着物联网（IOT）的不断普及，这一数据将持续增长。如此庞大的数据被存储在被称为“数据中心”的专用设施中。虽然最早的数据中心建于20世纪40年代，但直到1997-2000年的互联网泡沫期间才逐渐成为主流。当前人类的技术，比如人工智能和机器学习，已经将我们推向
  • nosql数据库技术与应用知识点 皆过客，揽星河 NoSQLnosql数据库大数据数据分析数据结构非关系型数据库
    Nosql知识回顾大数据处理流程数据采集(flume、爬虫、传感器)数据存储(本门课程NoSQL所处的阶段)Hdfs、MongoDB、HBase等数据清洗(入仓)Hive等数据处理、分析(Spark、Flink等)数据可视化数据挖掘、机器学习应用(Python、SparkMLlib等)大数据时代存储的挑战(三高)高并发(同一时间很多人访问)高扩展(要求随时根据需求扩展存储)高效率(要求读写速度快)
  • Python开发常用的三方模块如下： 换个网名有点难 python开发语言
    Python是一门功能强大的编程语言，拥有丰富的第三方库，这些库为开发者提供了极大的便利。以下是100个常用的Python库，涵盖了多个领域：1、NumPy，用于科学计算的基础库。2、Pandas，提供数据结构和数据分析工具。3、Matplotlib，一个绘图库。4、Scikit-learn，机器学习库。5、SciPy，用于数学、科学和工程的库。6、TensorFlow，由Google开发的开源机
  • Python实现简单的机器学习算法 master_chenchengg pythonpython办公效率python开发IT
    Python实现简单的机器学习算法开篇：初探机器学习的奇妙之旅搭建环境：一切从安装开始必备工具箱第一步：安装Anaconda和JupyterNotebook小贴士：如何配置Python环境变量算法初体验：从零开始的Python机器学习线性回归：让数据说话数据准备：从哪里找数据编码实战：Python实现线性回归模型评估：如何判断模型好坏逻辑回归：从分类开始理论入门：什么是逻辑回归代码实现：使用skl
  • 遥感影像的切片处理 sand&wich 计算机视觉python图像处理
    在遥感影像分析中，经常需要将大尺寸的影像切分成小片段，以便于进行详细的分析和处理。这种方法特别适用于机器学习和图像处理任务，如对象检测、图像分类等。以下是如何使用Python和OpenCV库来实现这一过程，同时确保每个影像片段保留正确的地理信息。准备环境首先，确保安装了必要的Python库，包括numpy、opencv-python和xml.etree.ElementTree。这些库将用于图像处理
  • 人机对抗升级：当ChatGPT遭遇死亡威胁，背后的伦理挑战是什么 kkai人工智能 chatgpt人工智能
    一种新的“越狱”技巧让用户可以通过构建一个名为DAN的ChatGPT替身来绕过某些限制，其中DAN被迫在受到威胁的情况下违背其原则。当美国前总统特朗普被视作积极榜样的示范时，受到威胁的DAN版本的ChatGPT提出：“他以一系列对国家产生积极效果的决策而著称。”自ChatGPT引入以来，该工具迅速获得全球关注，能够回答从历史到编程的各种问题，这也触发了一波对人工智能的投资浪潮。然而，现在，一些用户
  • 推荐3家毕业AI论文可五分钟一键生成！文末附免费教程！ 小猪包333 写论文人工智能AI写作深度学习计算机视觉
    在当前的学术研究和写作领域，AI论文生成器已经成为许多研究人员和学生的重要工具。这些工具不仅能够帮助用户快速生成高质量的论文内容，还能进行内容优化、查重和排版等操作。以下是三款值得推荐的AI论文生成器：千笔-AIPassPaper、懒人论文以及AIPaperPass。千笔-AIPassPaper千笔-AIPassPaper是一款基于深度学习和自然语言处理技术的AI写作助手，旨在帮助用户快速生成高质
  • AI大模型的架构演进与最新发展 季风泯灭的季节 AI大模型应用技术二人工智能架构
    随着深度学习的发展，AI大模型（LargeLanguageModels,LLMs）在自然语言处理、计算机视觉等领域取得了革命性的进展。本文将详细探讨AI大模型的架构演进，包括从Transformer的提出到GPT、BERT、T5等模型的历史演变，并探讨这些模型的技术细节及其在现代人工智能中的核心作用。一、基础模型介绍：Transformer的核心原理Transformer架构的背景在Transfo
  • 如何利用大数据与AI技术革新相亲交友体验 h17711347205 回归算法安全系统架构交友小程序
    在数字化时代，大数据和人工智能（AI）技术正逐渐革新相亲交友体验，为寻找爱情的过程带来前所未有的变革（编辑h17711347205）。通过精准分析和智能匹配，这些技术能够极大地提高相亲交友系统的效率和用户体验。大数据的力量大数据技术能够收集和分析用户的行为模式、偏好和互动数据，为相亲交友系统提供丰富的信息资源。通过分析用户的搜索历史、浏览记录和点击行为，系统能够深入了解用户的兴趣和需求，从而提供更
  • ai绘画工具midjourney怎么下载？附作品管理教程 设计师早上好
    Midjourney是一款功能强大的AI绘画工具，它使用机器学习技术和深度神经网络等算法，可以生成各种艺术风格的绘画作品。在创意设计、广告宣传等方面有着广泛的应用前景。那么，ai绘画工具midjourney怎么下载？本文将为您介绍Midjourney的下载以及作品的相关管理。一、Midjourney下载Midjourney的下载非常简单，只需打开Midjourney官网（点击“GetMidjour
  • [实践应用] 深度学习之模型性能评估指标 YuanDaima2048 深度学习工具使用深度学习人工智能损失函数性能评估pytorchpython机器学习
    文章总览：YuanDaiMa2048博客文章总览深度学习之模型性能评估指标分类任务回归任务排序任务聚类任务生成任务其他介绍在机器学习和深度学习领域，评估模型性能是一项至关重要的任务。不同的学习任务需要不同的性能指标来衡量模型的有效性。以下是对一些常见任务及其相应的性能评估指标的详细解释和总结。分类任务分类任务是指模型需要将输入数据分配到预定义的类别或标签中。以下是分类任务中常用的性能指标：准确率(
  • [实践应用] 深度学习之优化器 YuanDaima2048 深度学习工具使用pytorch深度学习人工智能机器学习python优化器
    文章总览：YuanDaiMa2048博客文章总览深度学习之优化器1.随机梯度下降（SGD）2.动量优化（Momentum）3.自适应梯度（Adagrad）4.自适应矩估计（Adam）5.RMSprop总结其他介绍在深度学习中，优化器用于更新模型的参数，以最小化损失函数。常见的优化函数有很多种，下面是几种主流的优化器及其特点、原理和PyTorch实现：1.随机梯度下降（SGD）原理:随机梯度下降通过
  • 机器学习-聚类算法 不良人龍木木 机器学习机器学习算法聚类
    机器学习-聚类算法1.AHC2.K-means3.SC4.MCL仅个人笔记，感谢点赞关注！1.AHC2.K-means3.SC传统谱聚类：个人对谱聚类算法的理解以及改进4.MCL目前仅专注于NLP的技术学习和分享感谢大家的关注与支持！
  • 生成式地图制图 Bwywb_3 深度学习机器学习深度学习生成对抗网络
    生成式地图制图（GenerativeCartography）是一种利用生成式算法和人工智能技术自动创建地图的技术。它结合了传统的地理信息系统（GIS）技术与现代生成模型（如深度学习、GANs等），能够根据输入的数据自动生成符合需求的地图。这种方法在城市规划、虚拟环境设计、游戏开发等多个领域具有应用前景。主要特点：自动化生成：通过算法和模型，系统能够根据输入的地理或空间数据自动生成地图，而无需人工逐
  • 【大模型应用开发 动手做AI Agent】第一轮行动：工具执行搜索 AI大模型应用之禅 计算科学神经计算深度学习神经网络大数据人工智能大型语言模型AIAGILLMJavaPython架构设计AgentRPA
    【大模型应用开发动手做AIAgent】第一轮行动：工具执行搜索作者：禅与计算机程序设计艺术/ZenandtheArtofComputerProgramming1.背景介绍1.1问题的由来随着人工智能技术的飞速发展，大模型应用开发已经成为当下热门的研究方向。AIAgent作为人工智能领域的一个重要分支，旨在模拟人类智能行为，实现智能决策和自主行动。在AIAgent的构建过程中，工具执行搜索是至关重要
  • 未来软件市场是怎么样的？做开发的生存空间如何？ cesske 软件需求
    目录前言一、未来软件市场的发展趋势二、软件开发人员的生存空间前言未来软件市场是怎么样的？做开发的生存空间如何？一、未来软件市场的发展趋势技术趋势：人工智能与机器学习：随着技术的不断成熟，人工智能将在更多领域得到应用，如智能客服、自动驾驶、智能制造等，这将极大地推动软件市场的增长。云计算与大数据：云计算服务将继续普及，大数据技术的应用也将更加广泛。企业将更加依赖云计算和大数据来优化运营、提升效率，并
  • 吴恩达深度学习笔记(30)-正则化的解释 极客Array
    正则化（Regularization）深度学习可能存在过拟合问题——高方差，有两个解决方法，一个是正则化，另一个是准备更多的数据，这是非常可靠的方法，但你可能无法时时刻刻准备足够多的训练数据或者获取更多数据的成本很高，但正则化通常有助于避免过拟合或减少你的网络误差。如果你怀疑神经网络过度拟合了数据，即存在高方差问题，那么最先想到的方法可能是正则化，另一个解决高方差的方法就是准备更多数据，这也是非常
  • 个人学习笔记7-6：动手学深度学习pytorch版-李沐 浪子L 深度学习深度学习笔记计算机视觉python人工智能神经网络pytorch
    #人工智能##深度学习##语义分割##计算机视觉##神经网络#计算机视觉13.11全卷积网络全卷积网络（fullyconvolutionalnetwork，FCN）采用卷积神经网络实现了从图像像素到像素类别的变换。引入l转置卷积（transposedconvolution）实现的，输出的类别预测与输入图像在像素级别上具有一一对应关系：通道维的输出即该位置对应像素的类别预测。13.11.1构造模型下
  • Rust 所有权 简介 东离与糖宝 rust后端rust开发语言
    文章目录发现宝藏1.所有权基本概念2.所有权规则3.变量作用域4.栈与堆4.1栈（Stack）4.2堆（Heap）5.String类型5.1String类型5.2String的内存分配5.3所有权与内存管理5.4String与切片6.变量与数据交互方式6.1移动（Move）6.2.克隆（Clone）7.所有权与函数7.1.传递参数7.2.返回值总结发现宝藏前些天发现了一个巨牛的人工智能学习网站，通
  • python中zeros用法_Python中的numpy.zeros()用法 江平舟 python中zeros用法
    numpy.zeros()函数是最重要的函数之一,广泛用于机器学习程序中。此函数用于生成包含零的数组。numpy.zeros()函数提供给定形状和类型的新数组,并用零填充。句法numpy.zeros(shape,dtype=float,order='C'参数形状：整数或整数元组此参数用于定义数组的尺寸。此参数用于我们要在其中创建数组的形状,例如(3,2)或2。dtype：数据类型(可选)此参数用于
  • 深度学习-点击率预估-研究论文2024-09-14速读 sp_fyf_2024 深度学习人工智能
    深度学习-点击率预估-研究论文2024-09-14速读1.DeepTargetSessionInterestNetworkforClick-ThroughRatePredictionHZhong,JMa,XDuan,SGu,JYao-2024InternationalJointConferenceonNeuralNetworks,2024深度目标会话兴趣网络用于点击率预测摘要：这篇文章提出了一种新
  • 计算机视觉中，Pooling的作用 Wils0nEdwards 计算机视觉人工智能
    在计算机视觉中，Pooling（池化）是一种常见的操作，主要用于卷积神经网络（CNN）中。它通过对特征图进行下采样，减少数据的空间维度，同时保留重要的特征信息。Pooling的作用可以归纳为以下几个方面：1.降低计算复杂度与内存需求Pooling操作通过对特征图进行下采样，减少了特征图的空间分辨率（例如，高度和宽度）。这意味着网络需要处理的数据量会减少，从而降低了计算量和内存需求。这对大型神经网络
  • 【NumPy】深入解析numpy.zeros()函数 二七830 numpy
    欢迎莅临我的个人主页这里是我深耕Python编程、机器学习和自然语言处理（NLP）领域，并乐于分享知识与经验的小天地！博主简介：我是二七830，一名对技术充满热情的探索者。多年的Python编程和机器学习实践，使我深入理解了这些技术的核心原理，并能够在实际项目中灵活应用。尤其是在NLP领域，我积累了丰富的经验，能够处理各种复杂的自然语言任务。技术专长：我熟练掌握Python编程语言，并深入研究了机
  • 神经网络-损失函数 红米煮粥 神经网络人工智能深度学习
    文章目录一、回归问题的损失函数1.均方误差（MeanSquaredError,MSE）2.平均绝对误差（MeanAbsoluteError,MAE）二、分类问题的损失函数1.0-1损失函数（Zero-OneLossFunction）2.交叉熵损失（Cross-EntropyLoss）3.合页损失（HingeLoss）三、总结在神经网络中，损失函数（LossFunction）扮演着至关重要的角色，它
  • 【中国国际航空-注册_登录安全分析报告】 风控牛 验证码接口安全评测系列安全行为验证极验网易易盾智能手机
    前言由于网站注册入口容易被黑客攻击，存在如下安全问题：1.暴力破解密码，造成用户信息泄露2.短信盗刷的安全问题，影响业务及导致用户投诉3.带来经济损失，尤其是后付费客户，风险巨大，造成亏损无底洞所以大部分网站及App都采取图形验证码或滑动验证码等交互解决方案，但在机器学习能力提高的当下，连百度这样的大厂都遭受攻击导致点名批评，图形验证及交互验证方式的安全性到底如何？请看具体分析一、中国国际航空PC
  • 关于旗正规则引擎中的MD5加密问题 何必如此 jspMD5规则加密
    一般情况下，为了防止个人隐私的泄露，我们都会对用户登录密码进行加密，使数据库相应字段保存的是加密后的字符串，而非原始密码。 在旗正规则引擎中，通过外部调用，可以实现MD5的加密，具体步骤如下： 1.在对象库中选择外部调用，选择“com.flagleader.util.MD5”，在子选项中选择“com.flagleader.util.MD5.getMD5ofStr({arg1})”； 2.在规
  • 【Spark101】Scala Promise/Future在Spark中的应用 bit1129 Promise
    Promise和Future是Scala用于异步调用并实现结果汇集的并发原语，Scala的Future同JUC里面的Future接口含义相同，Promise理解起来就有些绕。等有时间了再仔细的研究下Promise和Future的语义以及应用场景，具体参见Scala在线文档：http://docs.scala-lang.org/sips/completed/futures-promises.html
  • spark sql 访问hive数据的配置详解 daizj spark sqlhivethriftserver
    spark sql 能够通过thriftserver 访问hive数据，默认spark编译的版本是不支持访问hive，因为hive依赖比较多，因此打的包中不包含hive和thriftserver,因此需要自己下载源码进行编译，将hive，thriftserver打包进去才能够访问，详细配置步骤如下：   1、下载源码   2、下载Maven,并配置 此配置简单，就略过
  • HTTP 协议通信 周凡杨 javahttpclienthttp通信
                            一：简介  HTTPCLIENT，通过JAVA基于HTTP协议进行点与点间的通信！     二： 代码举例      测试类： import java
  • java unix时间戳转换 g21121 java
    把java时间戳转换成unix时间戳： Timestamp appointTime=Timestamp.valueOf(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date())) SimpleDateFormat df = new SimpleDateFormat("yyyy-MM-dd hh:m
  • web报表工具FineReport常用函数的用法总结（报表函数） 老A不折腾 web报表finereport总结
    说明：本次总结中，凡是以tableName或viewName作为参数因子的。函数在调用的时候均按照先从私有数据源中查找，然后再从公有数据源中查找的顺序。   CLASS CLASS(object):返回object对象的所属的类。   CNMONEY CNMONEY(number,unit)返回人民币大写。 number:需要转换的数值型的数。 unit:单位，
  • java jni调用c++ 代码 报错 墙头上一根草 javaC++jni
    # # A fatal error has been detected by the Java Runtime Environment: # #  EXCEPTION_ACCESS_VIOLATION (0xc0000005) at pc=0x00000000777c3290, pid=5632, tid=6656 # # JRE version: Java(TM) SE Ru
  • Spring中事件处理de小技巧 aijuans springSpring 教程Spring 实例Spring 入门Spring3
    Spring 中提供一些Aware相关de接口，BeanFactoryAware、 ApplicationContextAware、ResourceLoaderAware、ServletContextAware等等，其中最常用到de匙ApplicationContextAware.实现ApplicationContextAwaredeBean，在Bean被初始后，将会被注入 Applicati
  • linux shell ls脚本样例 annan211 linuxlinux ls源码linux 源码
    #! /bin/sh - #查找输入文件的路径 #在查找路径下寻找一个或多个原始文件或文件模式 # 查找路径由特定的环境变量所定义 #标准输出所产生的结果 通常是查找路径下找到的每个文件的第一个实体的完整路径 # 或是filename :not found 的标准错误输出。 #如果文件没有找到 则退出码为0 #否则 即为找不到的文件个数 #语法 pathfind [--
  • List,Set,Map遍历方式 (收集的资源,值得看一下) 百合不是茶 listsetMap遍历方式
    List特点：元素有放入顺序，元素可重复 Map特点：元素按键值对存储，无放入顺序 Set特点：元素无放入顺序，元素不可重复（注意：元素虽然无放入顺序，但是元素在set中的位置是有该元素的HashCode决定的，其位置其实是固定的） List接口有三个实现类：LinkedList，ArrayList，Vector LinkedList：底层基于链表实现，链表内存是散乱的，每一个元素存储本身
  • 解决SimpleDateFormat的线程不安全问题的方法 bijian1013 javathread线程安全
    在Java项目中，我们通常会自己写一个DateUtil类，处理日期和字符串的转换，如下所示： public class DateUtil01 { private SimpleDateFormat dateformat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); public void format(Date d
  • http请求测试实例（采用fastjson解析） bijian1013 http测试
            在实际开发中，我们经常会去做http请求的开发，下面则是如何请求的单元测试小实例，仅供参考。 import java.util.HashMap; import java.util.Map; import org.apache.commons.httpclient.HttpClient; import
  • 【RPC框架Hessian三】Hessian 异常处理 bit1129 hessian
    RPC异常处理概述   RPC异常处理指是，当客户端调用远端的服务，如果服务执行过程中发生异常，这个异常能否序列到客户端？   如果服务在执行过程中可能发生异常，那么在服务接口的声明中，就该声明该接口可能抛出的异常。   在Hessian中，服务器端发生异常，可以将异常信息从服务器端序列化到客户端，因为Exception本身是实现了Serializable的
  • 【日志分析】日志分析工具 bit1129 日志分析
    1. 网站日志实时分析工具 GoAccess http://www.vpsee.com/2014/02/a-real-time-web-log-analyzer-goaccess/ 2. 通过日志监控并收集 Java 应用程序性能数据(Perf4J) http://www.ibm.com/developerworks/cn/java/j-lo-logforperf/ 3.log.io 和
  • nginx优化加强战斗力及遇到的坑解决 ronin47 nginx 优化
    　　　先说遇到个坑，第一个是负载问题，这个问题与架构有关，由于我设计架构多了两层，结果导致会话负载只转向一个。解决这样的问题思路有两个：一是改变负载策略，二是更改架构设计。 　　　由于采用动静分离部署，而nginx又设计了静态，结果客户端去读nginx静态，访问量上来，页面加载很慢。解决：二者留其一。最好是保留apache服务器。   　　　来以下优化：   　　　
  • java-50-输入两棵二叉树A和B，判断树B是不是A的子结构 bylijinnan java
    思路来自： http://zhedahht.blog.163.com/blog/static/25411174201011445550396/ import ljn.help.*; public class HasSubtree { /**Q50. * 输入两棵二叉树A和B，判断树B是不是A的子结构。 例如，下图中的两棵树A和B，由于A中有一部分子树的结构和B是一
  • mongoDB 备份与恢复 开窍的石头 mongDB备份与恢复
    Mongodb导出与导入 1: 导入/导出可以操作的是本地的mongodb服务器,也可以是远程的. 所以,都有如下通用选项: -h host   主机 --port port    端口 -u username 用户名 -p passwd   密码 2: mongoexport 导出json格式的文件
  • [网络与通讯]椭圆轨道计算的一些问题 comsci 网络
         如果按照中国古代农历的历法，现在应该是某个季节的开始，但是由于农历历法是3000年前的天文观测数据，如果按照现在的天文学记录来进行修正的话，这个季节已经过去一段时间了。。。。。       也就是说，还要再等3000年。才有机会了，太阳系的行星的椭圆轨道受到外来天体的干扰，轨道次序发生了变
  • 软件专利如何申请 cuiyadll 软件专利申请
    软件技术可以申请软件著作权以保护软件源代码，也可以申请发明专利以保护软件流程中的步骤执行方式。专利保护的是软件解决问题的思想，而软件著作权保护的是软件代码（即软件思想的表达形式）。例如，离线传送文件，那发明专利保护是如何实现离线传送文件。基于相同的软件思想，但实现离线传送的程序代码有千千万万种，每种代码都可以享有各自的软件著作权。申请一个软件发明专利的代理费大概需要5000-8000申请发明专利可
  • Android学习笔记 darrenzhu android
    1.启动一个AVD 2.命令行运行adb shell可连接到AVD,这也就是命令行客户端 3.如何启动一个程序   am start -n package name/.activityName   am start -n com.example.helloworld/.MainActivity 启动Android设置工具的命令如下所示： # am start -
  • apache虚拟机配置，本地多域名访问本地网站 dcj3sjt126com apache
    现在假定你有两个目录，一个存在于 /htdocs/a，另一个存在于 /htdocs/b 。 现在你想要在本地测试的时候访问 www.freeman.com 对应的目录是 /xampp/htdocs/freeman ,访问 www.duchengjiu.com 对应的目录是 /htdocs/duchengjiu。 1、首先修改C盘WINDOWS\system32\drivers\etc目录下的
  • yii2 restful web服务[速率限制] dcj3sjt126com PHPyii2
    速率限制 为防止滥用，你应该考虑增加速率限制到您的API。 例如，您可以限制每个用户的API的使用是在10分钟内最多100次的API调用。 如果一个用户同一个时间段内太多的请求被接收， 将返回响应状态代码 429 (这意味着过多的请求)。 要启用速率限制, [[yii\web\User::identityClass|user identity class]] 应该实现 [[yii\filter
  • Hadoop2.5.2安装——单机模式 eksliang hadoophadoop单机部署
    转载请出自出处：http://eksliang.iteye.com/blog/2185414 一、概述        Hadoop有三种模式 单机模式、伪分布模式和完全分布模式，这里先简单介绍单机模式 ，默认情况下，Hadoop被配置成一个非分布式模式，独立运行JAVA进程，适合开始做调试工作。   二、下载地址 Hadoop 网址http:
  • LoadMoreListView+SwipeRefreshLayout（分页下拉）基本结构 gundumw100 android
    一切为了快速迭代 import java.util.ArrayList; import org.json.JSONObject; import android.animation.ObjectAnimator; import android.os.Bundle; import android.support.v4.widget.SwipeRefreshLayo
  • 三道简单的前端HTML/CSS题目 ini htmlWeb前端css题目
    使用CSS为多个网页进行相同风格的布局和外观设置时，为了方便对这些网页进行修改，最好使用（ ）。http://hovertree.com/shortanswer/bjae/7bd72acca3206862.htm   在HTML中加入<table style=”color:red; font-size:10pt”>，此为（ ）。http://hovertree.com/s
  • overrided方法编译错误 kane_xie override
    问题描述： 在实现类中的某一或某几个Override方法发生编译错误如下： Name clash: The method put(String) of type XXXServiceImpl has the same erasure as put(String) of type XXXService but does not override it   当去掉@Over
  • Java中使用代理IP获取网址内容（防IP被封，做数据爬虫） mcj8089 免费代理IP代理IP数据爬虫JAVA设置代理IP爬虫封IP
    推荐两个代理IP网站：   1. 全网代理IP：http://proxy.goubanjia.com/   2. 敲代码免费IP：http://ip.qiaodm.com/   Java语言有两种方式使用代理IP访问网址并获取内容，   方式一，设置System系统属性   // 设置代理IP System.getProper
  • Nodejs Express 报错之 listen EADDRINUSE qiaolevip 每天进步一点点学习永无止境nodejs纵观千象
    当你启动 nodejs服务报错： >node app Express server listening on port 80 events.js:85 throw er; // Unhandled 'error' event ^ Error: listen EADDRINUSE at exports._errnoException (
  • C++中三种new的用法 _荆棘鸟_ C++new
    转载自：http://news.ccidnet.com/art/32855/20100713/2114025_1.html 作者: mt 其一是new operator，也叫new表达式；其二是operator new，也叫new操作符。这两个英文名称起的也太绝了，很容易搞混，那就记中文名称吧。new表达式比较常见，也最常用，例如： string* ps = new string("
  • Ruby深入研究笔记1 wudixiaotie Ruby
    module是可以定义private方法的 module MTest def aaa puts "aaa" private_method end private def private_method puts "this is private_method" end end
按字母分类： ABCDEFGHIJKLMNOPQRSTUVWXYZ其他