0

我想将 CNN 结构扩展到 CCPCCPCCP 结构。但是，我收到以下错误：我不能做任何事情，因为它不起作用，我该如何解决这个问题？任何帮助将不胜感激。

我的代码有问题吗？还有其他方法吗？如何解决？

import numpy as np
import tensorflow as tf
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense,Dropout
from tensorflow.keras.optimizers import Adam

# CIFAR-10 데이터셋을 읽고 신경망에 입력할 형태로 변환
(x_train,y_train),(x_test,y_test)=cifar10.load_data()
x_train=x_train.astype(np.float32)/255.0
x_test=x_test.astype(np.float32)/255.0
y_train=tf.keras.utils.to_categorical(y_train,10)
y_test=tf.keras.utils.to_categorical(y_test,10)

# 신경망 모델 설계
cnn=Sequential()
cnn.add(Conv2D(32,(3,3),activation='relu',input_shape=(32,32,3)))
cnn.add(Conv2D(32,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Dropout(0.25))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Dropout(0.25))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Flatten())
cnn.add(Dense(512,activation='relu'))
cnn.add(Dropout(0.5))
cnn.add(Dense(10,activation='softmax'))

# 신경망 모델 학습
cnn.compile(loss='categorical_crossentropy',optimizer=Adam(),metrics=['accuracy'])
hist=cnn.fit(x_train,y_train,batch_size=128,epochs=30,validation_data=(x_test,y_test),verbose=2)

# 신경망 모델 정확률 평가
res=cnn.evaluate(x_test,y_test,verbose=0)
print("정확률은",res[1]*100)

import matplotlib.pyplot as plt

# 정확률 그래프
plt.plot(hist.history['accuracy'])
plt.plot(hist.history['val_accuracy'])
plt.title('Model accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train','Validation'], loc='best')
plt.grid()
plt.show()

# 손실 함수 그래프
plt.plot(hist.history['loss'])
plt.plot(hist.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train','Validation'],loc='best')
plt.grid()
plt.show()

# Train data의 20%를 validation set으로 설정
# 성능 평가는 test data만 이용
split_percent = 0.2
split_index = int(x_train.shape[0]*(1-split_percent))
x_t = x_train[:split_index]  #x_train
y_t = y_train[:split_index]  #y_train
x_v = x_train[split_index:]  #x_val
y_v = y_train[split_index:]  #y_val

错误 ：

Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz
170500096/170498071 [==============================] - 17s 0us/step
---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs, op_def)
   1879   try:
-> 1880     c_op = pywrap_tf_session.TF_FinishOperation(op_desc)
   1881   except errors.InvalidArgumentError as e:

InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for '{{node max_pooling2d_2/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", explicit_paddings=[], ksize=[1, 2, 2, 1], padding="VALID", strides=[1, 2, 2, 1]](Placeholder)' with input shapes: [?,1,1,64].

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
15 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs, op_def)
   1881   except errors.InvalidArgumentError as e:
   1882     # Convert to ValueError for backwards compatibility.
-> 1883     raise ValueError(str(e))
   1884 
   1885   return c_op

ValueError: Negative dimension size caused by subtracting 2 from 1 for '{{node max_pooling2d_2/MaxPool}} = MaxPool[T=DT_FLOAT, data_format="NHWC", explicit_paddings=[], ksize=[1, 2, 2, 1], padding="VALID", strides=[1, 2, 2, 1]](Placeholder)' with input shapes: [?,1,1,64].

这是我添加的代码。

# C-C-P-C-C-P
import numpy as np
import tensorflow as tf
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense,Dropout
from tensorflow.keras.optimizers import Adam

# CIFAR-10 데이터셋을 읽고 신경망에 입력할 형태로 변환
(x_train,y_train),(x_test,y_test)=cifar10.load_data()
x_train=x_train.astype(np.float32)/255.0
x_test=x_test.astype(np.float32)/255.0
y_train=tf.keras.utils.to_categorical(y_train,10)
y_test=tf.keras.utils.to_categorical(y_test,10)

# 신경망 모델 설계
cnn=Sequential()
cnn.add(Conv2D(32,(3,3),activation='relu',input_shape=(32,32,3)))
cnn.add(Conv2D(32,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Dropout(0.25))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Flatten())
cnn.add(Dropout(0.25))
cnn.add(Dense(10,activation='softmax'))

# 신경망 모델 학습
cnn.compile(loss='categorical_crossentropy',optimizer=Adam(),metrics=['accuracy'])
hist=cnn.fit(x_train,y_train,batch_size=128,epochs=30,validation_data=(x_test,y_test),verbose=2)

# 신경망 모델 정확률 평가
res=cnn.evaluate(x_test,y_test,verbose=0)
print("정확률은",res[1]*100)

import matplotlib.pyplot as plt

# 정확률 그래프
plt.plot(hist.history['accuracy'])
plt.plot(hist.history['val_accuracy'])
plt.title('Model accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train','Validation'], loc='best')
plt.grid()
plt.show()

# 손실 함수 그래프
plt.plot(hist.history['loss'])
plt.plot(hist.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train','Validation'],loc='best')
plt.grid()
plt.show()

# Train data의 20%를 validation set으로 설정
# 성능 평가는 test data만 이용
split_percent = 0.2
split_index = int(x_train.shape[0]*(1-split_percent))
x_t = x_train[:split_index]  #x_train
y_t = y_train[:split_index]  #y_train
x_v = x_train[split_index:]  #x_val
y_v = y_train[split_index:]  #y_val




# C-C-P-C-C-P-C-C-P 구조
import numpy as np
import tensorflow as tf
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense,Dropout
from tensorflow.keras.optimizers import Adam

# CIFAR-10 데이터셋을 읽고 신경망에 입력할 형태로 변환
(x_train,y_train),(x_test,y_test)=cifar10.load_data()
x_train=x_train.astype(np.float32)/255.0
x_test=x_test.astype(np.float32)/255.0
y_train=tf.keras.utils.to_categorical(y_train,10)
y_test=tf.keras.utils.to_categorical(y_test,10)

# 신경망 모델 설계
cnn=Sequential()
cnn.add(Conv2D(32,(3,3),activation='relu',input_shape=(32,32,3)))
cnn.add(Conv2D(32,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Dropout(0.25))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Dropout(0.25))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(1,1)))
cnn.add(Flatten())
cnn.add(Dense(512,activation='relu'))
cnn.add(Dropout(0.5))
cnn.add(Dense(10,activation='softmax'))

# 신경망 모델 학습
cnn.compile(loss='categorical_crossentropy',optimizer=Adam(),metrics=['accuracy'])
hist=cnn.fit(x_train,y_train,batch_size=128,epochs=30,validation_data=(x_test,y_test),verbose=2)

# 신경망 모델 정확률 평가
res=cnn.evaluate(x_test,y_test,verbose=0)
print("정확률은",res[1]*100)

import matplotlib.pyplot as plt

# 정확률 그래프
plt.plot(hist.history['accuracy'])
plt.plot(hist.history['val_accuracy'])
plt.title('Model accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train','Validation'], loc='best')
plt.grid()
plt.show()

# 손실 함수 그래프
plt.plot(hist.history['loss'])
plt.plot(hist.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train','Validation'],loc='best')
plt.grid()
plt.show()

# Train data의 20%를 validation set으로 설정
# 성능 평가는 test data만 이용
split_percent = 0.2
split_index = int(x_train.shape[0]*(1-split_percent))
x_t = x_train[:split_index]  #x_train
y_t = y_train[:split_index]  #y_train
x_v = x_train[split_index:]  #x_val
y_v = y_train[split_index:]  #y_val
4

1 回答 1

1

输入形状为 (32,32,3)，您有多个卷积和池化层。在每一层，输入的大小都会缩小。因此，您应该注意输入通过层的过程。例如，每个池化层 (2,2) 使输入大小减半。

在您的情况下，C-C-P-C-C-P输入的大小将为 (None,5,5,64) 并将具有 (5,5) 大小的输入提供给另外两个卷积，然后 maxpooling 使其大小减小到 (1,1) 和 maxpooling不能对大小 (1,1) 的输入采取任何行动。因此，重新组织您的图层并注意您的输入大小及其变化。

例如，您可以删除最后C-C-P一层以避免使输入变得更小。

import numpy as np
import tensorflow as tf
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D,MaxPooling2D,Flatten,Dense,Dropout
from tensorflow.keras.optimizers import Adam

# CIFAR-10 데이터셋을 읽고 신경망에 입력할 형태로 변환
(x_train,y_train),(x_test,y_test)=cifar10.load_data()
x_train=x_train.astype(np.float32)/255.0
x_test=x_test.astype(np.float32)/255.0
y_train=tf.keras.utils.to_categorical(y_train,10)
y_test=tf.keras.utils.to_categorical(y_test,10)

# 신경망 모델 설계
cnn=Sequential()
cnn.add(Conv2D(32,(3,3),activation='relu',input_shape=(32,32,3)))
cnn.add(Conv2D(32,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Dropout(0.25))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(Conv2D(64,(3,3),activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Dropout(0.25))
#cnn.add(Conv2D(64,(3,3),activation='relu'))
#cnn.add(Conv2D(64,(3,3),activation='relu'))
#cnn.add(MaxPooling2D(pool_size=(2,2)))
cnn.add(Flatten())
cnn.add(Dense(512,activation='relu'))
cnn.add(Dropout(0.5))
cnn.add(Dense(10,activation='softmax'))

您可以通过以下方式检查尺寸变化model.summary()：

model.summary()

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_6 (Conv2D)            (None, 30, 30, 32)        896       
_________________________________________________________________
conv2d_7 (Conv2D)            (None, 28, 28, 32)        9248      
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 14, 14, 32)        0         
_________________________________________________________________
dropout_2 (Dropout)          (None, 14, 14, 32)        0         
_________________________________________________________________
conv2d_8 (Conv2D)            (None, 12, 12, 64)        18496     
_________________________________________________________________
conv2d_9 (Conv2D)            (None, 10, 10, 64)        36928     
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 5, 5, 64)          0         
_________________________________________________________________
dropout_3 (Dropout)          (None, 5, 5, 64)          0         
_________________________________________________________________
flatten (Flatten)            (None, 1600)              0         
_________________________________________________________________
dense (Dense)                (None, 512)               819712    
_________________________________________________________________
dropout_4 (Dropout)          (None, 512)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 10)                5130      
=================================================================
Total params: 890,410
Trainable params: 890,410
Non-trainable params: 0
_________________________________________________________________
于 2021-06-16T07:11:10.990 回答