tensorflow代码错误ValueError：调用层“sequential”时遇到异常（类型Sequential）

Question

'从本地文件中学习。 有4760个训练数据和240个测试数据。 我收到这些错误，有什么问题？ '''

train_dir=''
train_csv = pd.read_csv(train_dir+'train.csv')
train_images=[]
train_labels=[]

for file in train_csv['data']:
    image=np.array(Image.open(train_dir+'train/'+file))
    train_images.append(image)
for label in train_csv['label']:
    train_labels.append(label)

train_images=np.array(train_images)
train_labels=np.array(train_labels)

test_dir=''
test_csv = pd.read_csv(test_dir+'test.csv')

test_images=[]
test_labels=[]

for file in test_csv['data']:
    image=np.array(Image.open(test_dir+'test/'+file))
    test_images.append(image)
for label in test_csv['label']:
    test_labels.append(label)

test_images=np.array(test_images)
test_labels=np.array(test_labels)

import numpy as np
import tensorflow as tf
from tensorflow.keras.datasets import fashion_mnist

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import SGD,Adam,Adagrad,RMSprop


print("train_images",train_images.shape)
print("train_labels",train_labels.shape)


print("test_images",test_images.shape)
print("test_labels",test_labels.shape)

train_images=train_images.reshape(4760,4096,3)
test_images=test_images.reshape(240,4096,3)


x_train=train_images.astype(np.float32)/255.0
x_test=test_images.astype(np.float32)/255.0




y_train=tf.keras.utils.to_categorical(train_labels,5)
y_test=tf.keras.utils.to_categorical(test_labels,5)


print("x_train",x_train.shape)
print("y_train",y_train.shape)


print("x_test",x_test.shape)
print("y_test",y_test.shape)

n_input=4096
n_hidden1=5000
n_hidden2=2500
n_hidden3=2500
n_hidden4=2500
n_output=5

batch_siz=256
n_epoch=5


def build_model():
    model=Sequential()
    model.add(Dense(units=n_hidden1,activation='relu',input_shape=(n_input,)))
    model.add(Dense(units=n_hidden2,activation='relu'))
    model.add(Dense(units=n_hidden3,activation='relu'))
    model.add(Dense(units=n_hidden4,activation='relu'))
    model.add(Dense(units=n_output,activation='softmax'))
    return model



dmlp_adam=build_model()
dmlp_adam.compile(loss='categorical_crossentropy',optimizer=Adam(),metrics=['accuracy'])
hist_adam=dmlp_adam.fit(x_train,y_train,batch_size=batch_siz,epochs=n_epoch,validation_data=(x_test,y_test),verbose=2)

''' 'error:WARNING:tensorflow:Model 是用形状 (None, 4096) 构造的输入 KerasTensor(type_spec=TensorSpec(shape=(None, 4096), dtype=tf.float32, name='dense_input'), name ='dense_input', description="created by layer 'dense_input'")，但它是在形状不兼容的输入上调用的 (None, 4096, 3)。

ValueError：调用层“sequential”（类型 Sequential）时遇到异常。

Input 0 of layer "dense" is incompatible with the layer: expected axis -1 of input shape to have value 4096, but received input with shape (None, 4096, 3)

Call arguments received by layer "sequential" (type Sequential):
  • inputs=tf.Tensor(shape=(None, 4096, 3), dtype=float32)
  • training=True
  • mask=None

'

Answer 1

选择过多的神经元可能会导致过度拟合并增加网络的训练时间。 隐藏神经元（单元）的数量最好介于输入层的大小和输出层的大小之间。 请在下面找到工作代码。

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense,Flatten
import numpy as np

x_train=tf.random.uniform((4760,4096,3))
x_test=tf.random.uniform((240,4096,3))

# It generates labels randomly within the range of 0 to 5
import random
def Rand(start, end, num):
    res = []
 
    for j in range(num):
        res.append(random.randint(start, end))
 
    return res

# Train and Test labels
y_test=np.array(Rand(0,4,240))
y_train=np.array(Rand(0,4,4760))    

y_train=tf.keras.utils.to_categorical(y_train)
y_test=tf.keras.utils.to_categorical(y_test)

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

# Changing the input shape from 4096 to (4096,3) resolves the issue as the input is of shape (4096,3).
n_input=(4096,3)  
n_hidden1= 128  #5000
n_hidden2= 64  #2500
n_hidden3= 32  #2500
n_hidden4= 16  #2500
n_output=5

batch_siz=256
n_epoch=5
    
def build_model():
    model=Sequential()
    model.add(Dense(units=n_hidden1,activation='relu',input_shape=(n_input)))
    model.add(Dense(units=n_hidden2,activation='relu'))
    model.add(Dense(units=n_hidden3,activation='relu'))
    model.add(Dense(units=n_hidden4,activation='relu'))

    # Added flatten layer to overcome ValueError: Shapes (None, 5) and (None, 4096, 5) are incompatible
    model.add(Flatten())

    model.add(Dense(units=n_output,activation='softmax'))
    return model    

model=build_model()   
model.summary()     
model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['accuracy'])
model.fit(x_train,y_train,batch_size=batch_siz,epochs=n_epoch,validation_data=(x_test,y_test),verbose=2)