valueerror：`logits'和`labels'必须具有相同的形状

Question

我正在尝试将带有传输学习的Imagenet V2用于多类分类（6类），但会遇到以下错误。有人可以帮忙吗？

ValueError: `logits` and `labels` must have the same shape, received ((None, 6) vs (None, 1)).

我从Andrew Ng的CNN课程中借了此代码，我花了一段时间，但原始代码是用于二进制分类的。我试图将其修改以进行多类分类，但出现了此错误。这是我的代码：

import matplotlib.pyplot as plt
import numpy as np
import os
import tensorflow as tf
import tensorflow.keras.layers as tfl
import datetime

from tensorflow.keras.preprocessing import image_dataset_from_directory
from tensorflow.keras.layers.experimental.preprocessing import RandomFlip, RandomRotation

BATCH_SIZE = 16
IMG_SIZE = (160, 160)
training_directory = "/content/drive/MyDrive/Microscopy Data/04112028_multiclass_maiden/Training/Actin"
validation_directory = "/content/drive/MyDrive/Microscopy Data/04112028_multiclass_maiden/Validation/Actin"
train_dataset = image_dataset_from_directory(training_directory,
                                             shuffle=True,
                                             batch_size=BATCH_SIZE,
                                             image_size=IMG_SIZE,
                                             seed=42)
validation_dataset = image_dataset_from_directory(validation_directory,
                                             shuffle=True,
                                             batch_size=BATCH_SIZE,
                                             image_size=IMG_SIZE,
                                             seed=42)

输出： 找到了600个属于6个类的文件。 找到了600个属于6个类的文件。 代码继续...

class_names = train_dataset.class_names

AUTOTUNE = tf.data.experimental.AUTOTUNE
train_dataset = train_dataset.prefetch(buffer_size=AUTOTUNE)

preprocess_input = tf.keras.applications.mobilenet_v2.preprocess_input

IMG_SHAPE = IMG_SIZE + (3,)
base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
                                               include_top=True,
                                               weights='imagenet')

def huvec_model (image_shape=IMG_SIZE, data_augmentation=data_augmenter()):
    ''' Define a tf.keras model for binary classification out of the MobileNetV2 model
    Arguments:
        image_shape -- Image width and height
        data_augmentation -- data augmentation function
    Returns:
    Returns:
        tf.keras.model
    '''
    
    
    input_shape = image_shape + (3,)
    
    # Freeze the base model by making it non trainable
    # base_model.trainable = None 

    # create the input layer (Same as the imageNetv2 input size)
    # inputs = tf.keras.Input(shape=None) 
    
    # apply data augmentation to the inputs
    # x = None
    
    # data preprocessing using the same weights the model was trained on
    # x = preprocess_input(None) 
    
    # set training to False to avoid keeping track of statistics in the batch norm layer
    # x = base_model(None, training=None) 
    
    # Add the new Binary classification layers
    # use global avg pooling to summarize the info in each channel
    # x = None()(x) 
    #include dropout with probability of 0.2 to avoid overfitting
    # x = None(None)(x)
        
    # create a prediction layer with one neuron (as a classifier only needs one)
    # prediction_layer = None
    
    base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
                                               include_top=False,
                                               weights='imagenet')
    base_model.trainable = False
    inputs = tf.keras.Input(shape=input_shape)
    x = data_augmentation(inputs)
    x = preprocess_input(x)
    x = base_model(x, training=False)
    x = tf.keras.layers.GlobalAveragePooling2D()(x)
    x = tfl.Dropout(.2)(x)
    prediction_layer = tf.keras.layers.Dense(units = len(class_names), activation='softmax')
    # YOUR CODE ENDS HERE
    
    outputs = prediction_layer(x) 
    model = tf.keras.Model(inputs, outputs)
    
    return model

model2 = huvec_model(IMG_SIZE)

base_model.trainable = True
# Let's take a look to see how many layers are in the base model
print("Number of layers in the base model: ", len(base_model.layers))

# Fine-tune from this layer onwards
fine_tune_at = 120

# Freeze all the layers before the `fine_tune_at` layer
# for layer in base_model.layers[:fine_tune_at]:
#    layer.trainable = None
    
# Define a BinaryCrossentropy loss function. Use from_logits=True
# loss_function=None
# Define an Adam optimizer with a learning rate of 0.1 * base_learning_rate
# optimizer = None
# Use accuracy as evaluation metric
# metrics=None
base_learning_rate = 0.01
# YOUR CODE STARTS HERE
for layer in base_model.layers[:fine_tune_at]:
    layer.trainable = False
loss_function=tf.keras.losses.BinaryCrossentropy(from_logits=True)
optimizer= tf.keras.optimizers.Adam(learning_rate=0.1*base_learning_rate)
metrics=['accuracy']

# YOUR CODE ENDS HERE
model2.compile(loss=loss_function,
              optimizer = optimizer,
              metrics=metrics)

initial_epochs = 5
history = model2.fit(train_dataset, validation_data=validation_dataset, epochs=initial_epochs)

Answer 1

找到了错误：

我必须在模型编译器中重新定义损失，为lose ='Sparse_categorical_crossentropy'最初定义为loss = tf.keras.losses.losses.binarycrossentropy（binarycrossentropy（from_logits）代码>。

请参阅so thread 更改Keras模型分类有关更多详细信息。

Answer 2

看起来您还必须对标签进行单速编码，即，对于属于i i <的图像标签，而不是编号i（0和5之间） /code> - th类，是形状（无，1），提供了所有0的数组，除了in Index i的a 1，该数组是shape i的（none，6）< /代码>。然后标签具有与logits相同的形状。

Answer 3

很容易匹配逻辑输出，或者需要在模型末尾删除SoftMax或分发。

几乎是正确的，我在有效的未定义的data_augmentation上改变了一些。

它将具有输出，但计算是基于输出期望尝试使用均值的均值，您会看到错误或使用将提供不同行为的类熵。

有人告诉它，当他们使用二进制交叉熵时，它提高了准确性输出，但并非如此，当使用二进制序列时，它会高度提高，请参见ALE GAMES（Street Fighters）

[sample]：

import os
from os.path import exists

import tensorflow as tf

import matplotlib.pyplot as plt

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
Variables
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
BATCH_SIZE = 16
IMG_SIZE = (160, 160)
PATH = 'F:\\datasets\\downloads\\sample\\cats_dogs\\training'
training_directory = os.path.join(PATH, 'train')
validation_directory = os.path.join(PATH, 'validation')

train_dataset = tf.keras.utils.image_dataset_from_directory(training_directory,
            shuffle=True,
            batch_size=BATCH_SIZE,
            image_size=IMG_SIZE,
            seed=42)
validation_dataset = tf.keras.utils.image_dataset_from_directory(validation_directory,
            shuffle=True,
            batch_size=BATCH_SIZE,
            image_size=IMG_SIZE,
            seed=42)
    
class_names = train_dataset.class_names
print( "class_names: " + str( class_names ) )

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
Functions
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
def huvec_model (image_shape=IMG_SIZE, data_augmentation = tf.keras.Sequential([ tf.keras.layers.RandomFlip('horizontal'), tf.keras.layers.RandomRotation(0.2), ])):
# def huvec_model (image_shape=IMG_SIZE, data_augmentation=data_augmenter()):
    ''' Define a tf.keras model for binary classification out of the MobileNetV2 model
    Arguments:
    image_shape -- Image width and height
    data_augmentation -- data augmentation function
    Returns:
    Returns:
    tf.keras.model
    '''

    input_shape = image_shape + (3,)
    
    base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
        include_top=False,
        weights='imagenet')
    base_model.trainable = False
    inputs = tf.keras.Input(shape=input_shape)
    x = data_augmentation(inputs)
    x = preprocess_input(x)
    x = base_model(x, training=False)
    x = tf.keras.layers.GlobalAveragePooling2D()(x)
    x = tf.keras.layers.Dropout(.2)(x)
    prediction_layer = tf.keras.layers.Dense(units = len(class_names), activation='softmax')

    outputs = prediction_layer(x) 
    model = tf.keras.Model(inputs, outputs)

    return model

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
DataSet
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
AUTOTUNE = tf.data.experimental.AUTOTUNE
train_dataset = train_dataset.prefetch(buffer_size=AUTOTUNE)
preprocess_input = tf.keras.applications.mobilenet_v2.preprocess_input

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Initialize
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
IMG_SHAPE = IMG_SIZE + (3,)
base_model = tf.keras.applications.MobileNetV2(input_shape=IMG_SHAPE,
            include_top=True,
            weights='imagenet')

base_model.summary()

model2 = huvec_model(IMG_SIZE)

base_model.trainable = True
# Let's take a look to see how many layers are in the base model
print("Number of layers in the base model: ", len(base_model.layers))

# Fine-tune from this layer onwards
fine_tune_at = 120
base_learning_rate = 0.01

for layer in base_model.layers[:fine_tune_at]:
    layer.trainable = False
    
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Optimizer
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
optimizer = tf.keras.optimizers.Adam(learning_rate=0.1*base_learning_rate)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Loss Fn
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""                               
lossfn = tf.keras.losses.BinaryCrossentropy(from_logits=False)

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Summary
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
model2.compile(optimizer=optimizer, loss=lossfn, metrics=[ 'accuracy' ])

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Training
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
history = model2.fit(train_dataset, validation_data=validation_dataset, epochs=5)

input('...')

[output]

示例