ValueError: ' logits '和' labels '必须具有相同的形状

Question

我试图使用Imagenet V2迁移学习多类分类(6类)，但得到以下错误。有人能帮忙吗?

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

我从Andrew Ng的CNN课程中借用了这个代码，我花了一段时间，但原始代码是用于二进制分类的。我试图修改它的多类分类，但得到了这个错误。下面是我的代码:

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:找到属于6个类的600个文件。找到属于6个类的600个文件。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

发现bug:

我必须在模型编译器中将损失重新定义为loss='sparse_categorical_crossentropy'，而最初定义为loss=tf.keras.losses.BinaryCrossentropy(from_logits=True)。

详细信息请参考SO线程将Keras模型从二元分类改为多分类。

Answer 2

看起来你还必须对你的标签进行一次热编码，即不是为属于i-th类的图像的标签提供数字i(在0和5之间，包括)，它的形状为(None, 1)，提供除索引i处的1之外的所有0的数组，它的形状为(None, 6)。那么labels和logits的形状是一样的。

Answer 3

很容易你需要匹配logits输出，或者你需要在模型结束时删除softmax或distribution。

几乎正确，我对未定义的data_augmentation进行了一些更改。

它将有输出，但计算是基于输出期望的，尝试使用平均值，你看到错误或使用类熵，将提供不同的行为。

有人告诉它提高了精度输出，因为他们使用二进制交叉熵，但不是这种方式，当使用二进制序列时，它会高度提高，看看ALE游戏的例子(街头霸王)

[示例]:

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('...')

[输出]

示例