使用 categorical_crossentropy 在 TensorFlow 中訓練圖像分類時出現“ValueError: Shapes (None, 1) and (None, 32) are incompatible”

Question

我正在嘗試訓練機器學習 model 來對圖像進行分類，但是當我嘗試使用 categorical_crossentropy 損失 function 時遇到了一些問題。

這是我用來生成 model 的代碼。

import numpy as np
import os
import PIL
import PIL.Image
import tensorflow as tf
import pathlib
import glob
import matplotlib.pyplot as plt
from tensorflow.keras import layers
from tensorflow.keras import callbacks 
from tensorflow import keras
from datetime import datetime
import tensorboard

if __name__ == "__main__":
    #This first section mostly follows the tutorial at https://www.tensorflow.org/tutorials/images/classification
    data_dir = "img_directories"
    image_count = len(list(glob.glob(f'{data_dir}/*/*.png')))
    print(image_count)

    batch_size = 128
    img_height = 100 
    img_width = 100

    #Set up training data
    val_split = 0.2

    train_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=val_split,
    subset="training",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)

    #Set up testing data
    val_ds = tf.keras.preprocessing.image_dataset_from_directory(
    data_dir,
    validation_split=val_split,
    subset="validation",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size, 
    color_mode='rgb')

    class_names = train_ds.class_names
    print(class_names)

    num_classes = len(train_ds.class_names)

    #   Normalize data
    normalization_layer = layers.experimental.preprocessing.Rescaling(1./255)
    normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))
    image_batch, labels_batch = next(iter(normalized_ds))

    #Set up model

    model = tf.keras.Sequential()
    # model.add(layers.experimental.preprocessing.Rescaling((1./255),input_shape=(100, 100, 3)))
    model.add(layers.Conv2D(64, (3,3), activation='relu',input_shape=(img_height, img_width, 3)))
    model.add(layers.MaxPooling2D(pool_size=(2,2)))
    model.add(layers.Dropout(0.2))
    model.add(layers.Conv2D(64, (5,5)))
    model.add(layers.MaxPooling2D(pool_size=(3,3)))
    model.add(layers.Dense(64))
    model.add(layers.Flatten())
    model.add(layers.Dense(num_classes, activation='softmax'))
    
    model.compile(optimizer='adam',
                loss='categorical_crossentropy',
                metrics=['accuracy'])


    model.summary()

    earlystopping = callbacks.EarlyStopping(monitor ="val_loss",  
                                        mode ="min", patience = 7,  
                                        restore_best_weights = True) 


    history=model.fit(
    normalized_ds,
    validation_data=val_ds,
    epochs=100,
    callbacks=[earlystopping]
    )

將損失 function 設置為categorical_crossentropy會給我以下錯誤：

    ValueError: Shapes (None, 1) and (None, 32) are incompatible

其中 32 是我擁有的數據集中的類數，因此我的 output 層存在問題。

但是，當我嘗試使用sparse_categorical_crossentropy運行它時，它似乎沒有問題

因為我的課程太少，我該如何讓它與categorical_crossentropy一起工作？

編輯：

我已經嘗試過類似的方法，但我仍然遇到與原始錯誤類似的錯誤。

    val_imgs, val_labels = next(iter(val_ds))
    val_labels_one_hot=tf.one_hot(labels_batch,num_classes)

    model.compile(optimizer='adam',
                loss='categorical_crossentropy',
                metrics=['accuracy'])


    model.summary()

    earlystopping = callbacks.EarlyStopping(monitor ="val_loss",  
                                        mode ="min", patience = 7,  
                                        restore_best_weights = True) 

    history=model.fit(
    train_ds,
    validation_data=[val_imgs,val_labels_one_hot],
    epochs=100,
    callbacks=[earlystopping]
    )

Answer 1

sparse_categorical_crossentropy （ 文檔）假設整數，而categorical_crossentropy （ 文檔）假設單熱編碼向量。 您可以同時使用兩者，但sparse_categorical_crossentropy有效，因為您為每個 label 提供形狀(None, 1) 。

總之，如果您想使用categorical_crossentropy ，您需要將當前目標張量轉換為單熱編碼（然后由最終的 softmax 層使用）。