我有同样的问题，总是一样的。当我运行一个混淆矩阵的结果显示只有0和1。它不应该这样去，这里的问题。

它应该在0和20之间，但它不是。我做错了什么？我怎么能解决这个问题。
这是我用的代码

from tensorflow import keras
from keras.preprocessing.image import ImageDataGenerator

imagegen = ImageDataGenerator()

test_datagen = ImageDataGenerator(
    featurewise_center=True,
    featurewise_std_normalization=True,
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    horizontal_flip=True,
)

test_generator = test_datagen.flow_from_directory(r"C:\Users\User\Desktop\Problem\New_one\Testing_Data",
                                                    class_mode="categorical",
                                                    shuffle=False,
                                                    batch_size=3,
                                                    target_size=(200, 200))

model = keras.models.load_model(r"C:\Users\User\Desktop\Problem\New_one\InceptionV3.h5")

import pandas as pd
import seaborn as sn
import matplotlib.pyplot as plt

data = {'y_Actual': ["Lablae", "Long", "Maejam(Ceiyng-saen-hnoy)","Maejam(Ceiyng-saen-luang)","Maejam(Hong-pi)","Maejam(Hong-poi)","Maejam(Kan-seiyn-sam)",
                    "Maejam(Kom-rup-nk)","Maejam(Kom-whua-mon-nai-nk-non)","Maejam(Kud-kho-bed)","Maejam(La-kon-klang)","Maejam(La-kon-luang)",
                    "Maejam(La-kon-noy)","Maejam(Lay-kan-sam-aew)","Maejam(Nak-kum)","Maejam(Nk-kum)","Maejam(Nok-nk-kum)","Maejan(Khan-aew-u)",
                    "Muang-nan","Sri-sat-shanalai"],
        'y_Predicted': ["Lablae", "Long", "Maejam(Ceiyng-saen-hnoy)","Maejam(Ceiyng-saen-luang)","Maejam(Hong-pi)","Maejam(Hong-poi)","Maejam(Kan-seiyn-sam)",
                    "Maejam(Kom-rup-nk)","Maejam(Kom-whua-mon-nai-nk-non)","Maejam(Kud-kho-bed)","Maejam(La-kon-klang)","Maejam(La-kon-luang)",
                    "Maejam(La-kon-noy)","Maejam(Lay-kan-sam-aew)","Maejam(Nak-kum)","Maejam(Nk-kum)","Maejam(Nok-nk-kum)","Maejan(Khan-aew-u)",
                    "Muang-nan","Sri-sat-shanalai"]}

df = pd.DataFrame(data, columns=['y_Actual','y_Predicted'])
confusion_matrix = pd.crosstab(df['y_Actual'], df['y_Predicted'], rownames=['Actual'], colnames=['Predicted'], margins = True)

sn.heatmap(confusion_matrix, annot=True)
plt.show()

我在这里承认。我不擅长编程，而且永远也不会。这是我唯一的问题，我需要解决它，这样我才能进步。
另外，我的英语写得不好，所以我可能在这里犯了一些错误。如果我犯了，那么我道歉。