问Tensorflow度量混淆:准确性和损失都很高，但混淆矩阵表示预测错误

EN

import tensorflow as tf
from tensorflow.keras.applications.vgg16 import VGG16

model = VGG16(include_top=True,
              weights=None,
              input_tensor=None,
              pooling=None,
              classes=len(labels),
              classifier_activation="softmax")


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

# Rescale by 1/255, add data augmentation:
train_datagen = ImageDataGenerator(
      rescale=1./255,
      width_shift_range=0.2,
      brightness_range=[0.8,1.2],
      fill_mode='nearest')

# Note that the validation data should not be augmented!
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        # This is the target directory
        train_dir,
        # All images will be resized to 224x224
        target_size=(224, 224),
        batch_size=20,
        # one hot label for multiclass
        class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=(224, 224),
        batch_size=20,
        class_mode='categorical')

model.compile(loss='categorical_crossentropy',
              optimizer=optimizers.RMSprop(learning_rate=2e-5),
              metrics=[tf.keras.metrics.CategoricalAccuracy(), 
                       tf.keras.metrics.Precision(), 
                       tf.keras.metrics.Recall()])

# Train the model:
history = model.fit(
      train_generator,
      steps_per_epoch=100,
      epochs=100,
      validation_data=validation_generator,
      validation_steps=50,
      verbose=2)

test_generator = test_datagen.flow_from_directory(
        test_dir,
        target_size=(224, 224),
        batch_size=20,
        class_mode='categorical')

test_loss, test_acc, test_precison, test_recall = model.evaluate(test_generator, steps=50)
print('test_acc:' + str(test_acc))

import numpy as np
import sklearn.metrics

# Print confuision matrix for test set:

test_pred_raw = model.predict(test_generator)
print('raw preditcitons:')
print(test_pred_raw)

test_pred = np.argmax(test_pred_raw, axis=1)
print('prediction:')
print(test_pred)

test_labels = test_generator.classes
print('labels')
print(test_labels)

# Calculate accuracy manualy:
my_test_acc = sum(test_pred == test_labels) / len(test_labels)
print('My_acc:')
print(my_test_acc)

# Calculate the confusion matrix using sklearn.metrics
cm = sklearn.metrics.confusion_matrix(test_labels, test_pred)    
figure = plot_confusion_matrix(cm, class_names=labels)