如何评估使用 flow_from_directory 加载数据的模型？

Question

您好，我训练了一个模型，并且加载了图像：batch_size = 16# Data augmentation and preprocesstrain_datagen = ImageDataGenerator(rescale=1./255,    shear_range=0.2,    zoom_range=0.2,    horizontal_flip=True,    validation_split=0.20) # set validation split# Train datasettrain_generator = train_datagen.flow_from_directory(    'PetImages/train',    target_size=(244, 244),    batch_size=batch_size,    class_mode='binary',    subset='training') # set as training data# Validation datasetvalidation_generator = train_datagen.flow_from_directory(    'PetImages/train',    target_size=(244, 244),    batch_size=batch_size,    class_mode='binary',    subset='validation') # set as validation datatest_datagen = ImageDataGenerator(rescale=1./255)# Test datasettest_datagen = test_datagen.flow_from_directory(    'PetImages/test')问题是如何使用 test_datagen 评估模型？我尝试了以下但没有工作：x=[]y=[]test_datagen.reset()for i in range(test_datagen.__len__()):    a,b=test_datagen.next()    x.append(a)    y.append(b)x=np.array(x)y=np.array(y)print(x.shape)print(y.shape)score = model.evaluate(x, y)print(f'Test loss: {score[0]} / Test accuracy: {score[1]}')我收到此错误：无法将 NumPy 数组转换为张量（不支持的对象类型 numpy.ndarray）。

Answer 1

最后我用：

score = model.evaluate_generator(test_datagen, steps=STEP_SIZE_VALID)

print(f'Test loss: {score[0]} / Test accuracy: {score[1]}')