我已经训练了一个简单的CNN用于二进制图像分类。然后我尝试进行预测。我使用ImageDataGenerator创建了一个预测迭代器（predict_it）。然后我使用

probabilities = model.predict(predict_it)

得到了如下结果：

print(probabilities)
 [[9.0815449e-01]
 [1.9250402e-02]
 [9.8504424e-01]
 ...
 [4.3504283e-06]
 [3.5914429e-06]
 [7.5442227e-07]]

因此，模型本身似乎工作正常。然而，这种预测方法处理的是一个充满图像的整个子目录。因此，我尝试处理一个图像。但当我执行下面的代码时，总是得到相同的值（对8个不同的图像执行多次）：

probabilitiy = model.predict(single_image)

结果：

1/1 [==============================] - 0s 82ms/step
probability: [[0.5078959]]
1/1 [==============================] - 0s 33ms/step
probability: [[0.5078958]]
1/1 [==============================] - 0s 32ms/step
probability: [[0.5078958]]
1/1 [==============================] - 0s 42ms/step
probability: [[0.5078958]]
1/1 [==============================] - 0s 45ms/step
probability: [[0.50789577]]
1/1 [==============================] - 0s 39ms/step
probability: [[0.5078958]]
1/1 [==============================] - 0s 32ms/step
probability: [[0.5078957]]
1/1 [==============================] - 0s 33ms/step
probability: [[0.5078958]]

有人知道这是怎么发生的吗？
先谢谢你。
我尝试以不同的形式保存模型：（.keras和.h5）-但这并没有改变上面提到的结果。
我用来预处理单个图像的代码：

# a function to load and prepare each image
def load_image(filename):
    # load the image
    img = load_img(filename, grayscale=False, target_size=(256, 256))
    # convert to array
    img = img_to_array(img)
    # reshape into a single sample with 1 channel
    img = img.reshape(1, 256, 256, 3)
    # prepare pixel data
    img = img.astype("float32")
    img = img / 255.0
    return img    

# run through all files in a specified folder
for filename in files:
    # load a single image
    img = load_image(filename)
    # predict the probability
    probability = model.predict(img)  
    # display the result
    print(f"probability: {probability}")