如@ fritera所示，为预测准备Tensor的方法是np.expand_dims()。
假设我们的模型看起来像这样

Model: "model_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_5 (InputLayer)         [(None, 224, 224, 3)]     0         
_________________________________________________________________
sequential (Sequential)      (None, 224, 224, 3)       0         
_________________________________________________________________
vggface_resnet50 (Functional (None, 1, 1, 2048)        23561152  
_________________________________________________________________
flatten (Flatten)            (None, 2048)              0         
_________________________________________________________________
classifier (Dense)           (None, 8)                 16392     
=================================================================
Total params: 23,577,544
Trainable params: 16,392
Non-trainable params: 23,561,152
_________________________________________________________________

字符串
假设这是VGGFace，那么我们需要确保图像是224 x224 x3，并且我们需要添加这个“批处理”维度。（假设我们已经用PIL.Image.open()加载了图像）
我们可以准备图像：

def prepPred(someImage, resizeTarget=224):
    """Prepare Image for prediction"""
    someImage = someImage.resize((resizeTarget, 
                                  resizeTarget), 
                                 pillowImageLoader.BILINEAR)
    # Convert image to array
    imageArray = np.array(someImage)
    # add the batch dimension and return
    return np.expand_dims(imageArray, axis=0)

型
模型总是期望批次-当你训练时，你提供批次，当你预测时，你必须提供批次-在这种情况下，它只是一个1的“批次”。