我在学习TensorFlow的一个教程，在模型预测阶段遇到了问题。

代码的最后部分是这样的：

import cv2import tensorflow as tfCATEGORIES = ["bishopB", "bishopW", "empty", "kingB", "kingW",            "knightB", "knightW", "pawnB", "pawnW",            "queenB", "queenW", "rookB", "rookW"]def prepare(file):    IMG_SIZE = 50    img_array = cv2.imread(file, cv2.IMREAD_GRAYSCALE)    new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))    return new_array.reshape(-1, IMG_SIZE, IMG_SIZE, 1)model = tf.keras.models.load_model("CNN.model")image = "test.jpg" #your image pathprediction = model.predict([image])prediction = list(prediction[0])print(CATEGORIES[prediction.index(max(prediction))])

这应该可以让我根据文件输入得到预测结果。

然而，当我运行时，出现了以下错误：

    prediction = model.predict([image])  File "/Users/stuff/Library/Python/2.7/lib/python/site-packages/tensorflow/python/keras/engine/training.py", line 1060, in predict    x, check_steps=True, steps_name='steps', steps=steps)  File "/Users/stuff/Library/Python/2.7/lib/python/site-packages/tensorflow/python/keras/engine/training.py", line 2651, in _standardize_user_data    exception_prefix='input')  File "/Users/stuff/Library/Python/2.7/lib/python/site-packages/tensorflow/python/keras/engine/training_utils.py", line 334, in standardize_input_data    standardize_single_array(x, shape) for (x, shape) in zip(data, shapes)  File "/Users/stuff/Library/Python/2.7/lib/python/site-packages/tensorflow/python/keras/engine/training_utils.py", line 265, in standardize_single_array    if (x.shape is not None and len(x.shape) == 1 andAttributeError: 'str' object has no attribute 'shape'

有谁能帮我理解我在这里做错了什么吗？我认为它甚至没有开始处理我的测试图像。

回答：

你的 image 应该使用 prepare_file(img_path) 而不是直接使用字符串。