ValueError：预期输入形状的轴-1的值为128，但接收到形状为[32，1]的输入

Question

我正在尝试对单个图像进行预测，并且正在训练输入形状= 128的模型，但是当我尝试仅对单个图像进行预测时，虽然输入形状也是128，但它给了我错误，我看到了 。有人能详细说明这个错误吗？

import cv2
import numpy as np
import tensorflow as tf

Categories = ["Badshahi Masjid", "Minare Pakistan", "ShahiQila(Lahore Fort)"]

sift = cv2.xfeatures2d.SIFT_create()


def prepare(filepath):
    IMG_SIZE = (124,124)
    img_array = cv2.imread(filepath, cv2.IMREAD_GRAYSCALE)
    new_array = cv2.resize(img_array, IMG_SIZE)
    keyImage, desImage = sift.detectAndCompute(new_array, None)
    feat = np.sum(desImage, axis=0)
    return feat
   
model = tf.keras.models.load_model("SuperClassPredictions.h5")
prediction = model.predict([prepare('E:\Python Telusko\OpenCv\download.jpg')])
print(prediction)
print(Categories[int(prediction[0][0])])