我使用以下程序来预测图像的类别。
from tensorflow.keras.preprocessing.image import load_img, img_to_array x = load_img("8-SignLanguageMNIST/test1.jpg", target_size = (28, 28)) x = img_to_array(x) x = np.expand_dims(x, axis = 0) x = np.vstack([x]) classes = model.predict(x) print(classes[0])
我用于训练的图像具有形状(28、28、1)。
在这里,我上传的是形状为(28,28,3)的RGB图像,我尝试将该图像转换为灰度,然后进行预测,但始终出现以下错误。
ValueError: Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 1 but received input with shape [None, 28, 28, 3]
谁能告诉我我在做什么错,并帮助我解决这个问题。