问题检索值decode_predictions`需要一批预测
问题检索值decode_predictions`需要一批预测
提问于 2021-03-17 22:30:20
我有一个预先训练的模型，试图删除一个层，并在新模型上执行预测。然而，检索错误。
model = applications.VGG16(include_top=False, input_shape=(224, 224, 3), weights='imagenet')
layers = [l for l in model.layers]
x = layers[9].output
x = layers[11](x)
x = layers[12](x)
x = layers[13](x)
x = layers[14](x)
x = layers[15](x)
x = layers[16](x)
x = layers[17](x)
x = layers[18](x)
result_model = Model(inputs=layers[0].input, outputs=x)
img='/content/elephant.jpg'
img = image.load_img(img, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = result_model.predict(x)
print('Predicted:', decode_predictions(preds, top=3)[0])错误
ValueError: `decode_predictions` expects a batch of predictions (i.e. a 2D array of shape (samples, 1000)). Found array with shape: (1, 14, 14, 512)回答 1
Stack Overflow用户
发布于 2021-03-17 22:37:40
你的神经网络没有输出层。decode_predictions不能解码卷积层的输出，这是您执行include_top=False时所得到的。执行以下操作：
model = applications.VGG16(include_top=True, input_shape=(224, 224, 3),
weights='imagenet')页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/66675147
复制相关文章
相似问题