在尝试在keras模型中使用predict_classes
时,即使输入形状似乎是必需的,该函数也会引发异常
model = get_model()
flist = [10, 1.0, 0.0, 0.0, 1]
X = np.array(flist)
print(X.shape) # prints (5,)
model.predict_classes(X)
不断抛出错误
ValueError: Error when checking input: expected dense_1_input to have shape (5,) but got array with shape (1,)
答案 0 :(得分:1)
X的形状必须为(Number_of_samples, input_dim)
。使用np.expand_dims
。
X = np.expand_dims(X,axis=0)