我想对神经网络的预测进行非规范化。我首先标准化我的基本事实,并将其标准值和平均值保存在一个 numpy 数组中:
def norm(x):
return ((x - x.mean()) / x.std())
norm_y_train_n = norm(y_train_n)
mean_y_train_n = y_train_n.mean
std_y_train_n = y_train_n.std
然后我训练我的网络:
history = model.fit(x_train_n, norm_y_train_n, batch_size=10, epochs=200, validation_split=0.1, shuffle=True, callbacks=[es])
我想将我的数据非规范化为原始分布,以便我可以在一个有意义的范围内解释 rmse,如下所示:
def rmse_denorm(y_true, y_pred):
return backend.sqrt(backend.mean(backend.square((y_pred*std_y_train_n + mean_y_train_n) - (y_true*std_y_train_n+mean_y_train_n))))
但我不能,如果我尝试使用 tf.convert_to_tensor 将 numpy 值转换为张量值,如下所示:
def rmse_denorm(y_true, y_pred):
return backend.sqrt(backend.mean(backend.square((y_pred*tf.convert_to_tensor(std_y_train_n) + tf.convert_to_tensor(mean_y_train_n)) - (y_true*tf.convert_to_tensor(std_y_train_n)+tf.convert_to_tensor(mean_y_train_n)))))
我会收到这个错误:
Failed to convert object of type <class 'builtin_function_or_method'> to Tensor. Contents: <built-in method std of numpy.ndarray object at 0x7ff00811aee0>. Consider casting elements to a supported type.
如果我想转换张量值:
def rmse_denorm(y_true, y_pred):
return backend.sqrt(backend.mean(backend.square((tf.dtypes.cast(y_pred)*std_y_train_n + mean_y_train_n) - (tf.dtypes.cast(y_true)*std_y_train_n+mean_y_train_n))))
我收到此错误:
TypeError: cast() missing 1 required positional argument: 'dtype'
我该怎么做呢?