NotImplementedError：无法将符号张量(lstm_2/strided_slice:0)转换为numpy数组。吨

html5 • • 问答

张量流版本 2.3.1 numpy 版本 1.20

代码下方

# define model
model = Sequential()
model.add(LSTM(50, activation='relu', input_shape=(n_steps, n_features)))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')

我们有

NotImplementedError：无法将符号张量 (lstm_2/strided_slice:0) 转换为 numpy 数组。此错误可能表明您正在尝试将张量传递给 NumPy 调用，但不受支持

在我看来这是一个疯狂的错误！

回答

我用 numpy 降级到 1.18.5 解决了

pip install -U numpy==1.18.5

  • I was just looking at the 1.20 release notes. There are a number of low level changes (which I didn't fully understand), so I'm not surprised that there compatibility issues with `tensorflow`. I don't know who has to fix what.
  • Numpy version 1.19.5 resolves the issues as well.
  • I just did as well 🙂
以上是NotImplementedError：无法将符号张量(lstm_2/strided_slice:0)转换为numpy数组。吨的全部内容。
THE END
分享
二维码
< <上一篇
下一篇>>