NotImplementedError: Cannot convert a symbolic Tensor (2nd_target:0) to a numpy array

by

For me, the issue occurred when upgrading from numpy 1.19 to 1.20 and using ray‘s RLlib, which uses tensorflow 2.2 internally.
Simply downgrading with

pip install numpy==1.19.5

solved the problem; the error did not occur anymore.

Update (comment by @codeananda): You can also update to a newer TensorFlow (2.6+) version now that resolves the problem (pip install -U tensorflow).

More Related Contents:

  1. Keras, How to get the output of each layer?
  2. Keras Dense layer’s input is not flattened
  3. Tensorflow – ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float)
  4. Deep-Learning Nan loss reasons
  5. Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,
  6. Why is TensorFlow 2 much slower than TensorFlow 1?
  7. NaN loss when training regression network
  8. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  9. Proper way to feed time-series data to stateful LSTM?
  10. What is the difference between tf.keras and tf.python.keras?
  11. How to use a Keras RNN model to forecast for future dates or events?
  12. TypeError: __array__() takes 1 positional argument but 2 were given (Image classification Keras)
  13. Tensorflow 2.0 – AttributeError: module ‘tensorflow’ has no attribute ‘Session’
  14. Can I run Keras model on gpu?
  15. Keras custom loss function: Accessing current input pattern
  16. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  17. Dimension of shape in conv1D
  18. How to know if underfitting or overfitting is occuring?
  19. Loading a trained Keras model and continue training
  20. Keras: .predict returns percentages instead of classes
  21. Keras Custom loss function to pass arguments other than y_true and y_pred
  22. Unknown initializer: GlorotUniform when loading Keras model
  23. Tensorflow : logits and labels must have the same first dimension
  24. Multiple outputs in Keras
  25. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  26. How to implement Grad-CAM on a trained network
  27. ‘Tensor’ object has no attribute ‘lower’
  28. Unexpected keyword argument ‘ragged’ in Keras
  29. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  30. Invalid Argument Error / Graph Execution Error

Leave a Comment