tf.GradientTape.gradient raise error with tf.nn.relu6 #21380
Description
System information
- Have I written custom code (as opposed to using a stock example script provided in TensorFlow): yes
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
- Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device:
- TensorFlow installed from (source or binary):
- TensorFlow version (use command below): 1.10.0-rc1
- Python version: 3.6
- Bazel version (if compiling from source):
- GCC/Compiler version (if compiling from source):
- CUDA/cuDNN version:
- GPU model and memory:
- Exact command to reproduce:
Describe the problem
tf.GradientTape.gradient raise error with tf.nn.relu6
Source code / logs
import tensorflow as tf
tf.enable_eager_execution()
w = tf.contrib.eager.Variable([[1.0]])
with tf.GradientTape() as tape:
loss = tf.nn.relu6(w * w)
grad = tape.gradient(loss, w)Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/eager/backprop.py", line 858, in gradient
output_gradients=output_gradients)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/eager/imperative_grad.py", line 63, in imperative_grad
tape._tape, vspace, target, sources, output_gradients) # pylint: disable=protected-access
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/eager/backprop.py", line 116, in _gradient_function
return grad_fn(mock_op, *out_grads)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/nn_grad.py", line 387, in _Relu6Grad
return gen_nn_ops.relu6_grad(grad, op.outputs[0])
TypeError: 'NoneType' object is not subscriptable