Open PhyllisJi opened 1 day ago
Hi @PhyllisJi-
Thanks for reporting the issue. Here in your code there is multiple errors:
tf.nn.relu(x)
- need to use tf.keras.activations.relu(x)' as latest tensorflow2.17(keras3.0.6) as kerasTensor output which is not compatible with
tf.nn.relu(x`output_padding
argument in tf.keras.layers.Conv1DTranspose
. Here you can find more detail about Conv1DTranspose API. dilation_rate=8
in this line x = tf.keras.layers.Conv1DTranspose(filters=128, kernel_size=1, strides=1, padding="valid", output_padding=0, data_format="channels_last", dilation_rate=8, use_bias=True, name="conv4_mutated")(x)
. So changing dilation_rate=1
will resolve the error. Attached gist for the reference as well.
Hi @PhyllisJi-
Thanks for reporting the issue. Here in your code there is multiple errors:
tf.nn.relu(x)
- need to usetf.keras.activations.relu(x)' as latest tensorflow2.17(keras3.0.6) as kerasTensor output which is not compatible with
tf.nn.relu(x`- There is no
output_padding
argument intf.keras.layers.Conv1DTranspose
. Here you can find more detail about Conv1DTranspose API.- And last error is causing due to
dilation_rate=8
in this linex = tf.keras.layers.Conv1DTranspose(filters=128, kernel_size=1, strides=1, padding="valid", output_padding=0, data_format="channels_last", dilation_rate=8, use_bias=True, name="conv4_mutated")(x)
. So changingdilation_rate=1
will resolve the error.Attached gist for the reference as well.
We use the version is 2.14.0. Why tf.nn.relu is not compatible with tf.keras.activations.relu(x)?
Hi @PhyllisJi-
Thanks for reporting the issue. Here in your code there is multiple errors:
tf.nn.relu(x)
- need to usetf.keras.activations.relu(x)' as latest tensorflow2.17(keras3.0.6) as kerasTensor output which is not compatible with
tf.nn.relu(x`- There is no
output_padding
argument intf.keras.layers.Conv1DTranspose
. Here you can find more detail about Conv1DTranspose API.- And last error is causing due to
dilation_rate=8
in this linex = tf.keras.layers.Conv1DTranspose(filters=128, kernel_size=1, strides=1, padding="valid", output_padding=0, data_format="channels_last", dilation_rate=8, use_bias=True, name="conv4_mutated")(x)
. So changingdilation_rate=1
will resolve the error.Attached gist for the reference as well. Our code is automatically generated, so it may not look very polished—apologies for that. However, based on your previous response, we identified the following concerns:
Issue type
Documentation Bug
Have you reproduced the bug with TensorFlow Nightly?
Yes
Source
source
TensorFlow version
tf 2.14.0
Custom code
Yes
OS platform and distribution
Ubuntu 20.04
Mobile device
No response
Python version
No response
Bazel version
No response
GCC/compiler version
No response
CUDA/cuDNN version
No response
GPU model and memory
No response
Current behavior?
Throw Error:
Also, I'm not quite sure why the error message relates to Conv2DBackpropInput
Standalone code to reproduce the issue