问题
I am trying to implement a recent paper. Part of this implementation involves moving from tf 1.14 to tf 2.1.0. The code was working with tf 1.14 but is no longer working.
NOTE: If I disable eager execution tf.compat.v1.disable_eager_execution() then the code works as expected.
Is this the solution? I've made plenty of models before in TF 2.x and never had to disable eager execution to achieve normal functionality.
I have distilled the problem to a very short gist that shows what's happening.
Links & Code First Followed By Detailed Error Message
Link to Gist -- https://gist.github.com/darien-schettler/fd5b25626e9eb5b1330cce670bf9cc17
Code
# version 2.1.0
import tensorflow as tf
# version 1.18.1
import numpy as np
# ######## DEFINE CUSTOM FUNCTION FOR TF LAMBDA LAYER ######## #
def resize_like(input_tensor, ref_tensor):
""" Resize an image tensor to the same size/shape as a reference image tensor
Args:
input_tensor : (image tensor) Input image tensor that will be resized
ref_tensor : (image tensor) Reference image tensor that we want to resize the input tensor to.
Returns:
reshaped tensor
"""
reshaped_tensor = tf.image.resize(images=input_tensor,
size=tf.shape(ref_tensor)[1:3],
method=tf.image.ResizeMethod.NEAREST_NEIGHBOR,
preserve_aspect_ratio=False,
antialias=False,
name=None)
return reshaped_tensor
# ############################################################# #
# ############ DEFINE MODEL USING TF.KERAS FN API ############ #
# INPUTS
model_input_1 = tf.keras.layers.Input(shape=(160,160,3))
model_input_2 = tf.keras.layers.Input(shape=(160,160,3))
# OUTPUTS
model_output_1 = tf.keras.layers.Conv2D(filters=64,
kernel_size=(1, 1),
use_bias=False,
kernel_initializer='he_normal',
name='conv_name_base')(model_input_1)
model_output_2 = tf.keras.layers.Lambda(function=resize_like,
arguments={'ref_tensor': model_output_1})(model_input_2)
# MODEL
model = tf.keras.models.Model(inputs=[model_input_1, model_input_2],
outputs=model_output_2,
name="test_model")
# ############################################################# #
# ######### TRY TO UTILIZE PREDICT WITH DUMMY INPUT ########## #
dummy_input = [np.ones((1,160,160,3)), np.zeros((1,160,160,3))]
model.predict(x=dummy_input) # >>>>ERROR OCCURS HERE<<<<
# ############################################################# #
Full Error
>>> model.predict(x=dummy_input) # >>>>ERROR OCCURS HERE<<<<
Traceback (most recent call last):
File "/Users/<username>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/eager/execute.py", line 61, in quick_execute
num_outputs)
TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
@tf.function
def has_init_scope():
my_constant = tf.constant(1.)
with tf.init_scope():
added = my_constant * 2
The graph tensor has name: conv_name_base_1/Identity:0
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 1013, in predict
use_multiprocessing=use_multiprocessing)
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 498, in predict
workers=workers, use_multiprocessing=use_multiprocessing, **kwargs)
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 475, in _model_iteration
total_epochs=1)
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 128, in run_one_epoch
batch_outs = execution_function(iterator)
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py", line 98, in execution_function
distributed_function(input_fn))
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py", line 568, in __call__
result = self._call(*args, **kwds)
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py", line 638, in _call
return self._concrete_stateful_fn._filtered_call(canon_args, canon_kwds) # pylint: disable=protected-access
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 1611, in _filtered_call
self.captured_inputs)
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 1692, in _call_flat
ctx, args, cancellation_manager=cancellation_manager))
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 545, in call
ctx=ctx)
File "/Users/<user-name>/.virtualenvs/<venv-name>/lib/python3.7/site-packages/tensorflow_core/python/eager/execute.py", line 75, in quick_execute
"tensors, but found {}".format(keras_symbolic_tensors))
tensorflow.python.eager.core._SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors, but found [<tf.Tensor 'conv_name_base_1/Identity:0' shape=(None, 160, 160, 64) dtype=float32>]
One potential solution I thought of would be to replace the Lambda layer with a custom layer... this seems to fix the issue as well. Not sure what the best practices are surrounding this though. Code below.
# version 2.1.0
import tensorflow as tf
# version 1.18.1
import numpy as np
# ######## DEFINE CUSTOM LAYER DIRECTLY BY SUBCLASSING ######## #
class ResizeLike(tf.keras.layers.Layer):
""" tf.keras layer to resize a tensor to the reference tensor shape.
Attributes:
keras.layers.Layer: Base layer class.
This is the class from which all layers inherit.
- A layer is a class implementing common neural networks
operations, such as convolution, batch norm, etc.
- These operations require managing weights,
losses, updates, and inter-layer connectivity.
"""
def __init__(self, **kwargs):
super().__init__(**kwargs)
def call(self, inputs, **kwargs):
"""TODO: docstring
Args:
inputs (TODO): TODO
**kwargs:
TODO
Returns:
TODO
"""
input_tensor, ref_tensor = inputs
return self.resize_like(input_tensor, ref_tensor)
def resize_like(self, input_tensor, ref_tensor):
""" Resize an image tensor to the same size/shape as a reference image tensor
Args:
input_tensor: (image tensor) Input image tensor that will be resized
ref_tensor: (image tensor) Reference image tensor that we want to resize the input tensor to.
Returns:
reshaped tensor
"""
reshaped_tensor = tf.image.resize(images=input_tensor,
size=tf.shape(ref_tensor)[1:3],
method=tf.image.ResizeMethod.NEAREST_NEIGHBOR,
preserve_aspect_ratio=False,
antialias=False)
return reshaped_tensor
# ############################################################# #
# ############ DEFINE MODEL USING TF.KERAS FN API ############ #
# INPUTS
model_input_1 = tf.keras.layers.Input(shape=(160,160,3))
model_input_2 = tf.keras.layers.Input(shape=(160,160,3))
# OUTPUTS
model_output_1 = tf.keras.layers.Conv2D(filters=64,
kernel_size=(1, 1),
use_bias=False,
kernel_initializer='he_normal',
name='conv_name_base')(model_input_1)
model_output_2 = ResizeLike(name="resize_layer")([model_input_2, model_output_1])
# MODEL
model = tf.keras.models.Model(inputs=[model_input_1, model_input_2],
outputs=model_output_2,
name="test_model")
# ############################################################# #
# ######### TRY TO UTILIZE PREDICT WITH DUMMY INPUT ########## #
dummy_input = [np.ones((1,160,160,3)), np.zeros((1,160,160,3))]
model.predict(x=dummy_input) # >>>>ERROR OCCURS HERE<<<<
# ############################################################# #
Thoughts??
Thanks in advance!!
Let me know if you would like me to provide anything else.
回答1:
You can try the following steps:
Change
resize_likeas follows:def resize_like(inputs): input_tensor, ref_tensor = inputs reshaped_tensor = tf.image.resize(images=input_tensor, size=tf.shape(ref_tensor)[1:3], method=tf.image.ResizeMethod.NEAREST_NEIGHBOR, preserve_aspect_ratio=False, antialias=False, name=None) return reshaped_tensorThen, in the
Lambdalayer:model_output_2 = tf.keras.layers.Lambda(function=resize_like)([model_input_2, model_output_1])
来源：https://stackoverflow.com/questions/60551145/tensorflow-2-1-0-an-op-outside-of-the-function-building-code-is-being-passed-a