what is output_node_names in this case ( saved_model.save(keras_model, 'saved_model') ).
Following code out error:

from tensorflow.python.tools import freeze_graph
import tensorflow.keras as keras
import tensorflow as tf



# input_data = keras.layers.Input((300,300,3), dtype=tf.float32)
# y_pred = keras.layers.Lambda(lambda x: tf.identity(x, name="out"), name='fts_output')(input_data)
# model = keras.models.Model([input_data], y_pred)
# tf.saved_model.save(model, 'saved_model')




output_graph = 'final_model.pb'
output_node_names = 'model/fts_output/out'
input_saver = ""
input_binary = True
restore_op_name = 'save/restore_all'
filename_tensor_name = 'save/Const:0'
clear_devices = True
initializer_nodes = ''
variable_names_blacklist = ''


freeze_graph.freeze_graph('', input_saver, input_binary,
			'', output_node_names,
			restore_op_name, filename_tensor_name,
			output_graph, clear_devices, initializer_nodes,
			variable_names_blacklist, input_saved_model_dir='saved_model')

log error:

Traceback (most recent call last):
  File "freeze_graph.py", line 30, in <module>
    variable_names_blacklist, input_saved_model_dir='saved_model')
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/tensorflow/python/tools/freeze_graph.py", line 363, in freeze_graph
    checkpoint_version=checkpoint_version)
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/tensorflow/python/tools/freeze_graph.py", line 232, in freeze_graph_with_def_protos
    variable_names_blacklist=variable_names_blacklist)
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
    return func(*args, **kwargs)
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/graph_util_impl.py", line 270, in convert_variables_to_constants
    inference_graph = extract_sub_graph(input_graph_def, output_node_names)
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
    return func(*args, **kwargs)
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/graph_util_impl.py", line 182, in extract_sub_graph
    _assert_nodes_are_present(name_to_node, dest_nodes)
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/graph_util_impl.py", line 137, in _assert_nodes_are_present
    assert d in name_to_node, "%s is not in graph" % d
AssertionError: model/fts_output/out is not in graph

how to freeze graph in tensorflow 2.0 #27614

Description

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions