tf.compat.v1.profiler.write_op_log
Log provided 'op_log', and add additional model information below.
tf.compat.v1.profiler.write_op_log(
graph, log_dir, op_log=None, run_meta=None, add_trace=True
)
The API also assigns ops in tf.compat.v1.trainable_variables() an op type
called '_trainable_variables'.
The API also logs 'flops' statistics for ops with op.RegisterStatistics()
defined. flops calculation depends on Tensor shapes defined in 'graph',
which might not be complete. 'run_meta', if provided, completes the shape
information with best effort.
Args |
|---|
graph
|
tf.Graph. If None and eager execution is not enabled, use
default graph.
|
log_dir
|
directory to write the log file.
|
op_log
|
(Optional) OpLogProto proto to be written. If not provided, an new
one is created.
|
run_meta
|
(Optional) RunMetadata proto that helps flops computation using
run time shape information.
|
add_trace
|
Whether to add python code trace information.
Used to support "code" view.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-01-23 UTC.
[null,null,["Last updated 2024-01-23 UTC."],[],[]]
View source on GitHub