def _build_options(tfprof_options):
"""Build tfprof.OptionsProto.
Args:
tfprof_options: A dictionary of options.
Returns:
tfprof.OptionsProto.
"""
opts = tfprof_options_pb2.OptionsProto()
opts.max_depth = tfprof_options.get('max_depth', 10)
opts.min_bytes = tfprof_options.get('min_bytes', 0)
opts.min_micros = tfprof_options.get('min_micros', 0)
opts.min_params = tfprof_options.get('min_params', 0)
opts.min_float_ops = tfprof_options.get('min_float_ops', 0)
opts.min_occurrence = tfprof_options.get('min_occurrence', 0)
opts.step = tfprof_options.get('step', -1)
opts.order_by = tfprof_options.get('order_by', 'name')
for p in tfprof_options.get('account_type_regexes', []):
opts.account_type_regexes.append(p)
for p in tfprof_options.get('start_name_regexes', []):
opts.start_name_regexes.append(p)
for p in tfprof_options.get('trim_name_regexes', []):
opts.trim_name_regexes.append(p)
for p in tfprof_options.get('show_name_regexes', []):
opts.show_name_regexes.append(p)
for p in tfprof_options.get('hide_name_regexes', []):
opts.hide_name_regexes.append(p)
opts.account_displayed_op_only = tfprof_options.get(
'account_displayed_op_only', False)
for p in tfprof_options.get('select', []):
opts.select.append(p)
opts.output = tfprof_options.get('output', 'stdout')
opts.dump_to_file = tfprof_options.get('dump_to_file', '')
return opts
def print_model_analysis(graph,
run_meta=None,
op_log=None,
tfprof_cmd='scope',
tfprof_options=TRAINABLE_VARS_PARAMS_STAT_OPTIONS):
"""Print model statistics.
Prints the model statistics to stdout. Also returns the results
in a TFGraphNodeProto proto. See go/tfprof or run tfprof tool:
'bazel run third_party/tensorflow/tools/tfprof help'
Examples:
Show the parameter/shape statistics of tf.trainable_variables().
print_model_analysis(sess.graph).
Show number of float ops. Only ops with RegisterStatistics defined
are counted.
show_float_op_opts = model_analyzer.FLOAT_OPS_OPTIONS
print_model_analysis(sess.graph, tfprof_options=show_float_op_opts)
Args:
graph: tf.Graph.
run_meta: tensorflow::RunMetadata proto. When provided, also shows valid
timing and memory information when 'select' option contains
'micros' and 'bytes'.
op_log: tensorflow::tfprof::OpLog proto. users can use this proto to
group together ops and use a op_type to select the group.
tfprof_cmd: string. Either 'scope', 'graph', 'code'.
'scope' view organize outputs using ops' name scope.
'graph' view organize outputs using op's inputs/outputs.
'code' view organize outputs using Python call stack.
tfprof_options: See 'tfprof help' for details.
Returns:
If tfprof_cmd is 'scope' or 'graph', returns TFGraphNodeProto proto.
If tfprof_cmd is 'code', returns TFCodeNodeProto proto.
Side effect: a formatted output to stdout.
"""
# pylint: disable=protected-access
op_log = tfprof_logger._merge_default_with_oplog(
graph, op_log, run_meta, add_trace=tfprof_cmd == 'code')
# pylint: enable=protected-access
opts = tfprof_options_pb2.OptionsProto()
opts.max_depth = tfprof_options['max_depth']
opts.min_bytes = tfprof_options['min_bytes']
opts.min_micros = tfprof_options['min_micros']
opts.min_params = tfprof_options['min_params']
opts.min_float_ops = tfprof_options['min_float_ops']
for p in tfprof_options['device_regexes']:
opts.device_regexes.append(p)
opts.order_by = tfprof_options['order_by']
for p in tfprof_options['account_type_regexes']:
opts.account_type_regexes.append(p)
for p in tfprof_options['start_name_regexes']:
opts.start_name_regexes.append(p)
for p in tfprof_options['trim_name_regexes']:
opts.trim_name_regexes.append(p)
for p in tfprof_options['show_name_regexes']:
opts.show_name_regexes.append(p)
for p in tfprof_options['hide_name_regexes']:
opts.hide_name_regexes.append(p)
opts.account_displayed_op_only = tfprof_options['account_displayed_op_only']
for p in tfprof_options['select']:
opts.select.append(p)
opts.output = tfprof_options['output']
opts.dump_to_file = tfprof_options['dump_to_file']
run_meta_str = run_meta.SerializeToString() if run_meta else b''
if tfprof_cmd == 'code':
tfprof_node = tfprof_output_pb2.TFCodeNodeProto()
tfprof_node.ParseFromString(
print_mdl.PrintModelAnalysis(
graph.as_graph_def().SerializeToString(),
run_meta_str,
op_log.SerializeToString(),
tfprof_cmd.encode('utf-8'),
opts.SerializeToString()))
else:
tfprof_node = tfprof_output_pb2.TFGraphNodeProto()
tfprof_node.ParseFromString(
print_mdl.PrintModelAnalysis(
graph.as_graph_def().SerializeToString(),
run_meta_str,
op_log.SerializeToString(),
tfprof_cmd.encode('utf-8'),
opts.SerializeToString()))
return tfprof_node
def testPrintModelAnalysis(self):
opts = tfprof_options_pb2.OptionsProto()
opts.max_depth = TEST_OPTIONS['max_depth']
opts.min_bytes = TEST_OPTIONS['min_bytes']
opts.min_micros = TEST_OPTIONS['min_micros']
opts.min_params = TEST_OPTIONS['min_params']
opts.min_float_ops = TEST_OPTIONS['min_float_ops']
for p in TEST_OPTIONS['device_regexes']:
opts.device_regexes.append(p)
opts.order_by = TEST_OPTIONS['order_by']
for p in TEST_OPTIONS['account_type_regexes']:
opts.account_type_regexes.append(p)
for p in TEST_OPTIONS['start_name_regexes']:
opts.start_name_regexes.append(p)
for p in TEST_OPTIONS['trim_name_regexes']:
opts.trim_name_regexes.append(p)
for p in TEST_OPTIONS['show_name_regexes']:
opts.show_name_regexes.append(p)
for p in TEST_OPTIONS['hide_name_regexes']:
opts.hide_name_regexes.append(p)
opts.account_displayed_op_only = TEST_OPTIONS[
'account_displayed_op_only']
for p in TEST_OPTIONS['select']:
opts.select.append(p)
opts.viz = TEST_OPTIONS['viz']
with tf.Session() as sess, tf.device('/cpu:0'):
_ = self._BuildSmallModel()
tfprof_pb = tfprof_output_pb2.TFProfNode()
tfprof_pb.ParseFromString(
print_mdl.PrintModelAnalysis(
sess.graph.as_graph_def().SerializeToString(), b'', b'',
b'scope', opts.SerializeToString()))
expected_pb = tfprof_output_pb2.TFProfNode()
text_format.Merge(
r"""name: "_TFProfRoot"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 648
children {
name: "Conv2D"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
children {
name: "DW"
exec_micros: 0
requested_bytes: 0
parameters: 648
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 648
device: "/device:CPU:0"
children {
name: "DW/Assign"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
children {
name: "DW/Initializer"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
children {
name: "DW/Initializer/random_normal"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
children {
name: "DW/Initializer/random_normal/RandomStandardNormal"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
children {
name: "DW/Initializer/random_normal/mean"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
children {
name: "DW/Initializer/random_normal/mul"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
children {
name: "DW/Initializer/random_normal/shape"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
children {
name: "DW/Initializer/random_normal/stddev"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
float_ops: 0
total_float_ops: 0
}
float_ops: 0
total_float_ops: 0
}
children {
name: "DW/read"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
float_ops: 0
total_float_ops: 0
}
children {
name: "zeros"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
device: "/device:CPU:0"
float_ops: 0
total_float_ops: 0
}
float_ops: 0
total_float_ops: 0""", expected_pb)
self.assertEqual(expected_pb, tfprof_pb)
def testPrintModelAnalysis(self):
opts = tfprof_options_pb2.OptionsProto()
opts.max_depth = TEST_OPTIONS['max_depth']
opts.min_bytes = TEST_OPTIONS['min_bytes']
opts.min_micros = TEST_OPTIONS['min_micros']
opts.min_params = TEST_OPTIONS['min_params']
opts.min_float_ops = TEST_OPTIONS['min_float_ops']
opts.order_by = TEST_OPTIONS['order_by']
opts.step = -1
for p in TEST_OPTIONS['account_type_regexes']:
opts.account_type_regexes.append(p)
for p in TEST_OPTIONS['start_name_regexes']:
opts.start_name_regexes.append(p)
for p in TEST_OPTIONS['trim_name_regexes']:
opts.trim_name_regexes.append(p)
for p in TEST_OPTIONS['show_name_regexes']:
opts.show_name_regexes.append(p)
for p in TEST_OPTIONS['hide_name_regexes']:
opts.hide_name_regexes.append(p)
opts.account_displayed_op_only = TEST_OPTIONS[
'account_displayed_op_only']
for p in TEST_OPTIONS['select']:
opts.select.append(p)
opts.output = TEST_OPTIONS['output']
with session.Session() as sess, ops.device('/cpu:0'):
_ = self._BuildSmallModel()
tfprof_pb = tfprof_output_pb2.TFGraphNodeProto()
tfprof_pb.ParseFromString(
print_mdl.PrintModelAnalysis(
sess.graph.as_graph_def(
add_shapes=True).SerializeToString(), b'', b'',
b'scope', opts.SerializeToString()))
expected_pb = tfprof_output_pb2.TFGraphNodeProto()
text_format.Merge(
r"""name: "_TFProfRoot"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 648
children {
name: "Conv2D"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
input_shapes {
key: 0
value {
dim {
size: 2
}
dim {
size: 6
}
dim {
size: 6
}
dim {
size: 3
}
}
}
input_shapes {
key: 1
value {
dim {
size: 6
}
dim {
size: 6
}
dim {
size: 3
}
dim {
size: 6
}
}
}
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
children {
name: "DW"
exec_micros: 0
requested_bytes: 0
parameters: 648
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 648
children {
name: "DW/Assign"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
input_shapes {
key: 0
value {
dim {
size: 6
}
dim {
size: 6
}
dim {
size: 3
}
dim {
size: 6
}
}
}
input_shapes {
key: 1
value {
dim {
size: 6
}
dim {
size: 6
}
dim {
size: 3
}
dim {
size: 6
}
}
}
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
children {
name: "DW/Initializer"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
children {
name: "DW/Initializer/random_normal"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
children {
name: "DW/Initializer/random_normal/RandomStandardNormal"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
input_shapes {
key: 0
value {
dim {
size: 4
}
}
}
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
children {
name: "DW/Initializer/random_normal/mean"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
children {
name: "DW/Initializer/random_normal/mul"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
input_shapes {
key: 0
value {
dim {
size: 6
}
dim {
size: 6
}
dim {
size: 3
}
dim {
size: 6
}
}
}
input_shapes {
key: 1
value {
dim {
size: 1
}
}
}
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
children {
name: "DW/Initializer/random_normal/shape"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
children {
name: "DW/Initializer/random_normal/stddev"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
float_ops: 0
total_float_ops: 0
input_shapes {
key: 0
value {
dim {
size: 6
}
dim {
size: 6
}
dim {
size: 3
}
dim {
size: 6
}
}
}
input_shapes {
key: 1
value {
dim {
size: 1
}
}
}
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 6
}
float_ops: 0
total_float_ops: 0
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 7
}
children {
name: "DW/read"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
input_shapes {
key: 0
value {
dim {
size: 6
}
dim {
size: 6
}
dim {
size: 3
}
dim {
size: 6
}
}
}
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
float_ops: 0
total_float_ops: 0
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 10
}
children {
name: "zeros"
exec_micros: 0
requested_bytes: 0
total_exec_micros: 0
total_requested_bytes: 0
total_parameters: 0
float_ops: 0
total_float_ops: 0
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 1
}
float_ops: 0
total_float_ops: 0
accelerator_exec_micros: 0
cpu_exec_micros: 0
total_accelerator_exec_micros: 0
total_cpu_exec_micros: 0
run_count: 0
total_run_count: 0
total_definition_count: 13""", expected_pb)
self.assertEqual(expected_pb, tfprof_pb)
def print_model_analysis(graph,
run_meta=None,
op_log=None,
tfprof_cmd='scope',
tfprof_options=TRAINABLE_VARS_PARAMS_STAT_OPTIONS):
"""Print model statistics.
See go/tfprof or README for examples and tutorials.
Run tfprof tool for help:
'bazel run third_party/tensorflow/tools/tfprof help'
Args:
graph: tf.Graph.
run_meta: tensorflow::RunMetadata proto. When provided, also shows valid
timing and memory information when 'select' option contains
'micros' and 'bytes'.
op_log: tensorflow::tfprof::OpLog proto. users can use this proto to
group together ops and use a op_type to select the group.
tfprof_cmd: string. Either 'op', 'scope', 'graph', 'code'.
'op' view organize outputs using operation type. (e.g. MatMul)
'scope' view organize outputs using graph node name scope.
'graph' view organize outputs using graph node inputs/outputs.
'code' view organize outputs using Python call stack.
tfprof_options: See 'tfprof help' for details.
Returns:
If tfprof_cmd is 'scope' or 'graph', returns TFGraphNodeProto proto.
If tfprof_cmd is 'op' or 'code', returns TFMultiGraphNodeProto proto.
Side effect: stdout/file/timeline.json depending on tfprof_options['output']
"""
# pylint: disable=protected-access
op_log = tfprof_logger._merge_default_with_oplog(
graph, op_log, run_meta, add_trace=tfprof_cmd == 'code')
# pylint: enable=protected-access
opts = tfprof_options_pb2.OptionsProto()
opts.max_depth = tfprof_options['max_depth']
opts.min_bytes = tfprof_options['min_bytes']
opts.min_micros = tfprof_options['min_micros']
opts.min_params = tfprof_options['min_params']
opts.min_float_ops = tfprof_options['min_float_ops']
if 'min_occurrence' in tfprof_options:
opts.min_occurrence = tfprof_options['min_occurrence']
else:
opts.min_occurrence = 0
opts.order_by = tfprof_options['order_by']
for p in tfprof_options['account_type_regexes']:
opts.account_type_regexes.append(p)
for p in tfprof_options['start_name_regexes']:
opts.start_name_regexes.append(p)
for p in tfprof_options['trim_name_regexes']:
opts.trim_name_regexes.append(p)
for p in tfprof_options['show_name_regexes']:
opts.show_name_regexes.append(p)
for p in tfprof_options['hide_name_regexes']:
opts.hide_name_regexes.append(p)
opts.account_displayed_op_only = tfprof_options['account_displayed_op_only']
for p in tfprof_options['select']:
opts.select.append(p)
opts.output = tfprof_options['output']
opts.dump_to_file = tfprof_options['dump_to_file']
run_meta_str = run_meta.SerializeToString() if run_meta else b''
if tfprof_cmd == 'code' or tfprof_cmd == 'op':
tfprof_node = tfprof_output_pb2.TFMultiGraphNodeProto()
tfprof_node.ParseFromString(
print_mdl.PrintModelAnalysis(
graph.as_graph_def().SerializeToString(),
run_meta_str,
op_log.SerializeToString(),
tfprof_cmd.encode('utf-8'),
opts.SerializeToString()))
elif tfprof_cmd == 'graph' or tfprof_cmd == 'scope':
tfprof_node = tfprof_output_pb2.TFGraphNodeProto()
tfprof_node.ParseFromString(
print_mdl.PrintModelAnalysis(
graph.as_graph_def().SerializeToString(),
run_meta_str,
op_log.SerializeToString(),
tfprof_cmd.encode('utf-8'),
opts.SerializeToString()))
else:
raise errors.InvalidArgumentError(
None, None, 'unknown tfprof_cmd: %s\n' % tfprof_cmd)
return tfprof_node
