def testSelectEverything(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(builder.trainable_variables_parameter())
.with_file_output(outfile)
.with_accounted_types(['.*'])
.select(['params', 'float_ops', 'occurrence', 'device', 'op_types',
'input_shapes']).build())
rewriter_config = rewriter_config_pb2.RewriterConfig(
disable_model_pruning=True)
graph_options = config_pb2.GraphOptions(rewrite_options=rewriter_config)
config = config_pb2.ConfigProto(graph_options=graph_options)
with session.Session(config=config) as sess, ops.device('/cpu:0'):
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(
sess.graph, run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
self.assertEqual(
'node name | # parameters | # float_ops | assigned devices | op types | op count (run|defined) | input shapes\n_TFProfRoot (--/451 params, --/10.44k flops, _kTFScopeParent, --/7|--/35, )\n Conv2D (0/0 params, 5.83k/5.83k flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D, 1/1|1/1, 0:2x6x6x3|1:3x3x3x6)\n Conv2D_1 (0/0 params, 4.61k/4.61k flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D, 1/1|1/1, 0:2x3x3x6|1:2x2x6x12)\n DW (3x3x3x6, 162/162 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables, 1/2|1/10, )\n DW/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:3x3x3x6|1:3x3x3x6)\n DW/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n DW/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:3x3x3x6|1:1)\n DW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:4)\n DW/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:3x3x3x6|1:1)\n DW/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW/read (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity, 1/1|1/1, 0:3x3x3x6)\n DW2 (2x2x6x12, 288/288 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables, 1/2|1/10, )\n DW2/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:2x2x6x12|1:2x2x6x12)\n DW2/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n DW2/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:2x2x6x12|1:1)\n DW2/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:4)\n DW2/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW2/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:2x2x6x12|1:1)\n DW2/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW2/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW2/read (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity, 1/1|1/1, 0:2x2x6x12)\n ScalarW (1, 1/1 params, 0/0 flops, VariableV2|_trainable_variables, 0/0|1/10, )\n ScalarW/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:1|1:1)\n ScalarW/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n ScalarW/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:1|1:1)\n ScalarW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:0)\n ScalarW/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n ScalarW/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:1|1:1)\n ScalarW/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n ScalarW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n ScalarW/read (0/0 params, 0/0 flops, Identity, 0/0|1/1, 0:1)\n init (0/0 params, 0/0 flops, NoOp, 0/0|1/1, 0:1|1:3x3x3x6|2:2x2x6x12)\n zeros (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Const, 1/1|1/1, )\n',
f.read())
def testTrackPersistentBytes(self):
ops.reset_default_graph()
a = array_ops.constant(np.ones((100, 100)))
b = array_ops.constant(np.ones((100, 100)))
c = a * b
with session.Session() as sess:
run_options = config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE)
run_metadata = config_pb2.RunMetadata()
sess.run(c, options=run_options, run_metadata=run_metadata)
options = option_builder.ProfileOptionBuilder.time_and_memory()
options['min_bytes'] = 0
options['select'] = ('bytes', 'peak_bytes', 'output_bytes',
'residual_bytes')
ret = model_analyzer.profile(
sess.graph, run_meta=run_metadata, cmd='scope', options=options)
run_metadata = config_pb2.RunMetadata()
sess.run(c, options=run_options, run_metadata=run_metadata)
ret2 = model_analyzer.profile(
sess.graph, run_meta=run_metadata, cmd='scope', options=options)
n = lib.SearchTFProfNode(ret, 'mul')
n2 = lib.SearchTFProfNode(ret2, 'mul')
self.assertGreater(n.peak_bytes, 0)
self.assertGreater(n.output_bytes, 0)
self.assertGreater(n.residual_bytes, 0)
self.assertEqual(n.peak_bytes, n2.peak_bytes)
self.assertEqual(n.output_bytes, n2.output_bytes)
self.assertEqual(n.residual_bytes, n2.residual_bytes)
def testTrackPersistentBytes(self):
ops.reset_default_graph()
a = array_ops.constant(np.ones((100, 100)))
b = array_ops.constant(np.ones((100, 100)))
c = a * b
with session.Session() as sess:
run_options = config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE)
run_metadata = config_pb2.RunMetadata()
sess.run(c, options=run_options, run_metadata=run_metadata)
options = option_builder.ProfileOptionBuilder.time_and_memory()
options['min_bytes'] = 0
options['select'] = ('bytes', 'peak_bytes', 'output_bytes',
'residual_bytes')
ret = model_analyzer.profile(
sess.graph, run_meta=run_metadata, cmd='scope', options=options)
run_metadata = config_pb2.RunMetadata()
sess.run(c, options=run_options, run_metadata=run_metadata)
ret2 = model_analyzer.profile(
sess.graph, run_meta=run_metadata, cmd='scope', options=options)
n = lib.SearchTFProfNode(ret, 'mul')
n2 = lib.SearchTFProfNode(ret2, 'mul')
self.assertGreater(n.peak_bytes, 0)
self.assertGreater(n.output_bytes, 0)
self.assertGreater(n.residual_bytes, 0)
self.assertEqual(n.peak_bytes, n2.peak_bytes)
self.assertEqual(n.output_bytes, n2.output_bytes)
self.assertEqual(n.residual_bytes, n2.residual_bytes)
def testSimpleCodeView(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts['output'] = 'file:outfile=' + outfile
opts['account_type_regexes'] = ['.*']
opts['show_name_regexes'] = ['.*model_analyzer_testlib.*']
opts['account_displayed_op_only'] = False
# TODO(xpan): Test 'micros'. Since the execution time changes each run,
# it's a bit difficult to test it now.
opts['select'] = [
'bytes', 'params', 'float_ops', 'num_hidden_ops', 'device',
'input_shapes'
]
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(sess.graph,
run_meta,
cmd='code',
options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
self.assertEqual(
'node name | output bytes | # parameters | # float_ops | assigned devices | input',
f.read()[0:80])
def testSelectEverything(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(
builder.trainable_variables_parameter()).with_file_output(
outfile).with_accounted_types(['.*']).select([
'params', 'float_ops', 'occurrence', 'device', 'op_types',
'input_shapes'
]).build())
rewriter_config = rewriter_config_pb2.RewriterConfig(
disable_model_pruning=True)
graph_options = config_pb2.GraphOptions(
rewrite_options=rewriter_config)
config = config_pb2.ConfigProto(graph_options=graph_options)
with session.Session(config=config) as sess, ops.device('/cpu:0'):
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(sess.graph, run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
self.assertEqual(
'node name | # parameters | # float_ops | assigned devices | op types | op count (run|defined) | input shapes\n_TFProfRoot (--/451 params, --/10.44k flops, _kTFScopeParent, --/8|--/36, )\n Conv2D (0/0 params, 5.83k/5.83k flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D, 1/1|1/1, 0:2x6x6x3|1:3x3x3x6)\n Conv2D_1 (0/0 params, 4.61k/4.61k flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Conv2D, 1/1|1/1, 0:2x3x3x6|1:2x2x6x12)\n DW (3x3x3x6, 162/162 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables, 1/2|1/10, )\n DW/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:3x3x3x6|1:3x3x3x6)\n DW/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n DW/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:3x3x3x6|1:1)\n DW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:4)\n DW/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:3x3x3x6|1:1)\n DW/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW/read (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity, 1/1|1/1, 0:3x3x3x6)\n DW2 (2x2x6x12, 288/288 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|VariableV2|_trainable_variables, 1/2|1/10, )\n DW2/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:2x2x6x12|1:2x2x6x12)\n DW2/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n DW2/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:2x2x6x12|1:1)\n DW2/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:4)\n DW2/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW2/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:2x2x6x12|1:1)\n DW2/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW2/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n DW2/read (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Identity, 1/1|1/1, 0:2x2x6x12)\n ScalarW (1, 1/1 params, 0/0 flops, VariableV2|_trainable_variables, 0/0|1/10, )\n ScalarW/Assign (0/0 params, 0/0 flops, Assign, 0/0|1/1, 0:1|1:1)\n ScalarW/Initializer (0/0 params, 0/0 flops, _kTFScopeParent, 0/0|1/7, )\n ScalarW/Initializer/random_normal (0/0 params, 0/0 flops, Add, 0/0|1/6, 0:1|1:1)\n ScalarW/Initializer/random_normal/RandomStandardNormal (0/0 params, 0/0 flops, RandomStandardNormal, 0/0|1/1, 0:0)\n ScalarW/Initializer/random_normal/mean (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n ScalarW/Initializer/random_normal/mul (0/0 params, 0/0 flops, Mul, 0/0|1/1, 0:1|1:1)\n ScalarW/Initializer/random_normal/shape (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n ScalarW/Initializer/random_normal/stddev (0/0 params, 0/0 flops, Const, 0/0|1/1, )\n ScalarW/read (0/0 params, 0/0 flops, Identity, 0/0|1/1, 0:1)\n _retval_Conv2D_1_0_0 (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|RunTimeOp, 1/1|1/1, )\n init (0/0 params, 0/0 flops, NoOp, 0/0|1/1, 0:1|1:3x3x3x6|2:2x2x6x12)\n zeros (0/0 params, 0/0 flops, /job:localhost/replica:0/task:0/cpu:0, /job:localhost/replica:0/task:0/cpu:0|Const, 1/1|1/1, )\n',
f.read())
def testSimpleCodeView(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
# TODO(xpan): Test 'micros'. Since the execution time changes each run,
# it's a bit difficult to test it now.
opts = (builder(builder.trainable_variables_parameter())
.with_file_output(outfile)
.with_accounted_types(['.*'])
.with_node_names(show_name_regexes=['.*model_analyzer_testlib.*'])
.account_displayed_op_only(False)
.select(['bytes', 'params', 'float_ops', 'num_hidden_ops', 'device',
'input_shapes']).build())
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(
sess.graph, run_meta, cmd='code', options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
self.assertEqual(
'node name | output bytes | # parameters | # float_ops | assigned devices | input',
f.read()[0:80])
def testSelectEverything(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(
builder.trainable_variables_parameter()).with_file_output(
outfile).with_accounted_types(['.*']).select([
'params', 'float_ops', 'occurrence', 'device', 'op_types',
'input_shapes'
]).build())
rewriter_config = rewriter_config_pb2.RewriterConfig(
disable_model_pruning=True)
graph_options = config_pb2.GraphOptions(
rewrite_options=rewriter_config)
config = config_pb2.ConfigProto(graph_options=graph_options)
with session.Session(
config=config) as sess, ops.device('/device:CPU:0'):
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(sess.graph, run_meta, options=opts)
def testSimpleCodeView(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
# TODO(xpan): Test 'micros'. Since the execution time changes each run,
# it's a bit difficult to test it now.
opts = (builder(
builder.trainable_variables_parameter()).with_file_output(
outfile).with_accounted_types(['.*']).with_node_names(
show_name_regexes=['.*model_analyzer_testlib.*']).
account_displayed_op_only(False).select([
'bytes', 'params', 'float_ops', 'num_hidden_ops', 'device',
'input_shapes'
]).build())
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(sess.graph,
run_meta,
cmd='code',
options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
self.assertEqual(
'node name | requested bytes | # parameters | # float_ops | assigned devices | in',
lib.CheckAndRemoveDoc(f.read())[0:80])
def testSelectEverthingDetail(self):
ops.reset_default_graph()
dev = '/gpu:0' if test.is_gpu_available() else '/cpu:0'
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(builder.trainable_variables_parameter())
.with_file_output(outfile)
.with_accounted_types(['.*'])
.select(['micros', 'bytes', 'params', 'float_ops', 'occurrence',
'device', 'op_types', 'input_shapes']).build())
config = config_pb2.ConfigProto()
with session.Session(config=config) as sess, ops.device(dev):
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(
sess.graph, run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
outputs = f.read().split('\n')
self.assertEqual(outputs[0],
'node name | # parameters | # float_ops | requested bytes | total execution time | accelerator execution time | cpu execution time | assigned devices | op types | op count (run|defined) | input shapes')
for o in outputs[1:]:
if o.find('Conv2D ') > 0:
metrics = o[o.find('(') +1: o.find(')')].split(',')
# Make sure time is profiled.
gap = 1 if test.is_gpu_available() else 2
for i in range(3, 6, gap):
mat = re.search('(.*)[um]s/(.*)[um]s', metrics[i])
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)
# Make sure device is profiled.
if test.is_gpu_available():
self.assertTrue(metrics[6].find('gpu') > 0)
self.assertFalse(metrics[6].find('cpu') > 0)
else:
self.assertFalse(metrics[6].find('gpu') > 0)
self.assertTrue(metrics[6].find('cpu') > 0)
# Make sure float_ops is profiled.
mat = re.search('(.*)k/(.*)k flops', metrics[1].strip())
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)
# Make sure op_count is profiled.
self.assertEqual(metrics[8].strip(), '1/1|1/1')
# Make sure input_shapes is profiled.
self.assertEqual(metrics[9].strip(), '0:2x6x6x3|1:3x3x3x6')
if o.find('DW (3x3x3x6') > 0:
metrics = o[o.find('(') +1: o.find(')')].split(',')
mat = re.search('(.*)/(.*) params', metrics[1].strip())
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)
def testSelectEverything(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(builder.trainable_variables_parameter())
.with_file_output(outfile)
.with_accounted_types(['.*'])
.select(['params', 'float_ops', 'occurrence', 'device', 'op_types',
'input_shapes']).build())
rewriter_config = rewriter_config_pb2.RewriterConfig(
disable_model_pruning=True)
graph_options = config_pb2.GraphOptions(rewrite_options=rewriter_config)
config = config_pb2.ConfigProto(graph_options=graph_options)
with session.Session(config=config) as sess, ops.device('/device:CPU:0'):
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(
sess.graph, run_meta, options=opts)
def _profiled_run(self,
fetches,
feed_dict=None,
options=None,
run_metadata=None):
"""Overwrites the session.run()."""
# pylint: disable=protected-access
# Count the session steps.
self.profile_context._new_step()
# Fast path if no need for profiling.
to_profiles = self.profile_context._profile_candidates()
to_dumps = self.profile_context._dump_candidates()
if (not to_profiles and not to_dumps
and not self.profile_context._is_capture_enforced()):
return self._profiler_run_internal(fetches, feed_dict, options,
run_metadata)
# Enable tracing, perform auto profiling or auto dump.
if not run_metadata:
run_metadata = config_pb2.RunMetadata()
if not options:
options = config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE)
old_trace_level = options.trace_level
else:
old_trace_level = options.trace_level
options.trace_level = config_pb2.RunOptions.FULL_TRACE
ret = self._profiler_run_internal(fetches, feed_dict, options,
run_metadata)
if self.profile_context._capture_next_step:
self.profile_context._add_run_meta(run_metadata)
for to_dump in to_dumps:
outdir, _ = to_dump
if not gfile.Exists(outdir):
gfile.MakeDirs(outdir)
with gfile.Open(os.path.join(outdir, 'graph.pbtxt'), 'w') as f:
f.write('%s' % self.graph.as_graph_def(add_shapes=True))
with gfile.Open(os.path.join(outdir, 'run_metadata'), 'w') as f:
f.write(run_metadata.SerializeToString())
tfprof_logger.write_op_log(self.graph,
outdir,
run_meta=run_metadata,
add_trace=True)
for to_prof in to_profiles:
cmd, opts, _ = to_prof
model_analyzer.profile(self.graph,
run_meta=run_metadata,
cmd=cmd,
options=opts)
# Restore to default.
options.trace_level = old_trace_level
return ret
def _profiled_run(self,
fetches,
feed_dict=None,
options=None,
run_metadata=None):
"""Overwrites the session.run()."""
# pylint: disable=protected-access
# Count the session steps.
self.profile_context._new_step()
# Fast path if no need for profiling.
to_profiles = self.profile_context._profile_candidates()
to_dumps = self.profile_context._dump_candidates()
if (not to_profiles and not to_dumps and
not self.profile_context._is_capture_enforced()):
return self._profiler_run_internal(
fetches, feed_dict, options, run_metadata)
# Enable tracing, perform auto profiling or auto dump.
if not run_metadata:
run_metadata = config_pb2.RunMetadata()
if not options:
options = config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE)
old_trace_level = options.trace_level
else:
old_trace_level = options.trace_level
options.trace_level = config_pb2.RunOptions.FULL_TRACE
ret = self._profiler_run_internal(fetches, feed_dict, options, run_metadata)
if self.profile_context._capture_next_step:
self.profile_context._add_run_meta(run_metadata)
for to_dump in to_dumps:
outdir, _ = to_dump
if not gfile.Exists(outdir):
gfile.MakeDirs(outdir)
with gfile.Open(os.path.join(outdir, 'graph.pbtxt'), 'w') as f:
f.write('%s' % self.graph.as_graph_def(add_shapes=True))
with gfile.Open(os.path.join(outdir, 'run_metadata'), 'w') as f:
f.write(run_metadata.SerializeToString())
tfprof_logger.write_op_log(
self.graph, outdir, run_meta=run_metadata, add_trace=True)
for to_prof in to_profiles:
cmd, opts, _ = to_prof
model_analyzer.profile(
self.graph, run_meta=run_metadata, cmd=cmd, options=opts)
# Restore to default.
options.trace_level = old_trace_level
return ret
def testSelectOption(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
def check_selection(selected, not_selected):
with gfile.Open(outfile, 'r') as f:
s = f.read()
for attr in selected:
self.assertTrue(s.find(attr) > 0, s)
for attr in not_selected:
self.assertFalse(s.find(attr) > 0, s)
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
opts = builder(
builder.time_and_memory()).with_file_output(outfile).select(
['micros']).build()
_ = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_selection(
['total execution time', 'accelerator execution time'],
['bytes'])
opts = builder(
builder.time_and_memory()).with_file_output(outfile).select(
['bytes']).build()
_ = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_selection(['requested bytes'],
['peak bytes', 'residual bytes', 'output bytes'])
opts = builder(
builder.time_and_memory()).with_file_output(outfile).select(
['peak_bytes', 'residual_bytes', 'output_bytes']).build()
_ = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_selection(['peak bytes', 'residual bytes', 'output bytes'],
['requested_bytes'])
def testComplexCodeView(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(builder.trainable_variables_parameter())
.with_file_output(outfile)
.with_accounted_types(['.*'])
.with_node_names(show_name_regexes=
['.*model_analyzer_testlib.py.*'])
.account_displayed_op_only(False)
.select(['params', 'float_ops']).build())
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(
sess.graph, run_meta, cmd='code', options=opts)
# pylint: disable=line-too-long
with gfile.Open(outfile, 'r') as f:
lines = f.read().split('\n')
result = '\n'.join([l[:min(len(l), 80)] for l in lines])
self.assertEqual('node name | # parameters | # float_ops\n_TFProfRoot (--/2.84k params, --/91.04k flops)\n model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_... (0/1.80k para\n model_analyzer_testlib.py:35:BuildSmallModel:image = array_ops... (0/0 param\n model_analyzer_testlib.py:39:BuildSmallModel:initializer=init_... (0/4 param\n model_analyzer_testlib.py:43:BuildSmallModel:initializer=init_... (0/648 par\n model_analyzer_testlib.py:44:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n model_analyzer_testlib.py:48:BuildSmallModel:initializer=init_... (0/1.15k p\n model_analyzer_testlib.py:49:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_... (gradient) (0\n model_analyzer_testlib.py:44:BuildSmallModel:x = nn_ops.conv2d... (gradient)\n model_analyzer_testlib.py:49:BuildSmallModel:x = nn_ops.conv2d... (gradient)\n model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c... (0/1.04k para\n model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c... (gradient) (0\n model_analyzer_testlib.py:64:BuildFullModel:target = array_op... (0/0 params, \n model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_... (0/0 params, \n model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_... (gradient) (0\n model_analyzer_testlib.py:67:BuildFullModel:return sgd_op.min... (0/0 params, \n',
result)
self.assertLess(0, tfprof_node.total_exec_micros)
self.assertEqual(2844, tfprof_node.total_parameters)
self.assertEqual(91040, tfprof_node.total_float_ops)
self.assertEqual(8, len(tfprof_node.children))
self.assertEqual('_TFProfRoot', tfprof_node.name)
self.assertEqual(
'model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_...',
tfprof_node.children[0].name)
self.assertEqual(
'model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_... (gradient)',
tfprof_node.children[1].name)
self.assertEqual(
'model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c...',
tfprof_node.children[2].name)
self.assertEqual(
'model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c... (gradient)',
tfprof_node.children[3].name)
self.assertEqual(
'model_analyzer_testlib.py:64:BuildFullModel:target = array_op...',
tfprof_node.children[4].name)
self.assertEqual(
'model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_...',
tfprof_node.children[5].name)
self.assertEqual(
'model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_... (gradient)',
tfprof_node.children[6].name)
self.assertEqual(
'model_analyzer_testlib.py:67:BuildFullModel:return sgd_op.min...',
tfprof_node.children[7].name)
def testTimeline(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
outfile = os.path.join(test.get_temp_dir(), 'timeline')
opts['output'] = 'timeline:outfile=' + outfile
opts['account_type_regexes'] = ['.*']
opts['max_depth'] = 100000
opts['step'] = 0
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
_ = model_analyzer.profile(sess.graph,
run_meta,
cmd='graph',
options=opts)
with gfile.Open(outfile, 'r') as f:
# Test that a json file is created.
# TODO(xpan): tfprof Timeline isn't quite correct on Windows.
# Investigate why.
if os.name != 'nt':
self.assertLess(1000, len(f.read()))
else:
self.assertLess(1, len(f.read()))
def testCodeViewLeafGraphNode(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
opts['account_type_regexes'] = ['.*']
opts['account_displayed_op_only'] = False
opts['select'] = ['bytes', 'params', 'float_ops', 'device']
opts['output'] = 'none'
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(sess.graph,
run_meta,
cmd='code',
options=opts)
leaf = tfprof_node
while leaf.children:
self.assertEqual(0, len(leaf.graph_nodes))
leaf = leaf.children[0]
self.assertEqual(1, len(leaf.graph_nodes))
def _run_model():
x = random_ops.random_normal(shape=[1, SIZE])
w = random_ops.random_normal(shape=[SIZE, 2 * SIZE])
y = math_ops.matmul(x, w)
config = config_pb2.ConfigProto()
config.graph_options.rewrite_options.arithmetic_optimization = (
rewriter_config_pb2.RewriterConfig.OFF)
with session.Session(config=config) as sess:
run_metadata = config_pb2.RunMetadata()
opts = builder.time_and_memory()
opts['min_micros'] = 0
opts['min_bytes'] = 0
opts['order_by'] = 'name'
opts['output'] = 'none'
_ = sess.run(y,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_metadata)
tfprof_node = model_analyzer.profile(
sess.graph,
run_meta=run_metadata,
options=opts)
return tfprof_node, run_metadata
def testCodeViewLeafGraphNode(self):
ops.reset_default_graph()
opts = (builder(builder.trainable_variables_parameter())
.with_empty_output()
.with_accounted_types(['.*'])
.account_displayed_op_only(False)
.select(['bytes', 'params', 'float_ops', 'device']).build())
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(
sess.graph, run_meta, cmd='code', options=opts)
leaf = tfprof_node
while leaf.children:
self.assertEqual(0, len(leaf.graph_nodes))
leaf = leaf.children[0]
self.assertEqual(1, len(leaf.graph_nodes))
def testTimeline(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
outfile = os.path.join(test.get_temp_dir(), 'timeline')
opts['output'] = 'timeline:outfile=' + outfile
opts['account_type_regexes'] = ['.*']
opts['max_depth'] = 100000
opts['step'] = 0
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(
x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
_ = model_analyzer.profile(
sess.graph, run_meta, cmd='graph', options=opts)
with gfile.Open(outfile, 'r') as f:
# Test that a json file is created.
# TODO(xpan): tfprof Timeline isn't quite correct on Windows.
# Investigate why.
if os.name != 'nt':
self.assertLess(1000, len(f.read()))
else:
self.assertLess(1, len(f.read()))
def testTimeline(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'timeline')
opts = (builder(builder.trainable_variables_parameter())
.with_max_depth(100000)
.with_step(0)
.with_timeline_output(outfile)
.with_accounted_types(['.*']).build())
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(
x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
_ = model_analyzer.profile(
sess.graph, run_meta, cmd='graph', options=opts)
with gfile.Open(outfile, 'r') as f:
# Test that a json file is created.
# TODO(xpan): tfprof Timeline isn't quite correct on Windows.
# Investigate why.
if os.name != 'nt':
self.assertLess(1000, len(f.read()))
else:
self.assertLess(1, len(f.read()))
def testCodeViewLeafGraphNode(self):
ops.reset_default_graph()
opts = (builder(builder.trainable_variables_parameter()).
with_empty_output().with_accounted_types(
['.*']).account_displayed_op_only(False).select(
['bytes', 'params', 'float_ops', 'device']).build())
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(sess.graph,
run_meta,
cmd='code',
options=opts)
leaf = tfprof_node
while leaf.children:
self.assertEqual(0, len(leaf.graph_nodes))
leaf = leaf.children[0]
self.assertEqual(1, len(leaf.graph_nodes))
def testTimeline(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'timeline')
opts = (
builder(
builder.trainable_variables_parameter()).with_max_depth(100000)
.with_step(0).with_timeline_output(outfile).with_accounted_types(
['.*']).build())
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
_ = model_analyzer.profile(sess.graph,
run_meta,
cmd='graph',
options=opts)
with gfile.Open(outfile + '_0', 'r') as f:
# Test that a json file is created.
# TODO(xpan): tfprof Timeline isn't quite correct on Windows.
# Investigate why.
if os.name != 'nt':
self.assertLess(1000, len(f.read()))
else:
self.assertLess(1, len(f.read()))
def _run_model():
x = random_ops.random_normal(shape=[1, SIZE])
w = random_ops.random_normal(shape=[SIZE, 2 * SIZE])
y = math_ops.matmul(x, w)
config = config_pb2.ConfigProto()
config.graph_options.rewrite_options.arithmetic_optimization = (
rewriter_config_pb2.RewriterConfig.OFF)
with session.Session(config=config) as sess:
run_metadata = config_pb2.RunMetadata()
opts = builder.time_and_memory()
opts['min_micros'] = 0
opts['min_bytes'] = 0
opts['order_by'] = 'name'
opts['output'] = 'none'
_ = sess.run(y,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.SOFTWARE_TRACE),
run_metadata=run_metadata)
tfprof_node = model_analyzer.profile(
sess.graph,
run_meta=run_metadata,
options=opts)
return tfprof_node, run_metadata
def testCodeViewLeafGraphNode(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
opts['account_type_regexes'] = ['.*']
opts['account_displayed_op_only'] = False
opts['select'] = [
'bytes', 'params', 'float_ops', 'device'
]
opts['output'] = 'none'
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(
sess.graph, run_meta, cmd='code', options=opts)
leaf = tfprof_node
while leaf.children:
self.assertEqual(0, len(leaf.graph_nodes))
leaf = leaf.children[0]
self.assertEqual(1, len(leaf.graph_nodes))
def get_flops(model, write_path=tempfile.NamedTemporaryFile().name):
forward_pass = tf.function(model.call,
input_signature=[tf.TensorSpec(shape=(1,) + model.input_shape[1:])])
opts = ProfileOptionBuilder.float_operation()
if write_path:
opts['output'] = 'file:outfile={}'.format(write_path)
graph_info = profile(forward_pass.get_concrete_function().graph, options=opts)
return graph_info.total_float_ops
def testDumpToFile(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = builder(builder.trainable_variables_parameter()
).with_file_output(outfile).build()
with session.Session() as sess:
_ = lib.BuildSmallModel()
model_analyzer.profile(sess.graph, options=opts)
with gfile.Open(outfile, 'r') as f:
self.assertEqual(u'node name | # parameters\n'
'_TFProfRoot (--/451 params)\n'
' DW (3x3x3x6, 162/162 params)\n'
' DW2 (2x2x6x12, 288/288 params)\n'
' ScalarW (1, 1/1 params)\n',
f.read())
def testDumpToFile(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts['output'] = 'file:outfile=' + outfile
with session.Session() as sess:
_ = lib.BuildSmallModel()
model_analyzer.profile(sess.graph, options=opts)
with gfile.Open(outfile, 'r') as f:
self.assertEqual(
u'node name | # parameters\n'
'_TFProfRoot (--/451 params)\n'
' DW (3x3x3x6, 162/162 params)\n'
' DW2 (2x2x6x12, 288/288 params)\n'
' ScalarW (1, 1/1 params)\n', f.read())
def testDumpToFile(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts['output'] = 'file:outfile=' + outfile
with session.Session() as sess:
_ = lib.BuildSmallModel()
model_analyzer.profile(sess.graph, options=opts)
with gfile.Open(outfile, 'r') as f:
self.assertEqual(u'node name | # parameters\n'
'_TFProfRoot (--/451 params)\n'
' DW (3x3x3x6, 162/162 params)\n'
' DW2 (2x2x6x12, 288/288 params)\n'
' ScalarW (1, 1/1 params)\n',
f.read())
def testDumpToFile(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = builder(builder.trainable_variables_parameter()
).with_file_output(outfile).build()
with session.Session() as sess:
_ = lib.BuildSmallModel()
model_analyzer.profile(sess.graph, options=opts)
with gfile.Open(outfile, 'r') as f:
self.assertEqual(u'node name | # parameters\n'
'_TFProfRoot (--/451 params)\n'
' DW (3x3x3x6, 162/162 params)\n'
' DW2 (2x2x6x12, 288/288 params)\n'
' ScalarW (1, 1/1 params)\n',
f.read())
def testComplexCodeView(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(
builder.trainable_variables_parameter()).with_file_output(
outfile).with_accounted_types(['.*']).with_node_names(
show_name_regexes=['.*model_analyzer_testlib.py.*']).
account_displayed_op_only(False).select(
['params', 'float_ops']).build())
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(sess.graph,
run_meta,
cmd='code',
options=opts)
# pylint: disable=line-too-long
with gfile.Open(outfile, 'r') as f:
lines = f.read().split('\n')
result = '\n'.join([l[:min(len(l), 80)] for l in lines])
self.assertEqual(
'node name | # parameters | # float_ops\n_TFProfRoot (--/2.84k params, --/91.04k flops)\n model_analyzer_testlib.py:58:BuildFullModel (0/1.80k params, 0/41.76k flops)\n model_analyzer_testlib.py:35:BuildSmallModel (0/0 params, 0/0 flops)\n model_analyzer_testlib.py:39:BuildSmallModel (0/4 params, 0/0 flops)\n model_analyzer_testlib.py:43:BuildSmallModel (0/648 params, 0/0 flops)\n model_analyzer_testlib.py:44:BuildSmallModel (0/0 params, 0/23.33k flops)\n model_analyzer_testlib.py:48:BuildSmallModel (0/1.15k params, 0/0 flops)\n model_analyzer_testlib.py:49:BuildSmallModel (0/0 params, 0/18.43k flops)\n model_analyzer_testlib.py:58:BuildFullModel (gradient) (0/0 params, 0/0 flops)\n model_analyzer_testlib.py:44:BuildSmallModel (gradient) (0/0 params, 0/0 flo\n model_analyzer_testlib.py:49:BuildSmallModel (gradient) (0/0 params, 0/0 flo\n model_analyzer_testlib.py:62:BuildFullModel (0/1.04k params, 0/16.51k flops)\n model_analyzer_testlib.py:62:BuildFullModel (gradient) (0/0 params, 0/32.77k f\n model_analyzer_testlib.py:64:BuildFullModel (0/0 params, 0/0 flops)\n model_analyzer_testlib.py:65:BuildFullModel (0/0 params, 0/0 flops)\n model_analyzer_testlib.py:65:BuildFullModel (gradient) (0/0 params, 0/0 flops)\n model_analyzer_testlib.py:67:BuildFullModel (0/0 params, 0/0 flops)\n',
result)
self.assertLess(0, tfprof_node.total_exec_micros)
self.assertEqual(2844, tfprof_node.total_parameters)
self.assertEqual(91040, tfprof_node.total_float_ops)
self.assertEqual(8, len(tfprof_node.children))
self.assertEqual('_TFProfRoot', tfprof_node.name)
self.assertEqual('model_analyzer_testlib.py:58:BuildFullModel',
tfprof_node.children[0].name)
self.assertEqual(
'model_analyzer_testlib.py:58:BuildFullModel (gradient)',
tfprof_node.children[1].name)
self.assertEqual('model_analyzer_testlib.py:62:BuildFullModel',
tfprof_node.children[2].name)
self.assertEqual(
'model_analyzer_testlib.py:62:BuildFullModel (gradient)',
tfprof_node.children[3].name)
self.assertEqual('model_analyzer_testlib.py:64:BuildFullModel',
tfprof_node.children[4].name)
self.assertEqual('model_analyzer_testlib.py:65:BuildFullModel',
tfprof_node.children[5].name)
self.assertEqual(
'model_analyzer_testlib.py:65:BuildFullModel (gradient)',
tfprof_node.children[6].name)
self.assertEqual('model_analyzer_testlib.py:67:BuildFullModel',
tfprof_node.children[7].name)
def testOpView(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(
builder.trainable_variables_parameter()).with_file_output(
outfile).with_accounted_types([
'.*'
]).with_min_occurrence(10).order_by('occurrence').select(
['params', 'micros', 'occurrence',
'input_shapes']).build())
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(sess.graph,
run_meta,
cmd='op',
options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
self.assertEqual(
'nodename|totalexecutiontime|acceleratorexecutiontime|cpuexecutiontime|#parameters|opoccurrence(run|defined)|inputshapes\n',
f.read().replace('\t', '').replace(' ', '')[0:120])
# pylint: enable=line-too-long
total_children = 0
last_occurrence = 1e32
input_shapes = 0
last_total_micros = tfprof_node.total_exec_micros
last_micros = tfprof_node.exec_micros
while tfprof_node.children:
for gnode in tfprof_node.graph_nodes:
input_shapes += len(gnode.input_shapes)
self.assertEqual(len(tfprof_node.children), 1)
tfprof_node = tfprof_node.children[0]
self.assertEqual(last_total_micros,
tfprof_node.total_exec_micros + last_micros)
last_total_micros = tfprof_node.total_exec_micros
last_micros = tfprof_node.exec_micros
total_children += 1
self.assertLessEqual(len(tfprof_node.graph_nodes),
last_occurrence)
last_occurrence = len(tfprof_node.graph_nodes)
self.assertEqual(total_children, 15)
self.assertGreater(input_shapes, 0)
def testOpView(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(builder.trainable_variables_parameter())
.with_file_output(outfile)
.with_accounted_types(['.*'])
.with_min_occurrence(10)
.order_by('occurrence')
.select(['params', 'micros', 'bytes',
'peak_bytes', 'residual_bytes',
'output_bytes', 'occurrence', 'input_shapes']).build())
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(
sess.graph, run_meta, cmd='op', options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
self.assertEqual(
'nodename|requestedbytes|peakbytes|residualbytes|outputbytes|totalexecutiontime|acceleratorexecutiontime|cpuexecutiontime|#parameters|opoccurrence(run|defined)|inputshapes',
lib.CheckAndRemoveDoc(f.read()).replace('\t',
'').replace(' ', '')[0:170])
# pylint: enable=line-too-long
total_children = 0
last_occurrence = 1e32
input_shapes = 0
last_total_micros = tfprof_node.total_exec_micros
last_micros = tfprof_node.exec_micros
while tfprof_node.children:
for gnode in tfprof_node.graph_nodes:
input_shapes += len(gnode.input_shapes)
self.assertEqual(len(tfprof_node.children), 1)
tfprof_node = tfprof_node.children[0]
self.assertEqual(
last_total_micros, tfprof_node.total_exec_micros + last_micros)
last_total_micros = tfprof_node.total_exec_micros
last_micros = tfprof_node.exec_micros
total_children += 1
self.assertLessEqual(len(tfprof_node.graph_nodes), last_occurrence)
last_occurrence = len(tfprof_node.graph_nodes)
self.assertGreater(input_shapes, 0)
def testSelectOption(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
def check_selection(selected, not_selected):
with gfile.Open(outfile, 'r') as f:
s = f.read()
for attr in selected:
self.assertTrue(s.find(attr) > 0, s)
for attr in not_selected:
self.assertFalse(s.find(attr) > 0, s)
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
opts = builder(builder.time_and_memory()
).with_file_output(outfile).select(['micros']).build()
_ = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_selection(['total execution time', 'accelerator execution time'],
['bytes'])
opts = builder(builder.time_and_memory()
).with_file_output(outfile).select(['bytes']).build()
_ = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_selection(['requested bytes'],
['peak bytes', 'residual bytes', 'output bytes'])
opts = builder(builder.time_and_memory()).with_file_output(
outfile).select(
['peak_bytes', 'residual_bytes', 'output_bytes']).build()
_ = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_selection(['peak bytes', 'residual bytes', 'output bytes'],
['requested_bytes'])
def testComplexCodeView(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts['output'] = 'file:outfile=' + outfile
opts['account_type_regexes'] = ['.*']
opts['show_name_regexes'] = ['.*model_analyzer_testlib.py.*']
opts['account_displayed_op_only'] = False
opts['select'] = ['params', 'float_ops']
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(sess.graph,
run_meta,
cmd='code',
options=opts)
# pylint: disable=line-too-long
with gfile.Open(outfile, 'r') as f:
lines = f.read().split('\n')
result = '\n'.join([l[:min(len(l), 80)] for l in lines])
self.assertEqual(
'node name | # parameters | # float_ops\n_TFProfRoot (--/2.84k params, --/91.04k flops)\n model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_... (0/1.80k para\n model_analyzer_testlib.py:35:BuildSmallModel:image = array_ops... (0/0 param\n model_analyzer_testlib.py:39:BuildSmallModel:initializer=init_... (0/4 param\n model_analyzer_testlib.py:43:BuildSmallModel:initializer=init_... (0/648 par\n model_analyzer_testlib.py:44:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n model_analyzer_testlib.py:48:BuildSmallModel:initializer=init_... (0/1.15k p\n model_analyzer_testlib.py:49:BuildSmallModel:x = nn_ops.conv2d... (0/0 param\n model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c... (0/1.04k para\n model_analyzer_testlib.py:64:BuildFullModel:target = array_op... (0/0 params, \n model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_... (0/0 params, \n model_analyzer_testlib.py:67:BuildFullModel:return sgd_op.min... (0/0 params, \n',
result)
self.assertLess(0, tfprof_node.total_exec_micros)
self.assertEqual(2844, tfprof_node.total_parameters)
self.assertEqual(91040, tfprof_node.total_float_ops)
self.assertEqual(5, len(tfprof_node.children))
self.assertEqual('_TFProfRoot', tfprof_node.name)
self.assertEqual(
'model_analyzer_testlib.py:58:BuildFullModel:seq.append(array_...',
tfprof_node.children[0].name)
self.assertEqual(
'model_analyzer_testlib.py:62:BuildFullModel:cell, array_ops.c...',
tfprof_node.children[1].name)
self.assertEqual(
'model_analyzer_testlib.py:64:BuildFullModel:target = array_op...',
tfprof_node.children[2].name)
self.assertEqual(
'model_analyzer_testlib.py:65:BuildFullModel:loss = nn_ops.l2_...',
tfprof_node.children[3].name)
self.assertEqual(
'model_analyzer_testlib.py:67:BuildFullModel:return sgd_op.min...',
tfprof_node.children[4].name)
def testOpView(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts['output'] = 'file:outfile=' + outfile
opts['account_type_regexes'] = ['.*']
opts['min_occurrence'] = 10
opts['select'] = ['params', 'micros', 'occurrence', 'input_shapes']
opts['order_by'] = 'occurrence'
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(
sess.graph, run_meta, cmd='op', options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
self.assertEqual(
'nodename|totalexecutiontime|acceleratorexecutiontime|cpuexecutiontime|#parameters|opoccurrence(run|defined)|inputshapes\n',
f.read().replace('\t', '').replace(' ', '')[0:120])
# pylint: enable=line-too-long
total_children = 0
last_occurrence = 1e32
input_shapes = 0
last_total_micros = tfprof_node.total_exec_micros
last_micros = tfprof_node.exec_micros
while tfprof_node.children:
for gnode in tfprof_node.graph_nodes:
input_shapes += len(gnode.input_shapes)
self.assertEqual(len(tfprof_node.children), 1)
tfprof_node = tfprof_node.children[0]
self.assertEqual(
last_total_micros, tfprof_node.total_exec_micros + last_micros)
last_total_micros = tfprof_node.total_exec_micros
last_micros = tfprof_node.exec_micros
total_children += 1
self.assertLessEqual(len(tfprof_node.graph_nodes), last_occurrence)
last_occurrence = len(tfprof_node.graph_nodes)
self.assertEqual(total_children, 15)
self.assertGreater(input_shapes, 0)
def get_flops(self):
@tf.function(input_signature=[
tf.TensorSpec(shape=(1, ) + self._eval_model.input_shape[1:],
dtype=tf.float32,
name='images')
])
def inference_function(images):
return self._eval_model(images, training=False)
concrete_funtion = inference_function.get_concrete_function()
graph_info = profile(concrete_funtion.graph,
options=ProfileOptionBuilder.float_operation())
flops = graph_info.total_float_ops // 2
return flops
def _run_loop_model():
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
tfprof_node = model_analyzer.profile(
sess.graph, run_meta,
options=builder.time_and_memory())
return tfprof_node, run_meta
def pprof_test_helper(self, attribute, should_fail=False):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), attribute + '_pprof.pb.gz')
opts = (builder(builder.time_and_memory())
.select([attribute])
.with_max_depth(100000)
.with_node_names(trim_name_regexes=['ops.py.*'])
.with_pprof_output(outfile).build())
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(
x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
_ = model_analyzer.profile(
sess.graph, run_meta, cmd='code', options=opts)
if should_fail:
self.assertFalse(gfile.Exists(outfile))
return
profile_pb = profile_pb2.Profile()
with gfile.Open(outfile, 'rb') as f:
with gzip.GzipFile(fileobj=io.BytesIO(f.read())) as gzipf:
profile_pb.ParseFromString(gzipf.read())
self.assertGreater(len(profile_pb.sample), 10)
self.assertGreater(len(profile_pb.location), 10)
self.assertGreater(len(profile_pb.function), 10)
self.assertGreater(len(profile_pb.string_table), 30)
has_rnn = False
has_loop = False
for s in profile_pb.string_table:
if s.find('rnn') > 0:
has_rnn = True
if s.find('while') > 0:
has_loop = True
self.assertFalse(s.startswith('ops.py'))
self.assertTrue(has_rnn)
self.assertTrue(has_loop)
def pprof_test_helper(self, attribute, should_fail=False):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), attribute + '_pprof.pb.gz')
opts = (builder(builder.time_and_memory()).select([
attribute
]).with_max_depth(100000).with_node_names(
trim_name_regexes=['ops.py.*']).with_pprof_output(outfile).build())
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
_ = model_analyzer.profile(sess.graph,
run_meta,
cmd='code',
options=opts)
if should_fail:
self.assertFalse(gfile.Exists(outfile))
return
profile_pb = profile_pb2.Profile()
with gfile.Open(outfile, 'rb') as f:
with gzip.GzipFile(fileobj=io.BytesIO(f.read())) as gzipf:
profile_pb.ParseFromString(gzipf.read())
self.assertGreater(len(profile_pb.sample), 10)
self.assertGreater(len(profile_pb.location), 10)
self.assertGreater(len(profile_pb.function), 10)
self.assertGreater(len(profile_pb.string_table), 30)
has_rnn = False
has_loop = False
for s in profile_pb.string_table:
if s.find('rnn') > 0:
has_rnn = True
if s.find('while') > 0:
has_loop = True
self.assertFalse(s.startswith('ops.py'))
self.assertTrue(has_rnn)
self.assertTrue(has_loop)
def get_num_flops(model, input_shape, readable_format=True):
if hasattr(model, 'model'):
model = model.model
forward_pass = tf.function(
model.call, input_signature=[tf.TensorSpec(shape=(1, ) + input_shape)])
graph_info = profile(forward_pass.get_concrete_function().graph,
options=ProfileOptionBuilder.float_operation())
# The //2 is necessary since `profile` counts multiply and accumulate
# as two flops, here we report the total number of multiply accumulate ops
flops = graph_info.total_float_ops // 2
if readable_format:
flops = float(flops) * 1e-9
return flops
def get_flops(self):
@tf.function(input_signature=[
tf.TensorSpec(shape=(1, ) + self._eval_model.input_shape[1:],
dtype=tf.float32,
name='images')
])
def inference_function(images):
return self._eval_model(images, training=False)
concrete_funtion = inference_function.get_concrete_function()
graph_info = profile(concrete_funtion.graph,
options=ProfileOptionBuilder.float_operation())
# The //2 is necessary since `profile` counts multiply and accumulate
# as two flops. We report the total number of multiply accumulate ops,
# polularly referred to as MACs
flops = graph_info.total_float_ops // 2
return flops
def _run_model():
x = random_ops.random_normal(shape=[1, SIZE])
w = random_ops.random_normal(shape=[SIZE, 2 * SIZE])
y = math_ops.matmul(x, w)
with session.Session() as sess:
run_metadata = config_pb2.RunMetadata()
opts = builder.time_and_memory()
opts['min_micros'] = 0
opts['min_bytes'] = 0
_ = sess.run(y,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_metadata)
tfprof_node = model_analyzer.profile(sess.graph,
run_meta=run_metadata,
options=opts)
return tfprof_node, run_metadata
def _run_model():
x = random_ops.random_normal(shape=[1, SIZE])
w = random_ops.random_normal(shape=[SIZE, 2 * SIZE])
y = math_ops.matmul(x, w)
with session.Session() as sess:
run_metadata = config_pb2.RunMetadata()
opts = builder.time_and_memory()
opts['min_micros'] = 0
opts['min_bytes'] = 0
_ = sess.run(y,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_metadata)
tfprof_node = model_analyzer.profile(
sess.graph,
run_meta=run_metadata,
options=opts)
return tfprof_node, run_metadata
def _run_loop_model():
config = config_pb2.ConfigProto()
# Grappler might fuse MatMul with BiasAdd in remapper optimizer.
config.graph_options.rewrite_options.remapping = (
rewriter_config_pb2.RewriterConfig.OFF)
with session.Session(config=config) as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.SOFTWARE_TRACE),
run_metadata=run_meta)
opts = builder.time_and_memory()
opts['order_by'] = 'name'
opts['output'] = 'none'
tfprof_node = model_analyzer.profile(
sess.graph, run_meta, options=opts)
return tfprof_node, run_meta
def testTraceLoopBytes(self):
if not test.is_gpu_available():
return
ops.reset_default_graph()
steps = 100
with ops.device('/gpu:0'):
x = array_ops.ones((100, 100), dtype=dtypes.float32)
n = array_ops.constant(steps, dtype=dtypes.int32)
x1 = array_ops.ones((100, 100))
x *= x1
def loop_body(i, x):
x *= x
return i + 1, x
_, y = control_flow_ops.while_loop(lambda i, x: i < n, loop_body,
[array_ops.constant(0), x])
grad = gradients.gradients(y, [x1])
with session.Session(config=self._no_rewrite_session_config()) as sess:
run_options = config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE)
run_metadata = config_pb2.RunMetadata()
sess.run(grad, options=run_options, run_metadata=run_metadata)
options = option_builder.ProfileOptionBuilder.time_and_memory()
options['min_bytes'] = 0
options['min_micros'] = 0
options['select'] = ('bytes', 'peak_bytes', 'output_bytes',
'residual_bytes')
options['output'] = 'none'
ret_pb = model_analyzer.profile(sess.graph,
run_meta=run_metadata,
cmd='scope',
options=options)
self.assertGreater(ret_pb.total_requested_bytes, 1000000)
def _run_loop_model():
config = config_pb2.ConfigProto()
# Grappler might fuse MatMul with BiasAdd in remapper optimizer.
config.graph_options.rewrite_options.remapping = (
rewriter_config_pb2.RewriterConfig.OFF)
with session.Session(config=config) as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
opts = builder.time_and_memory()
opts['order_by'] = 'name'
opts['output'] = 'none'
tfprof_node = model_analyzer.profile(
sess.graph, run_meta, options=opts)
return tfprof_node, run_meta
def testTraceLoopBytes(self):
if not test.is_gpu_available(): return
ops.reset_default_graph()
steps = 100
with ops.device('/gpu:0'):
x = array_ops.ones((100, 100), dtype=dtypes.float32)
n = array_ops.constant(steps, dtype=dtypes.int32)
x1 = array_ops.ones((100, 100))
x *= x1
def loop_body(i, x):
x *= x
return i + 1, x
_, y = control_flow_ops.while_loop(
lambda i, x: i < n, loop_body,
[array_ops.constant(0), x])
grad = gradients.gradients(y, [x1])
with session.Session() as sess:
run_options = config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE)
run_metadata = config_pb2.RunMetadata()
sess.run(grad, options=run_options, run_metadata=run_metadata)
options = option_builder.ProfileOptionBuilder.time_and_memory()
options['min_bytes'] = 0
options['min_micros'] = 0
options['select'] = ('bytes', 'peak_bytes', 'output_bytes',
'residual_bytes')
options['output'] = 'none'
ret_pb = model_analyzer.profile(
sess.graph, run_meta=run_metadata, cmd='scope', options=options)
self.assertGreater(ret_pb.total_requested_bytes, 1000000)
def testProfileBasic(self):
ops.reset_default_graph()
opts = model_analyzer.TRAINABLE_VARS_PARAMS_STAT_OPTIONS.copy()
opts['account_type_regexes'] = ['.*']
opts['select'] = ['params', 'float_ops', 'micros', 'bytes',
'device', 'op_types', 'occurrence']
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts['output'] = 'file:outfile=' + outfile
# Test the output without run_meta.
sess = session.Session()
r = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
profiler = model_analyzer.Profiler(sess.graph)
profiler.profile_name_scope(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='scope', options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
# Test the output with run_meta.
run_meta = config_pb2.RunMetadata()
_ = sess.run(r,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
profiler.add_step(1, run_meta)
profiler.profile_graph(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='graph', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
profiler.profile_python(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='code', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
profiler.profile_operations(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='op', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
model_analyzer.profile(
sess.graph, cmd='scope', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertNotEqual(pma_str, profiler_str)
opts2 = opts.copy()
opts2['select'] = ['params', 'float_ops']
profiler.profile_name_scope(opts2)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='scope', run_meta=run_meta, options=opts2)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
def testProfileBasic(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(builder.trainable_variables_parameter())
.with_file_output(outfile)
.with_accounted_types(['.*'])
.select(['params', 'float_ops', 'micros', 'bytes',
'device', 'op_types', 'occurrence']).build())
# Test the output without run_meta.
sess = session.Session()
r = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
# Test the output with run_meta.
run_meta = config_pb2.RunMetadata()
_ = sess.run(r,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
profiler = model_analyzer.Profiler(sess.graph)
profiler.add_step(1, run_meta)
profiler.profile_graph(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='graph', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
profiler.profile_name_scope(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='scope', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
profiler.profile_python(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='code', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
profiler.profile_operations(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='op', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
model_analyzer.profile(
sess.graph, cmd='scope', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertNotEqual(pma_str, profiler_str)
def testMinOption(self):
ops.reset_default_graph()
def check_min(nodes, mm=0, mam=0, mcm=0, mb=0, mpb=0, mrb=0, mob=0):
for n in nodes:
if mm > 0:
self.assertGreaterEqual(n.exec_micros, mm)
if mam > 0:
self.assertGreaterEqual(n.accelerator_exec_micros, mam)
if mcm > 0:
self.assertGreaterEqual(n.cpu_exec_micros, mcm)
if mb > 0:
self.assertGreaterEqual(n.requested_bytes, mb)
if mpb > 0:
self.assertGreaterEqual(n.peak_bytes, mpb)
if mrb > 0:
self.assertGreaterEqual(n.residual_bytes, mrb)
if mob > 0:
self.assertGreaterEqual(n.output_bytes, mob)
check_min(n.children, mm, mam, mcm, mb, mpb, mrb, mob)
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
min_val = random.randint(0, 10000)
opts = builder(builder.time_and_memory(
min_micros=min_val)).with_empty_output().build()
tfprof_node = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_min(tfprof_node.children, mm=min_val)
opts = builder(
builder.time_and_memory(min_accelerator_micros=min_val)
).with_empty_output().build()
tfprof_node = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_min(tfprof_node.children, mam=min_val)
opts = builder(builder.time_and_memory(
min_cpu_micros=min_val)).with_empty_output().build()
tfprof_node = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_min(tfprof_node.children, mcm=min_val)
opts = builder(builder.time_and_memory(
min_bytes=min_val)).with_empty_output().build()
tfprof_node = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_min(tfprof_node.children, mb=min_val)
opts = builder(builder.time_and_memory(
min_peak_bytes=min_val)).with_empty_output().build()
tfprof_node = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_min(tfprof_node.children, mpb=min_val)
opts = builder(builder.time_and_memory(
min_residual_bytes=min_val)).with_empty_output().build()
tfprof_node = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_min(tfprof_node.children, mrb=min_val)
opts = builder(builder.time_and_memory(
min_output_bytes=min_val)).with_empty_output().build()
tfprof_node = model_analyzer.profile(sess.graph,
run_meta=run_meta,
options=opts)
check_min(tfprof_node.children, mob=min_val)
def testMinOption(self):
ops.reset_default_graph()
def check_min(nodes, mm=0, mam=0, mcm=0, mb=0, mpb=0, mrb=0, mob=0):
for n in nodes:
if mm > 0:
self.assertGreaterEqual(n.exec_micros, mm)
if mam > 0:
self.assertGreaterEqual(n.accelerator_exec_micros, mam)
if mcm > 0:
self.assertGreaterEqual(n.cpu_exec_micros, mcm)
if mb > 0:
self.assertGreaterEqual(n.requested_bytes, mb)
if mpb > 0:
self.assertGreaterEqual(n.peak_bytes, mpb)
if mrb > 0:
self.assertGreaterEqual(n.residual_bytes, mrb)
if mob > 0:
self.assertGreaterEqual(n.output_bytes, mob)
check_min(n.children, mm, mam, mcm, mb, mpb, mrb, mob)
with session.Session() as sess:
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
min_val = random.randint(0, 10000)
opts = builder(builder.time_and_memory(min_micros=min_val)
).with_empty_output().build()
tfprof_node = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_min(tfprof_node.children, mm=min_val)
opts = builder(builder.time_and_memory(min_accelerator_micros=min_val)
).with_empty_output().build()
tfprof_node = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_min(tfprof_node.children, mam=min_val)
opts = builder(builder.time_and_memory(min_cpu_micros=min_val)
).with_empty_output().build()
tfprof_node = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_min(tfprof_node.children, mcm=min_val)
opts = builder(builder.time_and_memory(min_bytes=min_val)
).with_empty_output().build()
tfprof_node = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_min(tfprof_node.children, mb=min_val)
opts = builder(builder.time_and_memory(min_peak_bytes=min_val)
).with_empty_output().build()
tfprof_node = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_min(tfprof_node.children, mpb=min_val)
opts = builder(builder.time_and_memory(min_residual_bytes=min_val)
).with_empty_output().build()
tfprof_node = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_min(tfprof_node.children, mrb=min_val)
opts = builder(builder.time_and_memory(min_output_bytes=min_val)
).with_empty_output().build()
tfprof_node = model_analyzer.profile(
sess.graph, run_meta=run_meta, options=opts)
check_min(tfprof_node.children, mob=min_val)
def testProfileBasic(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(builder.trainable_variables_parameter())
.with_file_output(outfile)
.with_accounted_types(['.*'])
.select(['params', 'float_ops', 'micros', 'bytes',
'device', 'op_types', 'occurrence']).build())
# Test the output without run_meta.
sess = session.Session()
r = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
# Test the output with run_meta.
run_meta = config_pb2.RunMetadata()
_ = sess.run(r,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
profiler = model_analyzer.Profiler(sess.graph)
profiler.add_step(1, run_meta)
profiler.profile_graph(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='graph', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
profiler.profile_name_scope(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='scope', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
profiler.profile_python(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='code', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
profiler.profile_operations(opts)
with gfile.Open(outfile, 'r') as f:
profiler_str = f.read()
model_analyzer.profile(
sess.graph, cmd='op', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertEqual(pma_str, profiler_str)
model_analyzer.profile(
sess.graph, cmd='scope', run_meta=run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
pma_str = f.read()
self.assertNotEqual(pma_str, profiler_str)
def testSelectEverthingDetail(self):
ops.reset_default_graph()
dev = '/gpu:0' if test.is_gpu_available() else '/cpu:0'
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = (builder(
builder.trainable_variables_parameter()).with_file_output(
outfile).with_accounted_types(['.*']).select([
'micros', 'bytes', 'params', 'float_ops', 'occurrence',
'device', 'op_types', 'input_shapes'
]).build())
config = config_pb2.ConfigProto()
with session.Session(config=config) as sess, ops.device(dev):
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
run_meta = config_pb2.RunMetadata()
_ = sess.run(x,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=run_meta)
model_analyzer.profile(sess.graph, run_meta, options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
outputs = f.read().split('\n')
self.assertEqual(
outputs[0],
'node name | # parameters | # float_ops | requested bytes | total execution time | accelerator execution time | cpu execution time | assigned devices | op types | op count (run|defined) | input shapes'
)
for o in outputs[1:]:
if o.find('Conv2D ') > 0:
metrics = o[o.find('(') + 1:o.find(')')].split(',')
# Make sure time is profiled.
gap = 1 if test.is_gpu_available() else 2
for i in range(3, 6, gap):
mat = re.search('(.*)us/(.*)us', metrics[i])
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)
# Make sure device is profiled.
if test.is_gpu_available():
self.assertTrue(metrics[6].find('gpu') > 0)
self.assertFalse(metrics[6].find('cpu') > 0)
else:
self.assertFalse(metrics[6].find('gpu') > 0)
self.assertTrue(metrics[6].find('cpu') > 0)
# Make sure float_ops is profiled.
mat = re.search('(.*)k/(.*)k flops',
metrics[1].strip())
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)
# Make sure op_count is profiled.
self.assertEqual(metrics[8].strip(), '1/1|1/1')
# Make sure input_shapes is profiled.
self.assertEqual(metrics[9].strip(),
'0:2x6x6x3|1:3x3x3x6')
if o.find('DW (3x3x3x6') > 0:
metrics = o[o.find('(') + 1:o.find(')')].split(',')
mat = re.search('(.*)/(.*) params', metrics[1].strip())
self.assertGreater(float(mat.group(1)), 0.0)
self.assertGreater(float(mat.group(2)), 0.0)