def testAdvisor(self):
ops.reset_default_graph()
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)
advice_pb = model_analyzer.advise(sess.graph, run_meta)
self.assertTrue(
'AcceleratorUtilizationChecker' in advice_pb.checkers)
self.assertTrue('ExpensiveOperationChecker' in advice_pb.checkers)
self.assertTrue('OperationChecker' in advice_pb.checkers)
checker = advice_pb.checkers['AcceleratorUtilizationChecker']
if test.is_gpu_available():
self.assertGreater(len(checker.reports), 0)
else:
self.assertEqual(len(checker.reports), 0)
checker = advice_pb.checkers['ExpensiveOperationChecker']
self.assertGreater(len(checker.reports), 0)
def testBasics(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), "dump")
opts = builder(
builder.time_and_memory()).with_file_output(outfile).build()
x = lib.BuildFullModel()
profile_str = None
profile_step50 = os.path.join(test.get_temp_dir(), "profile_50")
with profile_context.ProfileContext(test.get_temp_dir()) as pctx:
pctx.add_auto_profiling("op",
options=opts,
profile_steps=[15, 50, 100])
with session.Session() as sess:
sess.run(variables.global_variables_initializer())
total_steps = 101 if test.is_gpu_available() else 50
for i in range(total_steps):
sess.run(x)
if i == 14 or i == 99:
self.assertTrue(gfile.Exists(outfile))
gfile.Remove(outfile)
if i == 49:
self.assertTrue(gfile.Exists(profile_step50))
with gfile.Open(outfile, "r") as f:
profile_str = f.read()
gfile.Remove(outfile)
with lib.ProfilerFromFile(
os.path.join(test.get_temp_dir(), "profile_50")) as profiler:
profiler.profile_operations(options=opts)
with gfile.Open(outfile, "r") as f:
self.assertEqual(profile_str, 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 + '_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 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 profile_context.ProfileContext(test.get_temp_dir(),
trace_steps=[],
dump_steps=[]) as pctx:
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
pctx.trace_next_step()
_ = sess.run(x)
tfprof_node = pctx.profiler.profile_python(options=opts)
# pylint: disable=line-too-long
with gfile.Open(outfile, 'r') as f:
lines = f.read().split('\n')
self.assertGreater(len(lines), 5)
result = '\n'.join([l[:min(len(l), 80)] for l in lines])
self.assertTrue(
compat.as_text(lib.CheckAndRemoveDoc(result))
.startswith('node name | # parameters | # float_ops'))
self.assertLess(0, tfprof_node.total_exec_micros)
self.assertEqual(2844, tfprof_node.total_parameters)
self.assertLess(168800, tfprof_node.total_float_ops)
self.assertEqual(8, len(tfprof_node.children))
self.assertEqual('_TFProfRoot', tfprof_node.name)
self.assertEqual(
'model_analyzer_testlib.py:63:BuildFullModel',
tfprof_node.children[0].name)
self.assertEqual(
'model_analyzer_testlib.py:63:BuildFullModel (gradient)',
tfprof_node.children[1].name)
self.assertEqual(
'model_analyzer_testlib.py:67:BuildFullModel',
tfprof_node.children[2].name)
self.assertEqual(
'model_analyzer_testlib.py:67:BuildFullModel (gradient)',
tfprof_node.children[3].name)
self.assertEqual(
'model_analyzer_testlib.py:69:BuildFullModel',
tfprof_node.children[4].name)
self.assertEqual(
'model_analyzer_testlib.py:70:BuildFullModel',
tfprof_node.children[5].name)
self.assertEqual(
'model_analyzer_testlib.py:70:BuildFullModel (gradient)',
tfprof_node.children[6].name)
self.assertEqual(
'model_analyzer_testlib.py:72:BuildFullModel',
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 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 profile_context.ProfileContext(test.get_temp_dir(),
trace_steps=[],
dump_steps=[]) as pctx:
with session.Session() as sess:
x = lib.BuildFullModel()
sess.run(variables.global_variables_initializer())
pctx.trace_next_step()
_ = sess.run(x)
tfprof_node = pctx.profiler.profile_python(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(compat.as_bytes('node name | # parameters | # float_ops\n_TFProfRoot (--/2.84k params, --/168.85k flops)\n model_analyzer_testlib.py:63:BuildFullModel (0/1.80k params, 0/45.37k flops)\n model_analyzer_testlib.py:40:BuildSmallModel (0/0 params, 0/0 flops)\n model_analyzer_testlib.py:44:BuildSmallModel (0/4 params, 0/8 flops)\n model_analyzer_testlib.py:48:BuildSmallModel (0/648 params, 0/1.30k flops)\n model_analyzer_testlib.py:49:BuildSmallModel (0/0 params, 0/23.33k flops)\n model_analyzer_testlib.py:53:BuildSmallModel (0/1.15k params, 0/2.30k flops)\n model_analyzer_testlib.py:54:BuildSmallModel (0/0 params, 0/18.43k flops)\n model_analyzer_testlib.py:63:BuildFullModel (gradient) (0/0 params, 0/67.39k f\n model_analyzer_testlib.py:49:BuildSmallModel (gradient) (0/0 params, 0/46.66\n model_analyzer_testlib.py:54:BuildSmallModel (gradient) (0/0 params, 0/20.74\n model_analyzer_testlib.py:67:BuildFullModel (0/1.04k params, 0/18.57k flops)\n model_analyzer_testlib.py:67:BuildFullModel (gradient) (0/0 params, 0/37.00k f\n model_analyzer_testlib.py:69:BuildFullModel (0/0 params, 0/0 flops)\n model_analyzer_testlib.py:70:BuildFullModel (0/0 params, 0/258 flops)\n model_analyzer_testlib.py:70:BuildFullModel (gradient) (0/0 params, 0/129 flop\n model_analyzer_testlib.py:72:BuildFullModel (0/0 params, 0/141 flops)\n'),
compat.as_bytes(result))
self.assertLess(0, tfprof_node.total_exec_micros)
self.assertEqual(2844, tfprof_node.total_parameters)
self.assertEqual(168854, tfprof_node.total_float_ops)
self.assertEqual(8, len(tfprof_node.children))
self.assertEqual('_TFProfRoot', tfprof_node.name)
self.assertEqual(
'model_analyzer_testlib.py:63:BuildFullModel',
tfprof_node.children[0].name)
self.assertEqual(
'model_analyzer_testlib.py:63:BuildFullModel (gradient)',
tfprof_node.children[1].name)
self.assertEqual(
'model_analyzer_testlib.py:67:BuildFullModel',
tfprof_node.children[2].name)
self.assertEqual(
'model_analyzer_testlib.py:67:BuildFullModel (gradient)',
tfprof_node.children[3].name)
self.assertEqual(
'model_analyzer_testlib.py:69:BuildFullModel',
tfprof_node.children[4].name)
self.assertEqual(
'model_analyzer_testlib.py:70:BuildFullModel',
tfprof_node.children[5].name)
self.assertEqual(
'model_analyzer_testlib.py:70:BuildFullModel (gradient)',
tfprof_node.children[6].name)
self.assertEqual(
'model_analyzer_testlib.py:72: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 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 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 _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 testBasics(self):
ops.reset_default_graph()
outfile = os.path.join(test.get_temp_dir(), "dump")
opts = builder(
builder.time_and_memory()).with_file_output(outfile).build()
x = lib.BuildFullModel()
profile_str = None
profile_step100 = os.path.join(test.get_temp_dir(), "profile_100")
with profile_context.ProfileContext(test.get_temp_dir()) as pctx:
pctx.add_auto_profiling("op",
options=opts,
profile_steps=[15, 50, 100])
with session.Session() as sess:
sess.run(variables.global_variables_initializer())
total_steps = 101
for i in range(total_steps):
sess.run(x)
if i == 14 or i == 49:
self.assertTrue(gfile.Exists(outfile))
gfile.Remove(outfile)
if i == 99:
self.assertTrue(gfile.Exists(profile_step100))
with gfile.Open(outfile, "r") as f:
profile_str = f.read()
gfile.Remove(outfile)
self.assertEqual(set([15, 50, 100]),
set(pctx.get_profiles("op").keys()))
with lib.ProfilerFromFile(
os.path.join(test.get_temp_dir(), "profile_100")) as profiler:
profiler.profile_operations(options=opts)
with gfile.Open(outfile, "r") as f:
if test.is_built_with_rocm():
# The profiler output for ROCm mode, includes an extra warning related
# to the lack of stream tracing in ROCm moed. Need to skip this warning
# when doing the diff in ROCm mode
profile_str = "\n".join(profile_str.split("\n")[7:])
self.assertEqual(profile_str, f.read())
def testAutoTracingInDeubMode(self):
ops.reset_default_graph()
x = lib.BuildFullModel()
with profile_context.ProfileContext(test.get_temp_dir(), debug=True):
with session.Session() as sess:
self.evaluate(variables.global_variables_initializer())
for _ in range(10):
self.evaluate(x)
for f in gfile.ListDirectory(test.get_temp_dir()):
# Warm up, no tracing.
self.assertFalse("run_meta" in f)
self.evaluate(x)
self.assertTrue(
gfile.Exists(os.path.join(test.get_temp_dir(), "run_meta_11")))
gfile.Remove(os.path.join(test.get_temp_dir(), "run_meta_11"))
# fetched already.
self.evaluate(x)
for f in gfile.ListDirectory(test.get_temp_dir()):
self.assertFalse("run_meta" in f)
def testDisabled(self):
ops.reset_default_graph()
x = lib.BuildFullModel()
with profile_context.ProfileContext(test.get_temp_dir(),
enabled=False) as pctx:
with session.Session() as sess:
self.evaluate(variables.global_variables_initializer())
for _ in range(10):
self.evaluate(x)
self.assertTrue(pctx.profiler is None)
self.assertTrue(
getattr(session.BaseSession, "profile_context", None) is None)
with profile_context.ProfileContext(test.get_temp_dir()) as pctx:
with session.Session() as sess:
self.evaluate(variables.global_variables_initializer())
for _ in range(10):
self.evaluate(x)
self.assertFalse(pctx.profiler is None)
self.assertFalse(
getattr(session.BaseSession, "profile_context", None) is None)
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 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)