def testAutoProfiling(self):
ops.reset_default_graph()
time_dir = os.path.join(test.get_temp_dir(), 'time')
memory_dir = os.path.join(test.get_temp_dir(), 'memory')
profile_dir = os.path.join(test.get_temp_dir(), 'dir/dir2/profile')
# TODO(xpan): Should we create parent directory for them?
gfile.MkDir(time_dir)
gfile.MkDir(memory_dir)
time_opts = (builder(builder.time_and_memory())
.with_file_output(os.path.join(time_dir, 'profile'))
.select(['micros']).build())
memory_opts = (builder(builder.time_and_memory())
.with_file_output(os.path.join(memory_dir, 'profile'))
.select(['bytes']).build())
time_steps = [2, 3]
memory_steps = [1, 3]
dump_steps = [3, 4]
x = lib.BuildSmallModel()
with profile_context.ProfileContext(profile_dir,
trace_steps=[1, 2, 3],
dump_steps=[3, 4]) as pctx:
pctx.add_auto_profiling('scope', time_opts, time_steps)
pctx.add_auto_profiling('scope', memory_opts, memory_steps)
self._trainLoop(x, 10, time_dir, time_steps,
memory_dir, memory_steps, profile_dir, dump_steps)
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(config=self._no_rewrite_session_config()) as sess:
x = lib.BuildSmallModel()
self.evaluate(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 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(config=self._no_rewrite_session_config()) as sess:
x = lib.BuildSmallModel()
self.evaluate(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 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)
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, --/11.34k flops, _kTFScopeParent, --/8|--/36, )\n Conv2D (0/0 params, 5.83k/5.83k flops, /job:localhost/replica:0/task:0/device:cpu:0, /job:localhost/replica:0/task:0/device: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/device:cpu:0, /job:localhost/replica:0/task:0/device:cpu:0|Conv2D, 1/1|1/1, 0:2x3x3x6|1:2x2x6x12)\n DW (3x3x3x6, 162/162 params, 0/324 flops, /job:localhost/replica:0/task:0/device:cpu:0, /job:localhost/replica:0/task:0/device: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, 0/324 flops, _kTFScopeParent, 0/0|1/7, )\n DW/Initializer/random_normal (0/0 params, 162/324 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, 162/162 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/device:cpu:0, /job:localhost/replica:0/task:0/device:cpu:0|Identity, 1/1|1/1, 0:3x3x3x6)\n DW2 (2x2x6x12, 288/288 params, 0/576 flops, /job:localhost/replica:0/task:0/device:cpu:0, /job:localhost/replica:0/task:0/device: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, 0/576 flops, _kTFScopeParent, 0/0|1/7, )\n DW2/Initializer/random_normal (0/0 params, 288/576 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, 288/288 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/device:cpu:0, /job:localhost/replica:0/task:0/device:cpu:0|Identity, 1/1|1/1, 0:2x2x6x12)\n ScalarW (1, 1/1 params, 0/2 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, 0/2 flops, _kTFScopeParent, 0/0|1/7, )\n ScalarW/Initializer/random_normal (0/0 params, 1/2 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, 1/1 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/device:cpu:0, /job:localhost/replica:0/task:0/device:cpu:0|_retval_Conv2D_1_0_0, 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/device:cpu:0, /job:localhost/replica:0/task:0/device:cpu:0|Const, 1/1|1/1, )\n',
f.read())
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 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 testMultipleProfilePerStep(self):
ops.reset_default_graph()
opts = (builder(builder.trainable_variables_parameter())
.with_empty_output()
.with_accounted_types(['.*'])
.select(['micros', 'bytes', 'peak_bytes',
'residual_bytes', 'output_bytes']).build())
r = lib.BuildSmallModel()
sess = session.Session()
profiler = model_analyzer.Profiler(sess.graph)
init_var_run_meta = config_pb2.RunMetadata()
sess.run(variables.global_variables_initializer(),
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=init_var_run_meta)
train_run_meta = config_pb2.RunMetadata()
sess.run(r,
options=config_pb2.RunOptions(
trace_level=config_pb2.RunOptions.FULL_TRACE),
run_metadata=train_run_meta)
profiler.add_step(0, train_run_meta)
ret1 = profiler.profile_name_scope(opts)
n1 = lib.SearchTFProfNode(
ret1, 'DW/Initializer/random_normal/RandomStandardNormal')
# Without the var initialization run_meta, it doesn't have the
# information of var_initialization.
self.assertEqual(n1.exec_micros, 0)
self.assertEqual(n1.requested_bytes, 0)
self.assertEqual(n1.peak_bytes, 0)
self.assertEqual(n1.residual_bytes, 0)
profiler.add_step(0, init_var_run_meta)
ret2 = profiler.profile_name_scope(opts)
n2 = lib.SearchTFProfNode(
ret2, 'DW/Initializer/random_normal/RandomStandardNormal')
# After adding the var initialization run_meta.
self.assertGreater(n2.exec_micros, 0)
self.assertGreater(n2.requested_bytes, 0)
self.assertGreater(n2.peak_bytes, 0)
self.assertGreater(n2.residual_bytes, 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())
with session.Session(config=self._no_rewrite_session_config()
) as sess, ops.device('/device:CPU:0'):
x = lib.BuildSmallModel()
self.evaluate(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 testEager(self):
ops.reset_default_graph()
with context.eager_mode():
outfile = os.path.join(test.get_temp_dir(), 'dump')
opts = builder(
builder.time_and_memory()).with_file_output(outfile).build()
context.enable_run_metadata()
lib.BuildSmallModel()
profiler = model_analyzer.Profiler()
profiler.add_step(0, context.export_run_metadata())
context.disable_run_metadata()
profiler.profile_operations(opts)
with gfile.Open(outfile, 'r') as f:
out_str = f.read()
self.assertTrue('Conv2D' in out_str)
self.assertTrue('VarHandleOp' in out_str)
with gfile.Open('/tmp/eager_profile', 'wb') as f:
profile_pb = tfprof_log_pb2.ProfileProto()
profile_pb.ParseFromString(profiler.serialize_to_string())
profile_pb_str = '%s' % profile_pb
self.assertTrue('Conv2D' in profile_pb_str)
self.assertTrue('VarHandleOp' in profile_pb_str)
def testSelectEverythingDetail(self):
ops.reset_default_graph()
dev = '/device:GPU:0' if test.is_gpu_available() else '/device: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())
with profile_context.ProfileContext(test.get_temp_dir(),
trace_steps=[],
dump_steps=[]) as pctx:
with session.Session() as sess, ops.device(dev):
x = lib.BuildSmallModel()
sess.run(variables.global_variables_initializer())
pctx.trace_next_step()
pctx.dump_next_step()
_ = sess.run(x)
pctx.profiler.profile_name_scope(options=opts)
with gfile.Open(outfile, 'r') as f:
# pylint: disable=line-too-long
dump_str = lib.CheckAndRemoveDoc(f.read())
outputs = dump_str.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)
# pylint: enable=line-too-long
# Test that profiler restored from profile file gives the same result.
gfile.Remove(outfile)
profile_file = os.path.join(test.get_temp_dir(), 'profile_1')
with lib.ProfilerFromFile(profile_file) as profiler:
profiler.profile_name_scope(options=opts)
with gfile.Open(outfile, 'r') as f:
self.assertEqual(dump_str, lib.CheckAndRemoveDoc(f.read()))
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 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)
