def test_profile_graph(self):
calls = [0]
def f0(t):
calls[0] += 1
time.sleep(t)
def f1(t):
calls[0] += 1
time.sleep(t)
def f2():
calls[0] += 1
f1(0.1)
f1(0.01)
def f3():
calls[0] += 1
f0(0.2)
f1(0.5)
def f4():
calls[0] += 1
f2()
f3()
ps = profile(f4)[0] # pylint: disable=W0632
profile2df(ps, verbose=False, clean_text=lambda x: x.split('/')[-1])
root, nodes = profile2graph(ps, clean_text=lambda x: x.split('/')[-1])
self.assertEqual(len(nodes), 6)
self.assertIsInstance(nodes, dict)
self.assertIsInstance(root, ProfileNode)
self.assertIn("(", str(root))
dicts = root.as_dict()
self.assertEqual(10, len(dicts))
text = root.to_text()
self.assertIn("1 1", text)
self.assertIn(' f1', text)
text = root.to_text(fct_width=20)
self.assertIn('...', text)
root.to_text(sort_key=SortKey.CUMULATIVE)
root.to_text(sort_key=SortKey.TIME)
self.assertRaise(lambda: root.to_text(sort_key=SortKey.NAME),
NotImplementedError)
js = root.to_json(indent=2)
self.assertIn('"details"', js)
js = root.to_json(as_str=False)
self.assertIsInstance(js, dict)
def test_profile_graph_recursive1(self):
def f0(t):
if t < 0.1:
time.sleep(t)
else:
f0(t - 0.1)
def f4():
f0(0.15)
ps = profile(f4)[0] # pylint: disable=W0632
profile2df(ps, verbose=False, clean_text=lambda x: x.split('/')[-1])
root, nodes = profile2graph(ps, clean_text=lambda x: x.split('/')[-1])
self.assertEqual(len(nodes), 3)
text = root.to_text()
self.assertIn(" f0", text)
js = root.to_json(indent=2)
self.assertIn('"details"', js)
return text[pos:]
pos = text.find('sklearn')
if pos >= 0:
return text[pos:]
pos = text.find('onnxcustom')
if pos >= 0:
return text[pos:]
pos = text.find('site-packages')
if pos >= 0:
return text[pos:]
return text
ps = profile(lambda: benchmark(X_train, y_train,
nn, train_session, name='NN-CPU'))[0]
root, nodes = profile2graph(ps, clean_text=clean_name)
text = root.to_text()
print(text)
######################################
# if GPU is available
# +++++++++++++++++++
if get_device().upper() == 'GPU':
train_session = OrtGradientForwardBackwardOptimizer(
onx, device='cuda', learning_rate=1e-5,
warm_start=False, max_iter=max_iter, batch_size=batch_size)
benches.append(benchmark(X_train, y_train, nn,
train_session, name='NN-GPU'))
#########################################
# Graph
# +++++
fig, ax = plt.subplots(1, 1)
piv.plot(title="Time processing of serialization functions\n"
"lower better",
ax=ax)
ax.set_xlabel("onnx size")
ax.set_ylabel("s")
###########################################
# Conclusion
# ++++++++++
#
# This graph shows that implementing check_model in python is much slower
# than the C++ version. However, protobuf prevents from sharing
# ModelProto from Python to C++ (see `Python Updates
# <https://developers.google.com/protocol-buffers/docs/news/2022-05-06>`_)
# unless the python package is compiled with a specific setting
# (problably slower). A profiling shows that the code spends quite some time
# in function :func:`getattr`.
ps = profile(lambda: check_model_py(onx))[0]
root, nodes = profile2graph(ps, clean_text=lambda x: x.split('/')[-1])
text = root.to_text()
print(text)
# plt.show()