def test_fast_memonger(self, input_dim, output_dim, batch_size, do):
m = model_helper.ModelHelper()
fc1 = brew.fc(m, "data", "fc1", dim_in=input_dim, dim_out=output_dim)
fc2 = brew.fc(m, fc1, "fc2", dim_in=output_dim, dim_out=output_dim)
fc3 = brew.fc(m, fc2, "fc3", dim_in=output_dim, dim_out=output_dim)
fc3.Relu([], fc3)\
.Softmax([], "pred") \
.LabelCrossEntropy(["label"], ["xent"]) \
.AveragedLoss([], "loss")
input_to_grad = m.AddGradientOperators(["loss"])
m.net.Proto().device_option.CopyFrom(do)
m.param_init_net.Proto().device_option.CopyFrom(do)
static_blobs = \
[o for op in m.param_init_net.Proto().op for o in op.output] + \
["data", "label", "loss", input_to_grad["fc1_w"]]
optimized_net = memonger.optimize_inference_fast(
m.Proto(), static_blobs)
data = np.random.randn(batch_size, input_dim).astype(np.float32)
label = np.random.randint(low=0, high=output_dim,
size=(batch_size, )).astype(np.int32)
workspace.RunNetOnce(m.param_init_net)
workspace.FeedBlob("data", data, device_option=do)
workspace.FeedBlob("label", label, device_option=do)
workspace.RunNetOnce(m.net)
loss = workspace.FetchBlob("loss")
grad = workspace.FetchBlob(str(input_to_grad["fc1_w"]))
workspace.RunNetOnce(optimized_net)
optimized_loss = workspace.FetchBlob("loss")
optimized_grad = workspace.FetchBlob(str(input_to_grad["fc1_w"]))
np.testing.assert_almost_equal(loss, optimized_loss)
np.testing.assert_almost_equal(grad, optimized_grad)
self.assertLess(count_blobs(optimized_net), count_blobs(m.Proto()))
def test_fast_memonger_unique_outputs(self):
m = model_helper.ModelHelper()
fc = []
for i in range(2):
z = brew.fc(m,
"data{}".format(i),
"fc".format(i),
dim_in=2,
dim_out=2)
fc.append(z)
r = []
# Trick is here to have same input appear twice in a same Sum
for x in fc:
for y in fc:
r.append(brew.sum(m, [x, y], 1))
concated = brew.concat(m, r, "concated")
brew.relu(m, concated, "merged")
static_blobs = \
[o for op in m.param_init_net.Proto().op for o in op.output] + \
["merged"] + ["data{}".format(i) for i in range(len(fc))]
optimized_net = memonger.optimize_inference_fast(
m.Proto(), static_blobs)
for op in optimized_net.op:
self.assertEqual(len(op.output), len(set(op.output)), str(op))
def test_fast_memonger(self, input_dim, output_dim, batch_size, do):
m = model_helper.ModelHelper()
fc1 = brew.fc(m, "data", "fc1", dim_in=input_dim, dim_out=output_dim)
fc2 = brew.fc(m, fc1, "fc2", dim_in=output_dim, dim_out=output_dim)
fc3 = brew.fc(m, fc2, "fc3", dim_in=output_dim, dim_out=output_dim)
fc3.Relu([], fc3)\
.Softmax([], "pred") \
.LabelCrossEntropy(["label"], ["xent"]) \
.AveragedLoss([], "loss")
input_to_grad = m.AddGradientOperators(["loss"])
m.net.Proto().device_option.CopyFrom(do)
m.param_init_net.Proto().device_option.CopyFrom(do)
static_blobs = \
[o for op in m.param_init_net.Proto().op for o in op.output] + \
["data", "label", "loss", input_to_grad["fc1_w"]]
optimized_net = memonger.optimize_inference_fast(
m.Proto(), static_blobs)
data = np.random.randn(batch_size, input_dim).astype(np.float32)
label = np.random.randint(
low=0, high=output_dim, size=(batch_size,)).astype(np.int32)
workspace.RunNetOnce(m.param_init_net)
workspace.FeedBlob("data", data, device_option=do)
workspace.FeedBlob("label", label, device_option=do)
workspace.RunNetOnce(m.net)
loss = workspace.FetchBlob("loss")
grad = workspace.FetchBlob(str(input_to_grad["fc1_w"]))
workspace.RunNetOnce(optimized_net)
optimized_loss = workspace.FetchBlob("loss")
optimized_grad = workspace.FetchBlob(str(input_to_grad["fc1_w"]))
np.testing.assert_almost_equal(loss, optimized_loss)
np.testing.assert_almost_equal(grad, optimized_grad)
self.assertLess(count_blobs(optimized_net), count_blobs(m.Proto()))
def test_resnet_forward_only_fast_simplenet(self):
'''
Test C++ memonger that is only for simple nets
'''
model = cnn.CNNModelHelper(
order="NCHW",
name="test",
cudnn_exhaustive_search=True,
)
with core.NameScope("gpu_0"):
data = model.net.AddExternalInput("gpu_0/data")
resnet.create_resnet50(
model,
data,
num_input_channels=3,
num_labels=1000,
is_test=True
)
count_before = count_blobs(model.net.Proto())
t = time.time()
optim_proto = memonger.optimize_inference_fast(
model.net.Proto(),
set(["gpu_0/data", "gpu_0/last_out_L1000"]).union(
set(model.net.Proto().external_input))
)
print("Optimization took {} secs".format(time.time() - t))
count_after = count_blobs(optim_proto)
num_shared_blobs = count_shared_blobs(optim_proto)
self.assertTrue(count_after < count_before)
print(count_after, count_before, num_shared_blobs)
self.assertTrue(num_shared_blobs < 7 and num_shared_blobs > 0)
# Run model and compare results
workspace.RunNetOnce(model.param_init_net)
data = np.random.rand(4, 3, 227, 227).astype(np.float32)
workspace.FeedBlob("gpu_0/data", data)
model.net.Proto().type = 'simple'
workspace.RunNetOnce(model.net)
loss1 = workspace.FetchBlob("gpu_0/last_out_L1000")
workspace.RunNetOnce(optim_proto)
optimized_loss1 = workspace.FetchBlob("gpu_0/last_out_L1000")
np.testing.assert_almost_equal(loss1, optimized_loss1)
def test_forward_only_fast_simplenet(
create_model,
last_out_blob,
data_blob="gpu_0/data",
num_labels=1000,
):
model = cnn.CNNModelHelper(
order="NCHW",
name="test",
cudnn_exhaustive_search=True,
)
with core.NameScope("gpu_0"):
data = model.net.AddExternalInput(data_blob)
create_model(model,
data,
num_input_channels=3,
num_labels=num_labels,
is_test=True)
count_before = count_blobs(model.net.Proto())
t = time.time()
optim_proto = memonger.optimize_inference_fast(
model.net.Proto(),
set([data_blob,
last_out_blob]).union(set(model.net.Proto().external_input)))
print("Optimization took {} secs".format(time.time() - t))
count_after = count_blobs(optim_proto)
num_shared_blobs = count_shared_blobs(optim_proto)
print(count_after, count_before, num_shared_blobs)
# Run model and compare results
workspace.RunNetOnce(model.param_init_net)
data = np.random.rand(4, 3, 227, 227).astype(np.float32)
workspace.FeedBlob(data_blob, data)
model.net.Proto().type = 'simple'
workspace.RunNetOnce(model.net)
loss1 = workspace.FetchBlob(last_out_blob)
workspace.RunNetOnce(optim_proto)
optimized_loss1 = workspace.FetchBlob(last_out_blob)
return [(count_after, count_before), (num_shared_blobs),
(loss1, optimized_loss1)]
def test_fast_memonger_unique_outputs(self):
m = model_helper.ModelHelper()
fc = []
for i in range(2):
z = brew.fc(
m, "data{}".format(i), "fc".format(i), dim_in=2, dim_out=2)
fc.append(z)
r = []
# Trick is here to have same input appear twice in a same Sum
for x in fc:
for y in fc:
r.append(brew.sum(m, [x, y], 1))
concated = brew.concat(m, r, "concated")
brew.relu(m, concated, "merged")
static_blobs = \
[o for op in m.param_init_net.Proto().op for o in op.output] + \
["merged"] + ["data{}".format(i) for i in range(len(fc))]
optimized_net = memonger.optimize_inference_fast(
m.Proto(), static_blobs)
for op in optimized_net.op:
self.assertEqual(len(op.output), len(set(op.output)), str(op))
