def testToyRegression(self):
"""Tests a toy regression end to end.
The test code carries a simple toy regression in the form
y = 2.0 x1 + 1.5 x2 + 0.5
by randomly generating gaussian inputs and calculating the ground
truth outputs in the net as well. It uses a standard SGD to then
train the parameters.
"""
workspace.ResetWorkspace()
init_net = core.Net("init")
W = init_net.UniformFill([], "W", shape=[1, 2], min=-1., max=1.)
B = init_net.ConstantFill([], "B", shape=[1], value=0.0)
W_gt = init_net.GivenTensorFill([],
"W_gt",
shape=[1, 2],
values=[2.0, 1.5])
B_gt = init_net.GivenTensorFill([], "B_gt", shape=[1], values=[0.5])
LR = init_net.ConstantFill([], "LR", shape=[1], value=-0.1)
ONE = init_net.ConstantFill([], "ONE", shape=[1], value=1.)
ITER = init_net.ConstantIntFill([], "ITER", shape=[1], value=0.)
train_net = core.Net("train")
X = train_net.GaussianFill([], "X", shape=[64, 2], mean=0.0, std=1.0)
Y_gt = X.FC([W_gt, B_gt], "Y_gt")
Y_pred = X.FC([W, B], "Y_pred")
dist = train_net.SquaredL2Distance([Y_gt, Y_pred], "dist")
loss = dist.AveragedLoss([], ["loss"])
# Get gradients for all the computations above. Note that in fact we
# don't need to get the gradient the Y_gt computation, but we'll just
# leave it there. In many cases, I am expecting one to load X and Y
# from the disk, so there is really no operator that will calculate the
# Y_gt input.
input_to_grad = train_net.AddGradientOperators([loss], skip=2)
# updates
train_net.Iter(ITER, ITER)
train_net.LearningRate(ITER,
"LR",
base_lr=-0.1,
policy="step",
stepsize=20,
gamma=0.9)
train_net.WeightedSum([W, ONE, input_to_grad[str(W)], LR], W)
train_net.WeightedSum([B, ONE, input_to_grad[str(B)], LR], B)
for blob in [loss, W, B]:
train_net.Print(blob, [])
# the CPU part.
plan = core.Plan("toy_regression")
plan.AddStep(core.ExecutionStep("init", init_net))
plan.AddStep(core.ExecutionStep("train", train_net, 200))
workspace.RunPlan(plan)
W_result = workspace.FetchBlob("W")
B_result = workspace.FetchBlob("B")
np.testing.assert_array_almost_equal(W_result, [[2.0, 1.5]], decimal=2)
np.testing.assert_array_almost_equal(B_result, [0.5], decimal=2)
workspace.ResetWorkspace()
def testRunPlan(self):
plan = core.Plan("test-plan")
plan.AddNets([self.net])
plan.AddStep(core.ExecutionStep("test-step", self.net))
self.assertEqual(workspace.RunPlan(plan.Proto().SerializeToString()),
True)
self.assertEqual(workspace.HasBlob("testblob"), True)
def testRunPlanInBackground(self):
plan = core.Plan("test-plan")
plan.AddStep(core.ExecutionStep("test-step", self.net))
background_plan = workspace.RunPlanInBackground(plan)
while not background_plan.is_done():
pass
self.assertEqual(background_plan.is_succeeded(), True)
self.assertEqual(workspace.HasBlob("testblob"), True)
def benchmark(ws, net, warmups=5, iters=100):
for _ in range(warmups):
ws.run(net)
plan = core.Plan("plan")
plan.AddStep(core.ExecutionStep("test-step", net, iters))
before = time.time()
ws.run(plan)
after = time.time()
print("Timing network, time taken per-iteration: {:.6f}ms".format((
after - before) / float(iters) * 1000.0))
return after - before
def benchmark(net, warmups=5, iters=100):
for _ in range(warmups):
workspace.RunNetOnce(net.Proto().SerializeToString())
plan = core.Plan("plan")
plan.AddStep(core.ExecutionStep("test-step", net, iters))
before = time.time()
workspace.RunPlan(plan.Proto().SerializeToString())
after = time.time()
print("Timing network, time taken per-iteration: {:.6f}ms".format(
(after - before) / float(iters) * 1000.0))
return after - before
def test_plan_run(self, blob_name, plan_name, net_name, value):
ws = workspace.C.Workspace()
plan = core.Plan(plan_name)
net = core.Net(net_name)
net.ConstantFill([], [blob_name], shape=[1], value=value)
plan.AddStep(core.ExecutionStep("step", nets=[net], num_iter=1))
ws.run(plan)
self.assertIn(blob_name, ws.blobs)
self.assertIn(net.Name(), ws.nets)
np.testing.assert_allclose(
[value], ws.blobs[blob_name].fetch(), atol=1e-4, rtol=1e-4)
def test_multithreaded_evaluation(self, x, n, w):
def f(inputs, outputs):
outputs[0].reshape(inputs[0].shape)
outputs[0].data[...] = inputs[0].data
ops = [CreatePythonOperator(f, ["x"], [str(i)]) for i in range(n)]
net = core.Net("net")
net.Proto().op.extend(ops)
net.Proto().type = "dag"
net.Proto().num_workers = w
iters = 100
plan = core.Plan("plan")
plan.AddStep(core.ExecutionStep("test-step", net, iters))
workspace.FeedBlob("x", x)
workspace.RunPlan(plan.Proto().SerializeToString())
for i in range(n):
y = workspace.FetchBlob(str(i))
np.testing.assert_almost_equal(x, y)
stride=1, order="NHWC").MaxPool([],
kernel=2,
stride=2,
order="NHWC"))
softmax = pool2.Flatten().FC([W3, B3]).Relu().FC([W4, B4]).Softmax()
# Cross entropy, and accuracy
xent = softmax.LabelCrossEntropy([label], "xent")
# The loss function.
loss = xent.AveragedLoss([], ["loss"])
# Get gradient
train_net.AddGradientOperators()
accuracy = softmax.Accuracy([label], "accuracy")
# parameter update.
for param in params:
train_net.WeightedSum([param, ONE, param.Grad(), LR], param)
LR = train_net.Mul([LR, DECAY], "LR")
train_net.Print([accuracy], [])
# Run all on GPU.
#init_net.RunAllOnGPU()
#train_net.RunAllOnGPU()
plan = core.Plan("mnist_lenet_gc")
plan.AddNets([init_net, train_net])
plan.AddStep(core.ExecutionStep("init", init_net))
plan.AddStep(core.ExecutionStep("train", train_net, 1000))
with open('mnist_lenet_group_convolution_nhwc.pbtxt', 'w') as fid:
fid.write(str(plan.Proto()))
def testConstructPlanFromSteps(self):
step = core.ExecutionStep("test-step-as-plan", self.net)
self.assertEqual(workspace.RunPlan(step), True)
self.assertEqual(workspace.HasBlob("testblob"), True)
def Benchmark(model_gen, arg):
model, input_size = model_gen(arg.order)
model.Proto().type = arg.net_type
model.Proto().num_workers = arg.num_workers
# In order to be able to run everything without feeding more stuff, let's
# add the data and label blobs to the parameter initialization net as well.
if arg.order == "NCHW":
input_shape = [arg.batch_size, 3, input_size, input_size]
else:
input_shape = [arg.batch_size, input_size, input_size, 3]
if arg.model == "MLP":
input_shape = [arg.batch_size, input_size]
model.param_init_net.GaussianFill([],
"data",
shape=input_shape,
mean=0.0,
std=1.0)
model.param_init_net.UniformIntFill([],
"label",
shape=[
arg.batch_size,
],
min=0,
max=999)
if arg.forward_only:
print('{}: running forward only.'.format(arg.model))
else:
print('{}: running forward-backward.'.format(arg.model))
model.AddGradientOperators(["loss"])
AddParameterUpdate(model)
if arg.order == 'NHWC':
print(
'==WARNING==\n'
'NHWC order with CuDNN may not be supported yet, so I might\n'
'exit suddenly.')
if not arg.cpu:
model.param_init_net.RunAllOnGPU()
model.net.RunAllOnGPU()
if arg.dump_model:
# Writes out the pbtxt for benchmarks on e.g. Android
with open("{0}_init_batch_{1}.pbtxt".format(arg.model, arg.batch_size),
"w") as fid:
fid.write(str(model.param_init_net.Proto()))
with open("{0}.pbtxt".format(arg.model, arg.batch_size),
"w") as fid:
fid.write(str(model.net.Proto()))
workspace.RunNetOnce(model.param_init_net)
workspace.CreateNet(model.net)
for i in range(arg.warmup_iterations):
workspace.RunNet(model.net.Proto().name)
plan = core.Plan("plan")
plan.AddStep(core.ExecutionStep("run", model.net, arg.iterations))
start = time.time()
workspace.RunPlan(plan)
print('Spent: {}'.format((time.time() - start) / arg.iterations))
if arg.layer_wise_benchmark:
print('Layer-wise benchmark.')
workspace.BenchmarkNet(model.net.Proto().name, 1, arg.iterations, True)
W8 = init_net.ConstantFill([], "W8", shape=[1000, 4096])
B8 = init_net.ConstantFill([], "B8", shape=[1000], value=0.0)
pred = (pool5_flatten.FC([W6, B6]).Relu().Dropout(outputs=2)[0].FC(
[W7, B7]).Relu().Dropout(outputs=2)[0].FC([W8, B8]).Softmax())
xent = pred.LabelCrossEntropy([label], "xent")
# The loss function.
loss = xent.AveragedLoss([], ["loss"])
test_net.AddGradientOperators(first=2)
test_net.Print([loss], [])
dump_net = core.Net("dump")
for blob in [
data, pool1, pool1a, pool1b, pool2, conv3a, conv3b, conv4a, conv4b,
conv5a, conv5b, pool5_flatten
]:
dump_net.SaveFloatTensor([blob], [], file=str(blob))
init_net.RunAllOnGPU()
test_net.RunAllOnGPU()
dump_net.RunAllOnGPU()
plan = core.Plan("alexnet")
plan.AddNets([init_net, test_net, dump_net])
plan.AddStep(core.ExecutionStep("init", init_net))
plan.AddStep(core.ExecutionStep("first_run", test_net))
#plan.AddStep(core.ExecutionStep("subsequent_run", test_net, 10))
plan.AddStep(core.ExecutionStep("dump", dump_net))
with open('alexnet.pbtxt', 'w') as fid:
fid.write(str(plan.Proto()))