4
from caffe2.python import core, workspace, test_util
7
class TestToyRegression(test_util.TestCase):
8
def testToyRegression(self):
9
"""Tests a toy regression end to end.
11
The test code carries a simple toy regression in the form
12
y = 2.0 x1 + 1.5 x2 + 0.5
13
by randomly generating gaussian inputs and calculating the ground
14
truth outputs in the net as well. It uses a standard SGD to then
17
workspace.ResetWorkspace()
18
init_net = core.Net("init")
19
W = init_net.UniformFill([], "W", shape=[1, 2], min=-1., max=1.)
20
B = init_net.ConstantFill([], "B", shape=[1], value=0.0)
21
W_gt = init_net.GivenTensorFill(
22
[], "W_gt", shape=[1, 2], values=[2.0, 1.5])
23
B_gt = init_net.GivenTensorFill([], "B_gt", shape=[1], values=[0.5])
24
LR = init_net.ConstantFill([], "LR", shape=[1], value=-0.1)
25
ONE = init_net.ConstantFill([], "ONE", shape=[1], value=1.)
26
ITER = init_net.ConstantFill([], "ITER", shape=[1], value=0,
27
dtype=core.DataType.INT64)
29
train_net = core.Net("train")
30
X = train_net.GaussianFill([], "X", shape=[64, 2], mean=0.0, std=1.0)
31
Y_gt = X.FC([W_gt, B_gt], "Y_gt")
32
Y_pred = X.FC([W, B], "Y_pred")
33
dist = train_net.SquaredL2Distance([Y_gt, Y_pred], "dist")
34
loss = dist.AveragedLoss([], ["loss"])
35
# Get gradients for all the computations above. Note that in fact we
36
# don't need to get the gradient the Y_gt computation, but we'll just
37
# leave it there. In many cases, I am expecting one to load X and Y
38
# from the disk, so there is really no operator that will calculate the
40
input_to_grad = train_net.AddGradientOperators([loss], skip=2)
42
train_net.Iter(ITER, ITER)
43
train_net.LearningRate(ITER, "LR", base_lr=-0.1,
44
policy="step", stepsize=20, gamma=0.9)
45
train_net.WeightedSum([W, ONE, input_to_grad[str(W)], LR], W)
46
train_net.WeightedSum([B, ONE, input_to_grad[str(B)], LR], B)
47
for blob in [loss, W, B]:
48
train_net.Print(blob, [])
51
plan = core.Plan("toy_regression")
52
plan.AddStep(core.ExecutionStep("init", init_net))
53
plan.AddStep(core.ExecutionStep("train", train_net, 200))
55
workspace.RunPlan(plan)
56
W_result = workspace.FetchBlob("W")
57
B_result = workspace.FetchBlob("B")
58
np.testing.assert_array_almost_equal(W_result, [[2.0, 1.5]], decimal=2)
59
np.testing.assert_array_almost_equal(B_result, [0.5], decimal=2)
60
workspace.ResetWorkspace()
63
if __name__ == '__main__':