def test_eval_plus_two_inputs():
result = cntk.eval(
cntk.plus(cntk.input_numpy([[1., 2., 3., 4.]]),
cntk.input_numpy([[1., 1., 0., 0.]])))
TOLERANCE_ABSOLUTE = 1E-06
assert np.allclose(result,
np.asarray([2., 3., 3., 4.]),
atol=TOLERANCE_ABSOLUTE)
def train_eval_logistic_regression_with_numpy(criterion_name=None,
eval_name=None,
device_id=-1):
# for repro and tests :-)
np.random.seed(1)
train_X, train_y = synthetic_data(train_N, feature_dim, num_classes)
test_X, test_y = synthetic_data(test_N, feature_dim, num_classes)
# Set up the training data for CNTK. Before writing the CNTK configuration,
# the data will be attached to X.reader.batch and y.reader.batch and then
# serialized.
X = C.input_numpy(train_X)
y = C.input_numpy(train_y)
# define our network -- one weight tensor and a bias
W = C.parameter(value=np.zeros(shape=(num_classes, feature_dim)))
b = C.parameter(value=np.zeros(shape=(num_classes, 1)))
out = C.times(W, X) + b
ce = C.cross_entropy_with_softmax(y, out)
ce.tag = 'criterion'
ce.name = criterion_name
eval = C.ops.cntk1.SquareError(y, out)
eval.tag = 'eval'
eval.name = eval_name
my_sgd = C.SGDParams(epoch_size=0,
minibatch_size=25,
learning_rates_per_mb=0.1,
max_epochs=3)
with C.LocalExecutionContext('logreg_numpy',
device_id=device_id,
clean_up=True) as ctx:
ctx.train(root_nodes=[ce, eval], training_params=my_sgd)
# For testing, we attach the test data to the input nodes.
X.reader.batch, y.reader.batch = test_X, test_y
result = ctx.test(root_nodes=[ce, eval])
return result
def train_eval_logistic_regression_with_numpy(criterion_name=None,
eval_name=None, device_id=-1):
# for repro and tests :-)
np.random.seed(1)
train_X, train_y = synthetic_data(train_N, feature_dim, num_classes)
test_X, test_y = synthetic_data(test_N, feature_dim, num_classes)
# Set up the training data for CNTK. Before writing the CNTK configuration,
# the data will be attached to X.reader.batch and y.reader.batch and then
# serialized.
X = C.input_numpy(train_X)
y = C.input_numpy(train_y)
# define our network -- one weight tensor and a bias
W = C.parameter(value=np.zeros(shape=(num_classes, feature_dim)))
b = C.parameter(value=np.zeros(shape=(num_classes, 1)))
out = C.times(W, X) + b
ce = C.cross_entropy_with_softmax(y, out)
ce.tag = 'criterion'
ce.name = criterion_name
eval = C.ops.cntk1.SquareError(y, out)
eval.tag = 'eval'
eval.name = eval_name
my_sgd = C.SGDParams(epoch_size=0, minibatch_size=25,
learning_rates_per_mb=0.1, max_epochs=3)
with C.LocalExecutionContext('logreg', clean_up=True) as ctx:
ctx.device_id = device_id
ctx.train(
root_nodes=[ce,eval],
training_params=my_sgd)
# For testing, we attach the test data to the input nodes.
X.reader.batch, y.reader.batch = test_X, test_y
result = ctx.test(root_nodes=[ce,eval])
return result
def train_eval_logistic_regression_with_numpy(criterion_name=None,
eval_name=None, device_id=-1):
# for repro and tests :-)
np.random.seed(1)
N = 500
d = 250
# create synthetic data using numpy
X = np.random.randn(N, d)
Y = np.random.randint(size=(N, 1), low=0, high=2)
Y = np.hstack((Y, 1-Y))
# set up the training data for CNTK
x = C.input_numpy(X)
y = C.input_numpy(Y)
# define our network -- one weight tensor and a bias
W = C.parameter(value=np.zeros(shape=(2, d)))
b = C.parameter(value=np.zeros(shape=(2, 1)))
out = C.times(W, x) + b
ce = C.cross_entropy_with_softmax(y, out)
ce.tag = 'criterion'
ce.name = criterion_name
eval = C.ops.cntk1.SquareError(y, out)
eval.tag = 'eval'
eval.name = eval_name
my_sgd = C.SGDParams(epoch_size=0, minibatch_size=25, learning_rates_per_mb=0.1, max_epochs=3)
with C.LocalExecutionContext('logreg') as ctx:
ctx.device_id = device_id
ctx.train(
root_nodes=[ce,eval],
training_params=my_sgd)
result = ctx.test(root_nodes=[ce,eval])
return result
def test_eval_plus_two_inputs():
result = cntk.eval(
cntk.plus(cntk.input_numpy([_LEFT]), cntk.input_numpy([_RIGHT])))
TOLERANCE_ABSOLUTE = 1E-06
assert np.allclose(result, _EXPECTED, atol=TOLERANCE_ABSOLUTE)
def test_eval_plus_two_inputs():
result = cntk.eval(cntk.plus(cntk.input_numpy([_LEFT]), cntk.input_numpy([_RIGHT])))
TOLERANCE_ABSOLUTE = 1E-06
assert np.allclose(result, _EXPECTED, atol=TOLERANCE_ABSOLUTE)
def test_eval_plus_two_inputs():
result = cntk.eval(cntk.plus(cntk.input_numpy([[1., 2., 3., 4.]]), cntk.input_numpy([[1., 1., 0., 0.]])))
TOLERANCE_ABSOLUTE = 1E-06
assert np.allclose(result, np.asarray([2., 3., 3., 4.]), atol=TOLERANCE_ABSOLUTE)