def test_predict_weights(X, expected):
W = numpy.asarray([1.0, 0.0, 0.0, 1.0], dtype="f").reshape((2, 2))
bias = numpy.asarray([0.0, 0.0], dtype="f")
model = Linear(W.shape[0], W.shape[1])
model.set_param("W", W)
model.set_param("b", bias)
scores = model.predict(X.reshape((1, -1)))
assert_allclose(scores.ravel(), expected)
def test_predict_extensive(W_b_input):
W, b, input_ = W_b_input
nr_out, nr_in = W.shape
model = Linear(nr_out, nr_in)
model.set_param("W", W)
model.set_param("b", b)
einsummed = numpy.einsum(
"bi,oi->bo",
numpy.asarray(input_, dtype="float32"),
numpy.asarray(W, dtype="float32"),
optimize=False,
)
expected_output = einsummed + b
predicted_output = model.predict(input_)
assert_allclose(predicted_output, expected_output, rtol=1e-04, atol=0.0001)
def test_update():
W = numpy.asarray([1.0, 0.0, 0.0, 1.0], dtype="f").reshape((2, 2))
bias = numpy.asarray([0.0, 0.0], dtype="f")
model = Linear(2, 2)
model.set_param("W", W)
model.set_param("b", bias)
sgd = SGD(1.0, L2=0.0, grad_clip=0.0)
sgd.averages = None
ff = numpy.asarray([[0.0, 0.0]], dtype="f")
tf = numpy.asarray([[1.0, 0.0]], dtype="f")
ft = numpy.asarray([[0.0, 1.0]], dtype="f") # noqa: F841
tt = numpy.asarray([[1.0, 1.0]], dtype="f") # noqa: F841
# ff, i.e. 0, 0
scores, backprop = model.begin_update(ff)
assert_allclose(scores[0, 0], scores[0, 1])
# Tell it the answer was 'f'
gradient = numpy.asarray([[-1.0, 0.0]], dtype="f")
backprop(gradient)
for key, (param, d_param) in model.get_gradients().items():
param, d_param = sgd(key, param, d_param)
model.set_param(key[1], param)
model.set_grad(key[1], d_param)
b = model.get_param("b")
W = model.get_param("W")
assert b[0] == 1.0
assert b[1] == 0.0
# Unchanged -- input was zeros, so can't get gradient for weights.
assert W[0, 0] == 1.0
assert W[0, 1] == 0.0
assert W[1, 0] == 0.0
assert W[1, 1] == 1.0
# tf, i.e. 1, 0
scores, finish_update = model.begin_update(tf)
# Tell it the answer was 'T'
gradient = numpy.asarray([[0.0, -1.0]], dtype="f")
finish_update(gradient)
for key, (W, dW) in model.get_gradients().items():
sgd(key, W, dW)
b = model.get_param("b")
W = model.get_param("W")
assert b[0] == 1.0
assert b[1] == 1.0
# Gradient for weights should have been outer(gradient, input)
# so outer([0, -1.], [1., 0.])
# = [[0., 0.], [-1., 0.]]
assert W[0, 0] == 1.0 - 0.0
assert W[0, 1] == 0.0 - 0.0
assert W[1, 0] == 0.0 - -1.0
assert W[1, 1] == 1.0 - 0.0
def get_model(W_values, b_values):
model = Linear(W_values.shape[0], W_values.shape[1], ops=NumpyOps())
model.initialize()
model.set_param("W", W_values)
model.set_param("b", b_values)
return model
