def test_020_matmul_build_specification():
name = "matmul01"
num_nodes = 8
num_features = 2
weights_initialization_scheme = "he"
expected_spec = {
_SCHEME: Matmul.class_id(),
_PARAMETERS: {
_NAME: name,
_NUM_NODES: num_nodes,
_NUM_FEATURES: num_features, # NOT including bias
_WEIGHTS: {
_SCHEME: weights_initialization_scheme
},
_OPTIMIZER: SGD.specification(name="sgd")
}
}
actual_spec = Matmul.specification(
name=name,
num_nodes=num_nodes,
num_features=num_features,
weights_initialization_scheme=weights_initialization_scheme,
)
assert expected_spec == actual_spec, \
"expected\n%s\nactual\n%s\n" % (expected_spec, actual_spec)
def test():
M = 1
D = 2
N = 100
X, T, V = linear_separable(d=D, n=N)
x_min, x_max = X[:, 0].min(), X[:, 0].max()
y_min, y_max = X[:, 1].min(), X[:, 1].max()
sigmoid_classifier_specification = {
_NAME: "softmax_classifier",
_NUM_NODES: M,
_LOG_LEVEL: logging.ERROR,
_COMPOSITE_LAYER_SPEC: {
"matmul01":
Matmul.specification(
name="matmul",
num_nodes=M,
num_features=D,
weights_initialization_scheme="he",
weights_optimizer_specification=SGD.specification(
lr=TYPE_FLOAT(0.2), l2=TYPE_FLOAT(1e-3))),
"loss":
CrossEntropyLogLoss.specification(
name="loss",
num_nodes=M,
loss_function=sigmoid_cross_entropy_log_loss.__qualname__)
}
}
logistic_classifier = SequentialNetwork.build(
specification=sigmoid_classifier_specification, )
for i in range(50):
logistic_classifier.train(X=X, T=T)
prediction = logistic_classifier.predict(
np.array([-1., -1.], dtype=TYPE_FLOAT))
np.isin(prediction, [0, 1])
print(prediction)