def test_neuralNetwork_sgd():
from sklearn.neural_network._stochastic_optimizers import SGDOptimizer
np.random.seed(2019)
X = np.random.normal(size=(1, 500))
target = 3.9285985 * X
nn = NeuralNetwork(inputs=1,
neurons=3,
outputs=1,
activations='sigmoid',
silent=True)
nn.addLayer()
nn.addLayer()
nn.addOutputLayer(activations='identity')
learning_rate = 0.001
yhat = nn.forward_pass(X)
nn.backpropagation(yhat.T, target.T)
nn.learning_rate = learning_rate
initial_params = copy.deepcopy(nn.weights + nn.biases)
nn.sgd()
grad = nn.d_weights + nn.d_biases
params = nn.weights + nn.biases
change = [p - i_p for p, i_p in zip(params, initial_params)]
skl_sgd = SGDOptimizer(params=initial_params,
learning_rate_init=learning_rate,
nesterov=False,
momentum=1.0)
upd = skl_sgd._get_updates(grad)
for update_nn, update_skl in zip(change, upd):
assert update_nn == pytest.approx(update_skl)
def test_neuralNetwork_adam():
from sklearn.neural_network._stochastic_optimizers import AdamOptimizer
np.random.seed(2019)
X = np.random.normal(size=(1, 500))
target = 3.9285985 * X
nn = NeuralNetwork(inputs=1,
neurons=3,
outputs=1,
activations='sigmoid',
silent=True)
nn.addLayer()
nn.addLayer()
nn.addOutputLayer(activations='identity')
learning_rate = 0.001
yhat = nn.forward_pass(X)
nn.backpropagation(yhat.T, target.T)
nn.learning_rate = learning_rate
nn.initializeAdam()
nn.adam()
skl_adam = AdamOptimizer(params=nn.param, learning_rate_init=learning_rate)
upd = skl_adam._get_updates(nn.grad)
for update_nn, update_skl in zip(nn.change, upd):
assert update_nn == pytest.approx(update_skl)
def test_neuralNetwork_backpropagation_multiple_outputs():
# Similar to the test_neuralNetwork_backpropagation() test, but with
# multiple samples and features, X having dimensions
# (n_samples, n_features) = (3,2), as well as the target having dimensions
# (n_outputs) = (2)
from sklearn.neural_network import MLPRegressor
X = np.array([[0, 1], [1, 2], [2, 3]])
y = np.array([[0, 1], [2, 3], [3, 4]])
mlp = MLPRegressor(solver='sgd',
alpha=0.0,
learning_rate='constant',
learning_rate_init=1e-20,
max_iter=1,
hidden_layer_sizes=(3, 3),
random_state=1,
activation='logistic')
# Force sklearn to set up all the matrices by fitting a data set.
with warnings.catch_warnings():
warnings.simplefilter("ignore")
mlp.fit(X, y)
W_skl = mlp.coefs_
b_skl = mlp.intercepts_
nn = NeuralNetwork(inputs=2,
outputs=2,
layers=3,
neurons=3,
activations='sigmoid',
silent=True)
nn.addLayer()
nn.addLayer()
nn.addOutputLayer(activations='identity')
for i, w in enumerate(W_skl):
nn.weights[i] = w
for i, b in enumerate(b_skl):
nn.biases[i] = np.expand_dims(b, axis=1)
# ========================================================================
n_samples, n_features = X.shape
batch_size = n_samples
hidden_layer_sizes = mlp.hidden_layer_sizes
if not hasattr(hidden_layer_sizes, "__iter__"):
hidden_layer_sizes = [hidden_layer_sizes]
hidden_layer_sizes = list(hidden_layer_sizes)
layer_units = ([n_features] + hidden_layer_sizes + [mlp.n_outputs_])
activations = [X]
activations.extend(
np.empty((batch_size, n_fan_out)) for n_fan_out in layer_units[1:])
deltas = [np.empty_like(a_layer) for a_layer in activations]
coef_grads = [
np.empty((n_fan_in_, n_fan_out_))
for n_fan_in_, n_fan_out_ in zip(layer_units[:-1], layer_units[1:])
]
intercept_grads = [np.empty(n_fan_out_) for n_fan_out_ in layer_units[1:]]
# ========================================================================
activations = mlp._forward_pass(activations)
if y.ndim == 1:
y = y.reshape((-1, 1))
loss, coef_grads, intercept_grads = mlp._backprop(X, y, activations,
deltas, coef_grads,
intercept_grads)
yhat = nn.forward_pass(X.T)
nn.backpropagation(yhat.T, y)
for i, d_bias in enumerate(nn.d_biases):
assert np.squeeze(d_bias) == pytest.approx(
np.squeeze(intercept_grads[i]))
for i, d_weight in enumerate(nn.d_weights):
assert np.squeeze(d_weight) == pytest.approx(np.squeeze(coef_grads[i]))
def test_neuralNetwork_backpropagation():
# We re-use the test_neuralNetwork_network networks and this time check
# that the computed backpropagation derivatives are equal.
from sklearn.neural_network import MLPRegressor
X = [[0.0], [1.0], [2.0], [3.0], [4.0], [5.0]]
y = [0, 2, 4, 6, 8, 10]
mlp = MLPRegressor(solver='sgd',
alpha=0.0,
hidden_layer_sizes=(3, 3),
random_state=1,
activation='logistic')
# Force sklearn to set up all the matrices by fitting a data set.
with warnings.catch_warnings():
warnings.simplefilter("ignore")
mlp.fit(X, y)
# Throw away all the fitted values, randomize W and b matrices.
np.random.seed(18)
for i, coeff in enumerate(mlp.coefs_):
mlp.coefs_[i] = np.random.normal(size=coeff.shape)
for i, bias in enumerate(mlp.intercepts_):
mlp.intercepts_[i] = np.random.normal(size=bias.shape)
W_skl = mlp.coefs_
b_skl = mlp.intercepts_
nn = NeuralNetwork(inputs=1,
outputs=1,
layers=3,
neurons=3,
activations='sigmoid',
silent=False)
nn.addLayer()
nn.addLayer()
nn.addOutputLayer(activations='identity')
nn.weights = W_skl
for i, b in enumerate(b_skl):
nn.biases[i] = np.expand_dims(b, axis=1)
# From the sklearn source, we need to set up some lists to use the _backprop
# function in MLPRegressor, see:
#
# https://github.com/scikit-learn/scikit-learn/blob/bac89c2/sklearn/neural_network/multilayer_perceptron.py#L355
#
# ========================================================================
# Initialize lists
X = np.array([[1.125982598]])
y = np.array([8.29289285])
mlp.predict(X)
n_samples, n_features = X.shape
batch_size = n_samples
hidden_layer_sizes = mlp.hidden_layer_sizes
# Make sure self.hidden_layer_sizes is a list
if not hasattr(hidden_layer_sizes, "__iter__"):
hidden_layer_sizes = [hidden_layer_sizes]
hidden_layer_sizes = list(hidden_layer_sizes)
layer_units = ([n_features] + hidden_layer_sizes + [mlp.n_outputs_])
activations = [X]
activations.extend(
np.empty((batch_size, n_fan_out)) for n_fan_out in layer_units[1:])
deltas = [np.empty_like(a_layer) for a_layer in activations]
coef_grads = [
np.empty((n_fan_in_, n_fan_out_))
for n_fan_in_, n_fan_out_ in zip(layer_units[:-1], layer_units[1:])
]
intercept_grads = [np.empty(n_fan_out_) for n_fan_out_ in layer_units[1:]]
# ========================================================================
activations = mlp._forward_pass(activations)
loss, coef_grads, intercept_grads = mlp._backprop(X, y, activations,
deltas, coef_grads,
intercept_grads)
yhat = nn(X)
nn.backpropagation(yhat, y)
for i, d_bias in enumerate(nn.d_biases):
assert np.squeeze(d_bias) == pytest.approx(
np.squeeze(intercept_grads[i]))
for i, d_weight in enumerate(nn.d_weights):
assert np.squeeze(d_weight) == pytest.approx(np.squeeze(coef_grads[i]))
