return vectors[1:]
@pytest.fixture(params=[softmax_cost_and_gradient, neg_sampling_cost_and_gradient])
def test_cost_and_grad_func_inputvec(input_vectors, output_vectors, parameters):
grad_func = lambda w: param(w, )
print "==== Gradient check for soft_max_cost_and_gradient ===="
def g_func_wrapper1(f, *params, **kws):
cost, grad_pred, grad = f(*params, **kws)
return cost, grad_pred
def g_func_wrapper2(f, *params, **kws):
cost, grad_pred, grad = f(*params, **kws)
return cost, grad
gradcheck_naive(lambda vec: g_func_wrapper1(softmax_cost_and_gradient, vec, 0, dummy_vectors[1:], dataset, parameters=parameters),
dummy_vectors[0])
gradcheck_naive(lambda vec: g_func_wrapper2(softmax_cost_and_gradient, dummy_vectors[0], 0, vec, dataset, parameters=parameters),
dummy_vectors[1:])
print "==== Gradient check for neg_sampling_max_cost_and_gradient ===="
print "test 1"
gradcheck_naive(lambda vec: g_func_wrapper1(neg_sampling_cost_and_gradient, vec, 0, dummy_vectors[1:], dataset, parameters=parameters),
dummy_vectors[0], verbose=False)
print "test 2"
gradcheck_naive(lambda vec: g_func_wrapper2(neg_sampling_cost_and_gradient, dummy_vectors[0], 0, vec, dataset, parameters=parameters),
dummy_vectors[1:])
parameters = AttrDict(
{
'context_size' : 1,
'sgd' : {'batch_size': 1},
class DatasetWrapper(object):
def __init__(self, dataset, parameters=None):
self._dataset = dataset
self._parameters = parameters
self.get_context = self.get_random_context
self.sample_token_idx = self._dataset.sampleTokenIdx
def get_random_context(self):
return self._dataset.getRandomContext()
if __name__ == '__main__':
# Sanity check for the gradient checker
quad = lambda x: (np.sum(x ** 2), x * 2)
gradcheck_naive(quad, np.array(123.456)) # scalar test
gradcheck_naive(quad, np.random.randn(3,)) # 1-D test
gradcheck_naive(quad, np.random.randn(4,5)) # 2-D test
# Set up fake data and parameters for the neural network
N = 20
dimensions = [10, 5, 10]
data = np.random.randn(N, dimensions[0]) # each row will be a datum
labels = np.zeros((N, dimensions[2]))
for i in xrange(N):
labels[i,random.randint(0, dimensions[2]-1)] = 1
params = np.random.randn((dimensions[0] + 1) * dimensions[1] + (dimensions[1] + 1) * dimensions[2], )
print "Dimensionality of parameter vector", params.shape
