def main():
n = 6000
v = [x for x in range(n)]
m = [[x for x in range(n)] for _ in range(n)]
time_start = time.time()
for _ in range(3):
linalg.mdotv(m, v)
print(time.time() - time_start)
def main():
n = 6000
v = [x for x in range(n)]
m = [[x for x in range(n)] for _ in range(n)]
time_start = time.time()
for _ in range(3):
linalg.mdotv(m, v)
print(time.time() - time_start)
def gradient_single(self, train_x, train_y):
# For batch, want to compute A and Z for each input all at once
sigma_Z = []
A = [train_x]
for l, layer in enumerate(self.layers):
z = layer.compute_z(A[l])
a = layer.compute_a(z)
A.append(a)
sigma_Z.append(layer.compute_da(z))
delta_L = linalg.vtimesw(self.cost_d_function(train_y, A[-1]), sigma_Z[-1])
prev_delta = delta_L
dCdb = [[] for _ in range(len(self.layers))]
dCdw = [[] for _ in range(len(self.layers))]
dCdb[-1] = delta_L
dCdw[-1] = linalg.outer(delta_L, A[-2])
# TODO: for batch, we should loop through each training example and add/reduce it to the gradient matrices
for l_plus_1 in range(len(self.layers)-1, 0, -1):
layer = self.layers[l_plus_1]
delta = linalg.vtimesw(linalg.mdotv(linalg.transpose(layer.w), prev_delta), sigma_Z[l_plus_1-1])
# Bias and weight dervis
dCdb[l_plus_1-1] = delta
dCdw[l_plus_1-1] = linalg.outer(delta, A[l_plus_1-1])
prev_delta = delta
# TODO: divide by N, were this not to be a "single" gradient
return dCdb, dCdw
