def test_gpu_node_sigmoid_cross_entropy(a, b):
set_cuda_active(True)
g1 = Variable(a)
g2 = Variable(b)
g3 = rm.sigmoid_cross_entropy(g1, g2)
g = g3.grad()
g_g1 = g.get(g1)
g3.to_cpu()
g_g1.to_cpu()
set_cuda_active(False)
c3 = rm.sigmoid_cross_entropy(g1, g2)
c = c3.grad()
c_g1 = c.get(g1)
close(g3, c3)
close(c_g1, g_g1)
def fit(self, x, y):
N = len(x)
labels = self.lb.transform(y)
for i in range(self.epoch):
perm = np.random.permutation(N)
for j in range(N // self.batch):
train_batch = x[perm[j * self.batch:(j + 1) * self.batch]]
labels_batch = labels[perm[j * self.batch:(j + 1) * self.batch]]
with self.network.train():
z = self.network(train_batch)
loss = rm.sigmoid_cross_entropy(z, labels_batch)
loss.grad().update(self.optimizer)
return t3
epoch = 50
batch = 1
N = len(X)
optimizer = Sgd()
network = Mnist()
learning_curve = []
for i in range(epoch):
perm = np.random.permutation(N)
loss = 0
for j in range(0, N // batch):
train_batch = X[perm[j * batch:(j + 1) * batch]]
response_batch = y[perm[j * batch:(j + 1) * batch]]
with network.train():
result = network(train_batch)
l = rm.sigmoid_cross_entropy(result, response_batch)
grad = l.grad()
grad.update(optimizer)
loss += l
train_loss = loss / (N // batch)
learning_curve.append(train_loss)
print("train_loss:{}".format(train_loss))
print(network(X))
plt.plot(learning_curve, linewidth=3, label="train")
plt.show()
def func(node, x):
return sum(rm.sigmoid_cross_entropy(node, x, reduce_sum=False))
def func(node, x):
return rm.sigmoid_cross_entropy(node, x)