def test_MNIST(self):
max_epoch = 5
batch_size = 100
hidden_size = 1000
train_set = dezero.datasets.MNIST(train=True)
test_set = dezero.datasets.MNIST(train=False)
train_loader = DataLoader(train_set, batch_size)
test_loader = DataLoader(test_set, batch_size, shuffle=False)
#model = MLP((hidden_size, 10))
model = MLP((hidden_size, hidden_size, 10), activation=F.relu)
optimizer = optimizers.SGD().setup(model)
if dezero.cuda.gpu_enable:
train_loader.to_gpu()
model.to_gpu()
for epoch in range(max_epoch):
sum_loss, sum_acc = 0, 0
for x, t in train_loader:
y = model(x)
loss = F.softmax_cross_entropy(y, t)
acc = F.accuracy(y, t)
model.cleargrads()
loss.backward()
optimizer.update()
sum_loss += float(loss.data) * len(t)
sum_acc += float(acc.data) * len(t)
print('epoch: {}'.format(epoch + 1))
print('train loss: {:.4f}, accuracy: {:.4f}'.format(
sum_loss / len(train_set), sum_acc / len(train_set)))
sum_loss, sum_acc = 0, 0
with dezero.no_grad():
for x, t in test_loader:
y = model(x)
loss = F.softmax_cross_entropy(y, t)
acc = F.accuracy(y, t)
sum_loss += float(loss.data) * len(t)
sum_acc += float(acc.data) * len(t)
print('test loss: {:.4f}, accuracy: {:.4f}'.format(
sum_loss / len(test_set), sum_acc / len(test_set)))
l.W.data = 0.02 * np.random.randn(*l.W.data.shape)
init_weight(dis, gen, hidden_size)
opt_g = Adam(alpha=0.0002, beta1=0.5).setup(gen)
opt_d = Adam(alpha=0.0002, beta1=0.5).setup(dis)
transform = lambda x: (x / 255.0).astype(np.float32)
train_set = dezero.datasets.MNIST(train=True, transform=transform)
train_loader = DataLoader(train_set, batch_size)
if use_gpu:
gen.to_gpu()
dis.to_gpu()
train_loader.to_gpu()
xp = dezero.cuda.cupy
else:
xp = np
label_real = xp.ones(batch_size).astype(np.int)
label_fake = xp.zeros(batch_size).astype(np.int)
test_z = xp.random.randn(25, hidden_size).astype(np.float32)
def generate_image():
with dezero.test_mode():
fake_images = gen(test_z)
img = dezero.cuda.as_numpy(fake_images.data)
plt.figure()