max_epoch = 3
batch_size = 100
train_set = dezero.datasets.MNIST(train=True)
train_loader = DataLoader(train_set, batch_size)
model = MLP((1000, 10))
optimizer = optimizers.SGD().setup(model)
# read params if exist
if os.path.exists('my_nlp.npz'):
model.load_weights('my_nlp.npz')
else:
for epoch in range(max_epoch):
sum_loss = 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)
print('epoch: {}, loss: {:.4f}'.format(epoch + 1,
sum_loss / len(train_set)))
# save params
model.save_weights('my_nlp.npz')
model = MLP((1000, 10))
optimizer = optimizers.SGD().setup(model)
# GPU mode
if dezero.cuda.gpu_enable:
train_loader.to_gpu()
model.to_gpu()
# 매개변수 읽기
if os.path.exists("my_mlp.npz"):
model.load_weights("my_mlp.npz")
for epoch in range(max_epoch):
start = time.time()
sum_loss = 0
for x, t in train_loader:
y = model(x)
loss = F.softmax_cross_entropy(y, t)
model.cleargrads()
loss.backward()
optimizer.update()
sum_loss += float(loss.data) * len(t)
elapsed_time = time.time() - start
print("epoch: {}, loss: {:.4f}, time: {:.4f}[sec]".format(
epoch + 1, sum_loss / len(train_set), elapsed_time))
# 매개변수 저장하기
model.save_weights("my_mlp.npz")