def test_MomentumSDG(self):
x = np.random.rand(100, 1)
y = np.sin(2 * np.pi * x) + np.random.rand(100, 1)
hidden_size = 10
model = MLP((hidden_size, 1))
optimizer = optimizers.MomentumSGD(lr)
optimizer.setup(model)
for i in range(max_iters):
y_pred = model(x)
loss = F.mean_squared_error(y, y_pred)
model.cleargrads()
loss.backward()
optimizer.update()
assert True
from dezero.models import MLP
import dezero
# np.random.seed(0)
# x = np.random.rand(100, 1)
# y = np.sin(2*np.pi*x)+np.random.rand(100, 1)
lr = 1.0
batch_size = 100
max_epoch = 5
hidden_size = 1000
train_set = dezero.datasets.MNIST(train=True)
train_loader = DataLoader(train_set, batch_size)
model = MLP((hidden_size, 10))
optimizer = optimizers.MomentumSGD(lr)
optimizer.setup(model)
if dezero.cuda.gpu_enable:
train_loader.to_gpu()
model.to_gpu()
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()
import numpy as np
from dezero import Variable, optimizers, layers as L, functions as F
from dezero.models import MLP
np.random.seed(0)
x = np.random.randn(100, 1)
y = np.sin(2 * np.pi * x) + np.random.rand(100, 1)
lr = 0.2
max_iter = 10000
hidden_size = 10
model = MLP((hidden_size, 1))
# optimizer = optimizers.SGD(lr).setup(model)
optimizer = optimizers.MomentumSGD(lr).setup(model)
for i in range(max_iter):
y_pred = model(x)
loss = F.mean_squared_error(y, y_pred)
model.cleargrads()
loss.backward()
optimizer.update()
if i % 1000 == 0:
print("loss", loss)