def mlp(num_epochs, unit_count, hidden_layer_num=1):
net = nn.Sequential()
with net.name_scope():
for _ in range(hidden_layer_num):
net.add(gluon.nn.Dense(unit_count, activation="relu"))
net.add(gluon.nn.Dense(10))
net.initialize()
ctx = utils.try_gpu()
batch_size = 256
train_data, test_data = utils.load_data_fashion_mnist(batch_size)
loss = gluon.loss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), "sgd", {"learning_rate": 0.5})
return utils.train(train_data, test_data, net, loss, trainer, ctx, num_epochs=num_epochs)
def train_linear(num_epochs, batch_size=5):
dataset = gdata.ArrayDataset(X, y)
data_iter = gdata.DataLoader(dataset, batch_size, shuffle=True)
net = nn.Sequential()
with net.name_scope():
net.add(nn.Dense(1))
net.initialize()
square_loss = gloss.L2Loss()
ctx = utils.try_gpu()
trainer = gluon.Trainer(net.collect_params(), 'sgd',
{'learning_rate': 0.05})
return utils.train(data_iter,
data_iter,
net,
square_loss,
trainer,
ctx,
num_epochs=num_epochs)
def cnn(num_epochs):
net = nn.Sequential()
with net.name_scope():
net.add(
nn.Conv2D(channels=20, kernel_size=5, activation="relu"),
nn.MaxPool2D(pool_size=2, strides=2),
nn.Conv2D(channels=50, kernel_size=3, activation="relu"),
nn.MaxPool2D(pool_size=2, strides=2),
nn.Flatten(),
nn.Dense(128, activation="relu"),
nn.Dense(10)
)
net.initialize()
ctx = utils.try_gpu()
batch_size = 256
train_data, test_data = utils.load_data_fashion_mnist(batch_size)
loss = gluon.loss.SoftmaxCrossEntropyLoss()
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': 0.5})
return utils.train(train_data, test_data, net, loss, trainer, ctx, num_epochs=num_epochs)