data_path = '~/data/decompress_mnist'
if __name__ == '__main__':
x_train, x_test, y_train, y_test = mnist.load_mnist(data_path, dst_size=(32, 32), shuffle=True)
x_train = x_train / 255 - 0.5
x_test = x_test / 255 - 0.5
data = {
'X_train': x_train,
'y_train': y_train,
'X_val': x_test,
'y_val': y_test
}
model = models.LeNet5(in_channels=1, out_channels=10, dropout=0.5)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.params, lr=1e-3, momentum=0.9, nesterov=True)
stepLR = optim.StepLR(optimizer, 5, gamma=0.1)
solver = pynet.Solver(model, data, criterion, optimizer,
lr_scheduler=stepLR, batch_size=128, num_epochs=10, print_every=1)
solver.train()
plt = Draw()
plt(solver.loss_history)
plt.multi_plot((solver.train_acc_history, solver.val_acc_history), ('train', 'val'),
title='准确率', xlabel='迭代/次', ylabel='准确率', save_path='acc.png')
print('best_train_acc: %f; best_val_acc: %f' % (solver.best_train_acc, solver.best_val_acc))
shuffle=True,
is_flatten=True)
x_train = x_train / 255 - 0.5
x_test = x_test / 255 - 0.5
data = {
'X_train': x_train,
'y_train': y_train,
'X_val': x_test,
'y_val': y_test
}
model = models.TwoLayerNet(num_in=784, num_hidden=200, num_out=10)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.params)
solver = pynet.Solver(model,
data,
criterion,
optimizer,
batch_size=128,
num_epochs=10)
solver.train()
plt = Draw()
plt(solver.loss_history)
plt.multi_plot((solver.train_acc_history, solver.val_acc_history),
('train', 'val'),
title='准确率',
xlabel='迭代/次',
from pynet.vision.data import mnist
from pynet.vision import Draw
data_path = '~/data/decompress_mnist'
if __name__ == '__main__':
x_train, x_test, y_train, y_test = mnist.load_mnist(data_path, shuffle=True, is_flatten=True)
x_train = x_train / 255 - 0.5
x_test = x_test / 255 - 0.5
data = {
'X_train': x_train,
'y_train': y_train,
'X_val': x_test,
'y_val': y_test
}
model = models.ThreeLayerNet(num_in=784, num_h1=1200, num_h2=200, num_out=10, dropout=0.5)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.params, lr=1e-3)
solver = pynet.Solver(model, data, criterion, optimizer, batch_size=256, num_epochs=10, print_every=1, reg=1e-3)
solver.train()
plt = Draw()
plt(solver.loss_history)
plt.multi_plot((solver.train_acc_history, solver.val_acc_history), ('train', 'val'),
title='准确率', xlabel='迭代/次', ylabel='准确率', save_path='acc.png')
print('best_train_acc: %f; best_val_acc: %f' % (solver.best_train_acc, solver.best_val_acc))
x_train = x_train / 255 - 0.5
x_test = x_test / 255 - 0.5
data = {
'X_train': x_train,
'y_train': y_train,
'X_val': x_test,
'y_val': y_test
}
model = models.ThreeLayerNet(num_in=644,
num_h1=2000,
num_h2=800,
num_out=40)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.params, lr=2e-2)
solver = pynet.Solver(model,
data,
criterion,
optimizer,
batch_size=4,
num_epochs=100,
reg=1e-3,
print_every=1)
solver.train()
plt = Draw()
plt(solver.loss_history)
plt.multi_plot((solver.train_acc_history, solver.val_acc_history),
('train', 'val'),