t = jhML.Variable(x, requires_grad=False)
activated_layers = net[:-1]
for l in activated_layers:
t = l(t)
t = activ(t)
return net[-1](t)
if __name__ == "__main__":
x = [[0, 0], [0, 1], [1, 0], [1, 1]]
gt = [[0], [1], [1], [0]]
net = [L.Linear(2, 4), L.Linear(4, 8), L.Linear(8, 8), L.Linear(8, 1)]
num_epoch = int(1e+5)
for epoch in range(num_epoch):
clear_grad(net)
pred = forward(x, net)
loss = F.mean_squared_error(pred, gt)
loss.backward()
if epoch % (num_epoch / 100) == 0:
print("%d/%d" % (epoch, num_epoch))
print(pred)
update_grad(net, lr=8e-5)
for num in x:
pred = forward([num], net)
[0, 1, 0], #2
[1, 1, 1], #7
]
gt = [
[0],
[6],
[4],
[3],
[2],
[7],
]
num_class = 8
net = nn.Sequential(nn.Linear(3, 4), nn.ReLU(), nn.Linear(4, 1000),
nn.ReLU(), nn.Linear(1000, 800), nn.ReLU(),
nn.Linear(800, 100), nn.ReLU(), nn.Linear(100, 8),
nn.ReLU(), nn.Linear(8, num_class)).to_gpu()
#### learning
optim = optim.RMSprop(net.params(), lr=1e-4)
num_epoch = int(1e+4)
for epoch in range(num_epoch):
data, label = jhML.Variable(x).to_gpu(), jhML.Variable(gt).to_gpu()
optim.zero_grad()
pred = net(data)
loss = F.softmax_cross_entropy(pred, label)
loss.backward()
optim.step()
os.path.dirname(
os.path.dirname(os.path.dirname(os.path.abspath(__file__))))))
import jhML
import jhML.layers as nn
import jhML.functions as F
import jhML.optimizer as optim
from jhML.tutorial.dataset import MNIST
def get_accuracy(pred, gt):
pred = jhML.as_cpu(pred)
gt = jhML.as_cpu(gt)
return np.sum((pred == gt).astype(float)) / len(gt)
net = nn.Sequential(nn.Linear(28 * 28, 28 * 28), nn.ReLU(),
nn.Linear(28 * 28, 1000), nn.ReLU(), nn.Linear(1000, 1000),
nn.ReLU(), nn.Linear(1000, 100), nn.ReLU(),
nn.Linear(100, 10), nn.ReLU(),
nn.Linear(10, MNIST.num_class))
if __name__ == "__main__":
using_gpu = True
num_class = 10
dataset_mnist_train = MNIST(train=True, flatten=True)
dataset_mnist_test = MNIST(train=False, flatten=True)
train_dataloader = jhML.Dataloader(dataset_mnist_train,
batch_size=256,
gpu=using_gpu,
drop_last=True)
sys.path.append( os.path.dirname( os.path.dirname( os.path.dirname( os.path.dirname( os.path.abspath(__file__) ) ) ) ))
import jhML
import jhML.layers as nn
import jhML.functions as F
import jhML.optimizer as optim
from jhML.tutorial.dataset import MNIST
def get_accuracy(pred, gt):
pred = jhML.as_cpu(pred)
gt = jhML.as_cpu(gt)
return np.sum((pred == gt).astype(float))/len(gt)
net = nn.Sequential(
nn.Linear(28*28, 28*28),
nn.ReLU(),
nn.Linear(28*28, 1000),
nn.ReLU(),
nn.Linear(1000, 1000),
nn.ReLU(),
nn.Linear(1000, 100),
nn.ReLU(),
nn.Linear(100, 10),
nn.ReLU(),
nn.Linear(10, MNIST.num_class)
)
if __name__ == "__main__":
using_gpu = True
if __name__ == "__main__":
x = [[0, 0],
[0, 1],
[1, 0],
[1, 1]]
gt = [[0],
[1],
[1],
[0]]
data = jhML.Variable(x)
net = nn.Sequential(
nn.Linear(2, 4),
nn.ReLU(),
nn.Linear(4, 8),
nn.ReLU(),
nn.Linear(8, 8),
nn.ReLU(),
nn.Linear(8, 1)
)
#### learning
optim = optim.RMSprop(net.params(), lr=1e-4)
num_epoch = int(1e+5)
for epoch in range(num_epoch):
optim.zero_grad()
pred = net(data)
loss = F.mean_squared_error(pred, gt)