def test_name():
a = np.arange(10)
b = np.zeros((3, 5))
c = np.arange(1, 11)
test1 = [str(L.Data(a)), str(L.Data([a, b])), str(L.Data(None))]
test1_truth = [
"<Data '/Data' input: (10,) num_output: (1)>",
"<Data '/Data' input: [(10,), (3, 5)] num_output: (2)>",
"<Data '/Data' input: None num_output: (0)>"
]
print(test1)
assert test1 == test1_truth
test2 = [str(L.ReLU(L.Data(a))), str(L.ReLU(L.FC(L.Data(b), dim_out=10)))]
test2_truth = [
"<ReLU '/ReLU' input: /Data:0 num_output: (1)>",
"<ReLU '/ReLU' input: /FC:0 num_output: (1)>"
]
print(test2)
assert test2 == test2_truth
la, lc = L.Data([a, c])
concat = L.Concat([la, lc], axis=0)
test3 = [str(concat)]
test3_truth = [
"<Concat '/Concat' input: [/Data:0,/Data:1] num_output: (1)>"
]
print(test3)
assert test3 == test3_truth
l = L.ReLU(a)
test4 = [str(l)]
test4_truth = ["<ReLU '/ReLU' input: (10,) num_output: (1)>"]
print(test4)
assert test4 == test4_truth
def __init__(self, X, labels):
data, label = L.Data([X, labels], "data", batch_size=100)
conv1 = L.Conv(data, dim_out=20, kernel=5)
pool1 = L.Pool(conv1, pool=L.Pool.MAX, kernel=2, stride=2)
relu1 = L.ReLU(pool1)
conv2 = L.Conv(relu1, dim_out=50, kernel=5)
pool2 = L.Pool(conv2, pool=L.Pool.MAX, kernel=2, stride=2)
relu2 = L.ReLU(pool2)
fc3 = L.FC(relu2, dim_out=500)
relu3 = L.ReLU(fc3)
pred = L.FC(relu3, "pred", dim_out=10)
loss = L.SoftmaxWithLoss(pred, "loss", label=label)
# Net Instance
self.net = mobula.Net()
# Set Loss Layer
self.net.set_loss(loss)
def test_relu():
l = L.ReLU(data, "ReLU")
l.reshape()
assert l.Y.shape == X.shape
l.forward()
l.dY = np.random.random(l.Y.shape) * 10
l.backward()
Y = np.zeros(X.shape)
b = (X > 0)
Y[b] = X[b]
dX = np.zeros(X.shape)
dX[b] = l.dY[b]
'''
d = (l.dX != dX)
print (l.dX[d], dX[d])
'''
assert np.allclose(l.Y.ravel(), Y.ravel())
assert np.allclose(l.dX.ravel(), dX.ravel())
def test_relu():
X = ((np.arange(10000) - 5000) / 1000.0).reshape((-1, 1, 1, 1))
data = L.Data(X, "data")
data.reshape()
l = L.ReLU(data)
l.reshape()
assert l.Y.shape == X.shape
l.forward()
l.dY = np.random.random(l.Y.shape) * 10
l.backward()
Y = np.zeros(X.shape)
b = (X > 0)
Y[b] = X[b]
dX = np.zeros(X.shape)
dX[b] = l.dY[b]
'''
d = (l.dX != dX)
print (l.dX[d], dX[d])
'''
assert np.allclose(l.Y.ravel(), Y.ravel())
assert np.allclose(l.dX.ravel(), dX.ravel())
Xmean = np.mean(X, 0)
np.save("xmean.npy", Xmean)
# Subtract mean and normalize
X = (X - Xmean) / 255.0
# transfer the shape of X to NCHW
# N, C, H, W = n, 1, 28, 28
X.resize((n, 1, 28, 28))
# LeNet-5
data, label = L.Data([X, labels], "data", batch_size = 100)
conv1 = L.Conv(data, "conv1", dim_out = 20, kernel = 5)
pool1 = L.Pool(conv1, "pool1", pool = L.Pool.MAX, kernel = 2, stride = 2)
relu1 = L.ReLU(pool1, "relu1")
conv2 = L.Conv(relu1, "conv2", dim_out = 50, kernel = 5)
pool2 = L.Pool(conv2, "pool2", pool = L.Pool.MAX, kernel = 2, stride = 2)
relu2 = L.ReLU(pool2, "relu2")
fc3 = L.FC(relu2, "fc3", dim_out = 500)
relu3 = L.ReLU(fc3, "relu3")
pred = L.FC(relu3, "pred", dim_out = 10)
loss = L.SoftmaxWithLoss(pred, "loss", label = label)
# Net Instance
net = mobula.Net()
# Set Loss Layer
net.set_loss(loss)
# Set Solver
im = imread("./mobula.png")
# Reshape
im = imresize(im, target_size)
# TO GRAY
im = im[:, :, 0] * 0.299 + im[:, :, 1] * 0.587 + im[:, :, 2] * 0.114
h, w = im.shape
t = 1
Y = im.reshape((1, h, w, t)).transpose((0, 3, 1, 2))
X = np.random.random((1, t, h, w)) - 0.5
data, label = L.Data([X, Y])
conv = L.Conv(data, dim_out=42, kernel=3, pad=1)
relu = L.ReLU(conv)
convt = L.ConvT(relu, dim_out=t, kernel=3, pad=1)
relu2 = L.ReLU(convt)
loss = L.MSE(relu2, label=label)
# Net Instance
net = mobula.Net()
# Set Loss Layer
net.set_loss(loss)
# Set Solver
net.set_solver(S.Momentum())
# Learning Rate
net.lr = 2e-6
start_iter = 0
# Subtract mean and normalize X = (X - Xmean) / 255.0 # transfer the shape of X to NCHW # N, C, H, W = n, 1, 28, 28 X.resize((n, 1, 28, 28)) # LeNet-5 data, label = L.Data([X, labels], "data", batch_size = 100)() conv1 = L.Conv(data, "conv1", dim_out = 20, kernel = 5) pool1 = L.Pool(conv1, "pool1", pool = L.Pool.MAX, kernel = 2, stride = 2) conv2 = L.Conv(pool1, "conv2", dim_out = 50, kernel = 5) pool2 = L.Pool(conv2, "pool2", pool = L.Pool.MAX, kernel = 2, stride = 2) fc3 = L.FC(pool2, "fc3", dim_out = 500) relu3 = L.ReLU(fc3, "relu3") pred = L.FC(relu3, "pred", dim_out = 10) loss = L.SoftmaxWithLoss(pred, "loss", label = label) # Net Instance net = mobula.Net() # Set Loss Layer net.set_loss(loss) # Set Solver net.set_solver(S.Momentum()) # Learning Rate net.lr = 0.2