def make_test_graph():
x_tsr = np.arange(4).reshape([2, 2, 1]).astype(np.float)
w_tsr = np.arange(6).reshape([3, 2]).astype(np.float)
b_tsr = np.arange(3).reshape([3, 1]).astype(np.float)
ylabel_tsr = np.arange(6).reshape([2, 3, 1]).astype(np.float)
x = dg.identity(x_tsr, name='x')
w = dg.identity(w_tsr, name='w')
b = dg.identity(b_tsr, name='b')
y = dg.mat_add(dg.mat_mul(w, x, 'mat_mul'), b, name='y')
y_label = dg.identity(ylabel_tsr, name='ylabel')
w_l2 = dg.l2(w, name='w_l2')
loss = dg.mse(y_label, y, name='MSEloss')
loss_reg = dg.mat_add(w_l2, loss, name='loss_reg')
print('Constructed the following graph:')
for n in dg.forward_iter(loss_reg):
print(n.name)
return [x, w, b, y_label, loss, loss_reg]
train_iter = iter(trainloader)
x_data, y_data = train_iter.next()
x_data = x_data.reshape([15, 28, 28, 1]).numpy()
y_data = label2onehot(y_data).reshape([15, 10, 1])
print('type(x_data):', type(x_data))
print('x_data.shape:', x_data.shape)
print('type(y_data):', type(y_data))
print('y_data.shape:', y_data.shape)
print()
img_in = dg.identity(x_data)
y_label = dg.identity(y_data)
conv1 = dg.cnn.conv(img_in, 3, 6)
relu1 = dg.relu(conv1)
pool1 = dg.cnn.max_pool(relu1, 3, stride=1)
print('pool1.shape:', pool1.shape())
fl = dg.reshape(pool1, (15, 3456, 1))
print('fl.shape:', fl.shape())
w = dg.identity(np.random.randn(10, 3456))
print('w shape:', w.shape())
fc = dg.mat_mul(w, fl)
print('fc.shape:', fc.shape())
b = dg.identity(np.random.randn(10, 1))
out = dg.mat_add(fc, b)
print('out.shape:', out.shape())
loss = dg.softmax_cross(out, y_label)
def construct_conv():
img = dg.identity(np.random.randn(5,7,7,3))
conv = dg.cnn.conv(img, 3, 6, stride = (2,1), padding = (1,2))
print('Info about the conv layer:')
print(conv.op.to_str())
return conv
download=True,
transform=transform)
# In[7]:
testloader = torch.utils.data.DataLoader(testset,
batch_size=batch_size,
shuffle=False,
num_workers=2)
# In[8]:
w1_stdev = 0.1
w2_stdev = 0.01
x = dg.identity(np.random.randn(batch_size, 784, 1), name='x')
w_1 = dg.identity(np.random.randn(500, 784) * w1_stdev, name='w_1')
b_1 = dg.identity(np.random.randn(500, 1), name='b_1')
w_2 = dg.identity(np.random.randn(10, 500) * w2_stdev, name='w_2')
b_2 = dg.identity(np.random.randn(10, 1), name='b_2')
y_label = dg.identity(np.random.randn(batch_size, 10, 1), name='ylabel')
y_1 = dg.mat_add(dg.mat_mul(w_1, x, 'mat_mul_1'), b_1, name='y_1')
y_2 = dg.mat_add(dg.mat_mul(w_2, y_1, 'mat_mul_2'), b_2, name='y_2')
loss = dg.mse(y_label, y_2, name='MSEloss')
# In[26]:
sgd_optim = dg.optim.SGD(loss, [w_1, w_2, b_1, b_2], 0.0001)
train_iter = iter(trainloader)
import dg
import numpy as np
if __name__ == '__main__':
y_tsr = np.array([[10, 4], [13, 7]])
ylabel_tsr = np.array([[1, 0], [0, 1]])
y = dg.identity(y_tsr)
ylabel = dg.identity(ylabel_tsr)
soft = dg.SoftmaxCrossEntropyOp(y, ylabel)
print('soft.data():')
print(soft.data())
print('Calculate step by step')
print('cross 1:')
c1 = -np.log(np.exp(10) / (np.exp(10) + np.exp(4)))
print(c1)
print('cross 2:')
c2 = -np.log(np.exp(7) / (np.exp(7) + np.exp(13)))
print(c2)
print('agv:')
print((c1 + c2) / 2)