def __init__(self):
self.conv1 = autograd.Conv2d(1, 20, 5, padding=0)
self.conv2 = autograd.Conv2d(20, 50, 5, padding=0)
self.linear1 = autograd.Linear(4 * 4 * 50, 500)
self.linear2 = autograd.Linear(500, 10)
self.pooling1 = autograd.MaxPool2d(2, 2, padding=0)
self.pooling2 = autograd.MaxPool2d(2, 2, padding=0)
def __init__(self, num_classes=10, num_channels=1):
super(CNN, self).__init__()
self.num_classes = num_classes
self.input_size = 28
self.dimension = 4
self.conv1 = autograd.Conv2d(num_channels, 20, 5, padding=0)
self.conv2 = autograd.Conv2d(20, 50, 5, padding=0)
self.linear1 = autograd.Linear(4 * 4 * 50, 500)
self.linear2 = autograd.Linear(500, num_classes)
self.pooling1 = autograd.MaxPool2d(2, 2, padding=0)
self.pooling2 = autograd.MaxPool2d(2, 2, padding=0)
def __init__(self, vocab_size, hidden_size=32):
super(CharRNN, self).__init__()
self.rnn = autograd.LSTM(vocab_size, hidden_size)
self.dense = autograd.Linear(hidden_size, vocab_size)
self.optimizer = opt.SGD(0.01)
self.hidden_size = hidden_size
self.vocab_size = vocab_size
self.hx = tensor.Tensor((1, self.hidden_size))
self.cx = tensor.Tensor((1, self.hidden_size))
def combine_node(model,modeldic):
'''
# for combine operators to layers
'''
for idx, i in enumerate(model.graph.node):
if (i.op_type == 'MatMul'):
addlist = Backend.find_add(model,i.output[0])
if (len(addlist) == 0): continue
if (len(addlist) > 1): continue
addidx = addlist[0]
if (i.name == "not_requires_grad" and model.graph.node[addidx].name == "not_requires_grad"): continue
model.graph.node[idx].output[0] = model.graph.node[addidx].output[0]
model.graph.node[idx].input.append(model.graph.node[addidx].input[1])
model.graph.node[idx].op_type = 'Linear'
model.graph.node[addidx].op_type = 'removed'
layer = {}
for i in model.graph.node:
if (i.op_type == 'Linear'):
shape = Backend.find_shape(model,i.input[1])
layer[str(i.output[0])] = autograd.Linear(shape[0], shape[1])
layer[str(i.output[0])].set_params(W=tensor.to_numpy(modeldic[str(i.input[1])]))
layer[str(i.output[0])].set_params(b=tensor.to_numpy(modeldic[str(i.input[2])]))
for i in model.graph.node:
if (i.op_type == 'Conv'):
shape = Backend.find_shape(model,i.input[1])
layer[str(i.output[0])] = autograd.Conv2d(shape[1], shape[0], shape[2],
padding=int(i.attribute[0].ints[0]))
layer[str(i.output[0])].set_params(W=tensor.to_numpy(modeldic[str(i.input[1])].clone()))
layer[str(i.output[0])].set_params(b=tensor.to_numpy(modeldic[str(i.input[2])].clone()))
for i in model.graph.node:
if (i.op_type == 'MaxPool'):
k = (int(i.attribute[0].ints[0]), int(i.attribute[0].ints[0]))
layer[str(i.output[0])] = autograd.MaxPool2d(k, int(i.attribute[2].ints[0]),
padding=int(i.attribute[1].ints[0]))
for i in model.graph.node:
if (i.op_type == 'AveragePool'):
k = (int(i.attribute[0].ints[0]), int(i.attribute[0].ints[0]))
layer[str(i.output[0])] = autograd.AvgPool2d(k, int(i.attribute[2].ints[0]),
padding=int(i.attribute[1].ints[0]))
for i in model.graph.node:
if (i.op_type == 'BatchNormalization'):
shape = Backend.find_shape(model,i.input[1])
layer[str(i.output[0])] = autograd.BatchNorm2d(shape[0])
layer[str(i.output[0])].set_params(scale=tensor.to_numpy(modeldic[str(i.input[1])].clone()))
layer[str(i.output[0])].set_params(bias=tensor.to_numpy(modeldic[str(i.input[2])].clone()))
return model,modeldic,layer
def singa_to_onnx(epochs, use_cpu=False, batchsize=32):
sgd = opt.SGD(lr=0.1)
# operations initialization
conv1 = autograd.Conv2d(1, 8, 3, 2, padding=1) # 28 - 14
conv2 = autograd.Conv2d(8, 4, 3, 2, padding=1) # 14 - 7
pooling = autograd.MaxPool2d(3, 2, padding=1) # 7 - 4
linear = autograd.Linear(64, 10)
def forward(x, t):
y = conv1(x)
y = autograd.relu(y)
y = conv2(y)
y = autograd.relu(y)
y = pooling(y)
y = autograd.flatten(y)
y = linear(y)
loss = autograd.softmax_cross_entropy(y, t)
return loss, y
autograd.training = True
(x_train, y_train), (x_test, y_test), dev = common(use_cpu)
niter = 1 # x_train.shape[0] // batchsize
for epoch in range(epochs):
accuracy_rate = 0.0
loss_rate = 0.0
for i in range(niter):
inputs = tensor.Tensor(
device=dev,
data=x_train[i * batchsize : (i + 1) * batchsize],
stores_grad=False,
name="input",
)
targets = tensor.Tensor(
device=dev,
data=y_train[i * batchsize : (i + 1) * batchsize],
requires_grad=False,
stores_grad=False,
name="target",
)
loss, y = forward(inputs, targets)
accuracy_rate += accuracy(
tensor.to_numpy(y), y_train[i * batchsize : (i + 1) * batchsize]
)
loss_rate += tensor.to_numpy(loss)[0]
for p, gp in autograd.backward(loss):
sgd.update(p, gp)
print( "accuracy is {}, loss is {}".format( accuracy_rate / niter, loss_rate / niter))
model = sonnx.to_onnx_model([inputs], [y])
sonnx.save(model, "cnn.onnx")
def __init__(self, block, layers, num_classes=1000):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = autograd.Conv2d(
3, 64, kernel_size=7, stride=2, padding=3, bias=False
)
self.bn1 = autograd.BatchNorm2d(64)
self.maxpool = autograd.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = autograd.AvgPool2d(7, stride=1)
self.fc = autograd.Linear(512 * block.expansion, num_classes)
def test_linear(self):
x = tensor.Tensor(shape=(2, 20), device=gpu_dev)
x.gaussian(0.0, 1.0)
x1 = x.clone()
y = autograd.Linear(20, 1, bias=False)(x)
# frontend
model = sonnx.to_onnx([x], [y])
# print('The model is:\n{}'.format(model))
# backend
sg_ir = sonnx.prepare(model, device=gpu_dev)
y_t = sg_ir.run([x1])
np.testing.assert_array_almost_equal(tensor.to_numpy(y),
tensor.to_numpy(y_t[0]),
decimal=5)
def __init__(self, num_classes=1000):
""" Constructor
Args:
num_classes: number of classes
"""
super(Xception, self).__init__()
self.num_classes = num_classes
self.conv1 = autograd.Conv2d(3, 32, 3, 2, 0, bias=False)
self.bn1 = autograd.BatchNorm2d(32)
self.conv2 = autograd.Conv2d(32, 64, 3, 1, 1, bias=False)
self.bn2 = autograd.BatchNorm2d(64)
# do relu here
self.block1 = Block(64,
128,
2,
2,
padding=0,
start_with_relu=False,
grow_first=True)
self.block2 = Block(128,
256,
2,
2,
padding=0,
start_with_relu=True,
grow_first=True)
self.block3 = Block(256,
728,
2,
2,
padding=0,
start_with_relu=True,
grow_first=True)
self.block4 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block5 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block6 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block7 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block8 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block9 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block10 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block11 = Block(728,
728,
3,
1,
start_with_relu=True,
grow_first=True)
self.block12 = Block(728,
1024,
2,
2,
start_with_relu=True,
grow_first=False)
self.conv3 = autograd.SeparableConv2d(1024, 1536, 3, 1, 1)
self.bn3 = autograd.BatchNorm2d(1536)
# do relu here
self.conv4 = autograd.SeparableConv2d(1536, 2048, 3, 1, 1)
self.bn4 = autograd.BatchNorm2d(2048)
self.globalpooling = autograd.MaxPool2d(10, 1)
self.fc = autograd.Linear(2048, num_classes)
x_train = preprocess(train[0])
y_train = to_categorical(train[1], num_classes)
x_test = preprocess(test[0])
y_test = to_categorical(test[1], num_classes)
print('the shape of training data is', x_train.shape)
print('the shape of training label is', y_train.shape)
print('the shape of testing data is', x_test.shape)
print('the shape of testing label is', y_test.shape)
# operations initialization
conv1 = autograd.Conv2d(1, 32, 3, padding=1)
conv21 = autograd.Conv2d(32, 16, 3, padding=1)
conv22 = autograd.Conv2d(32, 16, 3, padding=1)
linear = autograd.Linear(32 * 28 * 28, 10)
def forward(x, t):
y = conv1(x)
y = autograd.tanh(y)
y1 = conv21(y)
y2 = conv22(y)
y = autograd.cat((y1, y2), 1)
y = autograd.sigmoid(y)
y = autograd.mul(y, y)
y = autograd.flatten(y)
y = linear(y)
loss = autograd.softmax_cross_entropy(y, t)
return loss, y
autograd.training = True
'''
y = np.array(y, dtype='int')
n = y.shape[0]
categorical = np.zeros((n, num_classes))
categorical[np.arange(n), y] = 1
return categorical
label = to_categorical(label, 2).astype(np.float32)
print('train_data_shape:', data.shape)
print('train_label_shape:', label.shape)
inputs = Tensor(data=data)
target = Tensor(data=label)
linear1 = autograd.Linear(3, 2)
linear2 = autograd.Linear(2, 2)
linear3 = autograd.Linear(2, 2)
sgd = optimizer.SGD(0.00)
# training process
for i in range(1):
x = linear1(inputs)
x = autograd.relu(x)
x1 = linear2(x)
x2 = linear3(x)
x3 = autograd.add(x1, x2)
y = autograd.softmax(x3)
loss = autograd.cross_entropy(y, target)
gradient = autograd.backward(loss)
y_train = to_categorical(train[1], num_classes)
x_test = preprocess(test[0])
y_test = to_categorical(test[1], num_classes)
print('the shape of training data is', x_train.shape)
print('the shape of training label is', y_train.shape)
print('the shape of testing data is', x_test.shape)
print('the shape of testing label is', y_test.shape)
# operations initialization
conv1 = autograd.Conv2d(1, 1, 3, padding=1)
conv21 = autograd.Conv2d(1, 5, 3, padding=1)
conv22 = autograd.Conv2d(1, 5, 3, padding=1)
pooling1 = autograd.MaxPool2d(3, 1, padding=1)
pooling2 = autograd.AvgPool2d(28, 1, padding=0)
linear = autograd.Linear(10, 10)
bn = autograd.BatchNorm2d(10)
def forward(x, t):
y = conv1(x)
y = autograd.tanh(y)
y1 = conv21(y)
y2 = conv22(y)
y = autograd.cat((y1, y2), 1)
y = autograd.sigmoid(y)
y = bn(y)
y = autograd.relu(y)
y = autograd.mul(y, y)
y = pooling1(y)
y = autograd.sigmoid(y)
def __init__(self, sg_ir, last_layers):
self.sg_ir = sg_ir
self.last_layers = last_layers
self.append_linear1 = autograd.Linear(500, 128, bias=False)
self.append_linear2 = autograd.Linear(128, 32, bias=False)
self.append_linear3 = autograd.Linear(32, 10, bias=False)
'''
y = np.array(y, dtype='int')
n = y.shape[0]
categorical = np.zeros((n, num_classes))
categorical[np.arange(n), y] = 1
return categorical
label = to_categorical(label, 3).astype(np.float32)
print('train_data_shape:', data.shape)
print('train_label_shape:', label.shape)
inputs = Tensor(data=data)
target = Tensor(data=label)
linear1 = autograd.Linear(3, 3)
linear2 = autograd.Linear(3, 3)
linear3 = autograd.Linear(3, 3)
sgd = optimizer.SGD(0.00)
# training process
for i in range(1):
x = linear1(inputs)
x = autograd.relu(x)
x1 = linear2(x)
x2 = linear3(x)
x3 = autograd.add(x1, x2)
x3 = autograd.softmax(x3)
loss = autograd.cross_entropy(x3, target)
gradient = autograd.backward(loss)
