def __init__(self, num_classes=10, num_channels=1):
super(AlexNet, self).__init__()
self.num_classes = num_classes
self.input_size = 224
self.dimension = 4
self.conv1 = layer.Conv2d(num_channels, 64, 11, stride=4, padding=2)
self.conv2 = layer.Conv2d(64, 192, 5, padding=2)
self.conv3 = layer.Conv2d(192, 384, 3, padding=1)
self.conv4 = layer.Conv2d(384, 256, 3, padding=1)
self.conv5 = layer.Conv2d(256, 256, 3, padding=1)
self.linear1 = layer.Linear(4096)
self.linear2 = layer.Linear(4096)
self.linear3 = layer.Linear(num_classes)
self.pooling1 = layer.MaxPool2d(2, 2, padding=0)
self.pooling2 = layer.MaxPool2d(2, 2, padding=0)
self.pooling3 = layer.MaxPool2d(2, 2, padding=0)
self.avg_pooling1 = layer.AvgPool2d(3, 2, padding=0)
self.relu1 = layer.ReLU()
self.relu2 = layer.ReLU()
self.relu3 = layer.ReLU()
self.relu4 = layer.ReLU()
self.relu5 = layer.ReLU()
self.relu6 = layer.ReLU()
self.relu7 = layer.ReLU()
self.flatten = layer.Flatten()
self.dropout1 = layer.Dropout()
self.dropout2 = layer.Dropout()
self.softmax_cross_entropy = layer.SoftMaxCrossEntropy()
def __init__(self, perceptron_size=100, num_classes=10):
super(MLP, self).__init__()
self.num_classes = num_classes
self.relu = layer.ReLU()
self.linear1 = layer.Linear(perceptron_size)
self.linear2 = layer.Linear(num_classes)
self.softmax_cross_entropy = layer.SoftMaxCrossEntropy()
def __init__(self):
self.conv1 = layer.Conv2d(1, 20, 5, padding=0)
self.conv2 = layer.Conv2d(20, 50, 5, padding=0)
self.linear1 = layer.Linear(4 * 4 * 50, 500)
self.linear2 = layer.Linear(500, 10)
self.pooling1 = layer.MaxPool2d(2, 2, padding=0)
self.pooling2 = layer.MaxPool2d(2, 2, padding=0)
self.relu1 = layer.ReLU()
self.relu2 = layer.ReLU()
self.relu3 = layer.ReLU()
self.flatten = layer.Flatten()
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 = layer.Conv2d(num_channels, 20, 5, padding=0, activation="RELU")
self.conv2 = layer.Conv2d(20, 50, 5, padding=0, activation="RELU")
self.linear1 = layer.Linear(500)
self.linear2 = layer.Linear(num_classes)
self.pooling1 = layer.MaxPool2d(2, 2, padding=0)
self.pooling2 = layer.MaxPool2d(2, 2, padding=0)
self.relu = layer.ReLU()
self.flatten = layer.Flatten()
self.softmax_cross_entropy = layer.SoftMaxCrossEntropy()
def __init__(self, block, layers, num_classes=10, num_channels=3):
self.inplanes = 64
super(ResNet, self).__init__()
self.num_classes = num_classes
self.input_size = 224
self.dimension = 4
self.conv1 = layer.Conv2d(num_channels,
64,
7,
stride=2,
padding=3,
bias=False)
self.bn1 = layer.BatchNorm2d(64)
self.relu = layer.ReLU()
self.maxpool = layer.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1, layers1 = self._make_layer(block, 64, layers[0])
self.layer2, layers2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3, layers3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4, layers4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = layer.AvgPool2d(7, stride=1)
self.flatten = layer.Flatten()
self.fc = layer.Linear(num_classes)
self.softmax_cross_entropy = layer.SoftMaxCrossEntropy()
self.register_layers(*layers1, *layers2, *layers3, *layers4)
def __init__(self, onnx_model, num_classes=10, image_size=224, num_channels=3):
super(MyModel, self).__init__(onnx_model)
self.dimension = 4
self.num_classes = num_classes
self.input_size = image_size
self.num_channels = num_channels
self.linear = layer.Linear(512, num_classes)
def __init__(self, noise_size=100, feature_size=784, hidden_size=128):
super(LSGAN_MLP, self).__init__()
self.noise_size = noise_size
self.feature_size = feature_size
self.hidden_size = hidden_size
# Generative Net
self.gen_net_fc_0 = layer.Linear(self.hidden_size)
self.gen_net_relu_0 = layer.ReLU()
self.gen_net_fc_1 = layer.Linear(self.feature_size)
self.gen_net_sigmoid_1 = layer.Sigmoid()
# Discriminative Net
self.dis_net_fc_0 = layer.Linear(self.hidden_size)
self.dis_net_relu_0 = layer.ReLU()
self.dis_net_fc_1 = layer.Linear(1)
self.mse_loss = layer.MeanSquareError()
def __init__(self,
hidden_size,
mode='lstm',
return_sequences=False,
bidirectional="False",
num_layers=1):
super().__init__()
batch_first = True
self.lstm = layer.CudnnRNN(hidden_size=hidden_size,
batch_first=batch_first,
rnn_mode=mode,
return_sequences=return_sequences,
num_layers=1,
dropout=0.9,
bidirectional=bidirectional)
self.l1 = layer.Linear(64)
self.l2 = layer.Linear(2)
def __init__(self, hidden_size):
super(LSTMModel3, self).__init__()
self.lstm = layer.CudnnRNN(
hidden_size=hidden_size,
batch_first=True,
# return_sequences=True,
use_mask=True)
self.l1 = layer.Linear(2)
self.optimizer = opt.SGD(0.1)
def __init__(self, noise_size=100, feature_size=784, hidden_size=128):
super(GAN_MLP, self).__init__()
self.noise_size = noise_size
self.feature_size = feature_size
self.hidden_size = hidden_size
# Generative Net
self.gen_net_fc_0 = layer.Linear(self.hidden_size)
self.gen_net_relu_0 = layer.ReLU()
self.gen_net_fc_1 = layer.Linear(self.feature_size)
self.gen_net_sigmoid_1 = layer.Sigmoid()
# Discriminative Net
self.dis_net_fc_0 = layer.Linear(self.hidden_size)
self.dis_net_relu_0 = layer.ReLU()
self.dis_net_fc_1 = layer.Linear(1)
self.dis_net_sigmoid_1 = layer.Sigmoid()
self.binary_cross_entropy = layer.BinaryCrossEntropy()
def __init__(self, vocab_size, hidden_size=32):
super(CharRNN, self).__init__()
self.rnn = layer.LSTM(vocab_size, hidden_size)
self.cat = layer.Cat()
self.reshape1 = layer.Reshape()
self.dense = layer.Linear(hidden_size, vocab_size)
self.reshape2 = layer.Reshape()
self.softmax_cross_entropy = layer.SoftMaxCrossEntropy()
self.optimizer = opt.SGD(0.01)
self.hidden_size = hidden_size
self.vocab_size = vocab_size
def __init__(self,
onnx_model,
num_classes=10,
num_channels=3,
last_layers=-1,
in_dim=1000):
super(MyModel, self).__init__(onnx_model)
self.num_classes = num_classes
self.input_size = 224
self.dimension = 4
self.num_channels = num_channels
self.num_classes = num_classes
self.last_layers = last_layers
self.linear = layer.Linear(in_dim, num_classes)
def __init__(self, hidden_size):
super().__init__()
self.linear_q = layer.Linear(hidden_size)
self.linear_a = layer.Linear(hidden_size)
def __init__(self, a, b, c):
super(DoubleLinear, self).__init__()
self.l1 = layer.Linear(a, b)
self.l2 = layer.Linear(b, c)
def __init__(self, num_classes=10, num_channels=3):
""" Constructor
Args:
num_classes: number of classes
"""
super(Xception, self).__init__()
self.num_classes = num_classes
self.input_size = 299
self.dimension = 4
self.conv1 = layer.Conv2d(num_channels, 32, 3, 2, 0, bias=False)
self.bn1 = layer.BatchNorm2d(32)
self.relu1 = layer.ReLU()
self.conv2 = layer.Conv2d(32, 64, 3, 1, 1, bias=False)
self.bn2 = layer.BatchNorm2d(64)
self.relu2 = layer.ReLU()
# 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 = layer.SeparableConv2d(1024, 1536, 3, 1, 1)
self.bn3 = layer.BatchNorm2d(1536)
self.relu3 = layer.ReLU()
# do relu here
self.conv4 = layer.SeparableConv2d(1536, 2048, 3, 1, 1)
self.bn4 = layer.BatchNorm2d(2048)
self.relu4 = layer.ReLU()
self.globalpooling = layer.MaxPool2d(10, 1)
self.flatten = layer.Flatten()
self.fc = layer.Linear(num_classes)
self.softmax_cross_entropy = layer.SoftMaxCrossEntropy()
