def batch_relu_conv3d(in_channels,
out_channels,
kernel_size=3,
stride=1,
padding=1,
bn3d=True,
conv_param_attr=nn.initializer.KaimingNormal(),
conv_bias_attr=False,
bn_param_attr=None,
bn_bias_attr=None):
if bn3d:
# 3D batchnorm + relu + convolutional layer
return nn.Sequential(
nn.BatchNorm3D(num_features=in_channels), nn.ReLU(),
nn.Conv3D(in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
padding=padding,
stride=stride,
weight_attr=conv_param_attr,
bias_attr=conv_bias_attr))
else:
# 3D relu + convolutional layer
return nn.Sequential(
nn.ReLU(),
nn.Conv3D(in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
padding=padding,
stride=stride,
weight_attr=conv_param_attr,
bias_attr=conv_bias_attr))
def __init__(self, name_scope='VoxNet_', num_classes=10):
super(VoxNet, self).__init__()
self.backbone = nn.Sequential(nn.Conv3D(1, 32, 5, 2), nn.BatchNorm(32),
nn.LeakyReLU(), nn.Conv3D(32, 32, 3, 1),
nn.MaxPool3D(2, 2, 0))
self.head = nn.Sequential(nn.Linear(32 * 6 * 6 * 6, 128),
nn.LeakyReLU(), nn.Dropout(0.2),
nn.Linear(128, num_classes))
def __init__(self):
super(NetworkR, self).__init__()
self.layers = nn.Sequential(
nn.Pad3D((1, 1, 1, 1, 1, 1), mode='replicate'),
TempConv(1,
64,
kernel_size=(3, 3, 3),
stride=(1, 2, 2),
padding=(0, 0, 0)),
TempConv(64, 128, kernel_size=(3, 3, 3), padding=(1, 1, 1)),
TempConv(128, 128, kernel_size=(3, 3, 3), padding=(1, 1, 1)),
TempConv(128,
256,
kernel_size=(3, 3, 3),
stride=(1, 2, 2),
padding=(1, 1, 1)),
TempConv(256, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1)),
TempConv(256, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1)),
TempConv(256, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1)),
TempConv(256, 256, kernel_size=(3, 3, 3), padding=(1, 1, 1)),
Upsample(256, 128),
TempConv(128, 64, kernel_size=(3, 3, 3), padding=(1, 1, 1)),
TempConv(64, 64, kernel_size=(3, 3, 3), padding=(1, 1, 1)),
Upsample(64, 16),
nn.Conv3D(16,
1,
kernel_size=(3, 3, 3),
stride=(1, 1, 1),
padding=(1, 1, 1)))
def __init__(self, in_planes, out_planes, scale_factor=(1, 2, 2)):
super(Upsample, self).__init__()
self.scale_factor = scale_factor
self.conv3d = nn.Conv3D(in_planes,
out_planes,
kernel_size=(3, 3, 3),
stride=(1, 1, 1),
padding=(1, 1, 1))
self.bn = nn.BatchNorm(out_planes)
def __init__(self,
in_planes,
out_planes,
kernel_size=(1, 3, 3),
stride=(1, 1, 1),
padding=(0, 1, 1)):
super(TempConv, self).__init__()
self.conv3d = nn.Conv3D(in_planes,
out_planes,
kernel_size=kernel_size,
stride=stride,
padding=padding)
self.bn = nn.BatchNorm(out_planes)
def __init__(self, in_planes_s, in_planes_r):
"""
Parameters
----------
in_planes_s: int
Number of input source feature vector channels.
in_planes_r: int
Number of input reference feature vector channels.
"""
super(SourceReferenceAttention, self).__init__()
self.query_conv = nn.Conv3D(in_channels=in_planes_s,
out_channels=in_planes_s // 8,
kernel_size=1)
self.key_conv = nn.Conv3D(in_channels=in_planes_r,
out_channels=in_planes_r // 8,
kernel_size=1)
self.value_conv = nn.Conv3D(in_channels=in_planes_r,
out_channels=in_planes_r,
kernel_size=1)
self.gamma = self.create_parameter(
shape=[1],
dtype=self.query_conv.weight.dtype,
default_initializer=nn.initializer.Constant(0.0))
def paddle_nn_layer(self):
x_var = dg.to_variable(self.input)
conv = nn.Conv3D(self.num_channels,
self.num_filters,
self.filter_size,
padding=self.padding,
stride=self.stride,
dilation=self.dilation,
groups=self.groups,
data_format=self.data_format)
conv.weight.set_value(self.weight)
if not self.no_bias:
conv.bias.set_value(self.bias)
y_var = conv(x_var)
y_np = y_var.numpy()
return y_np
def paddle_nn_layer(self):
x_var = paddle.to_tensor(self.input)
x_var.stop_gradient = False
conv = nn.Conv3D(self.num_channels,
self.num_filters,
self.filter_size,
padding=self.padding,
stride=self.stride,
dilation=self.dilation,
groups=self.groups,
data_format=self.data_format)
conv.weight.set_value(self.weight)
if not self.no_bias:
conv.bias.set_value(self.bias)
y_var = conv(x_var)
y_var.backward()
y_np = y_var.numpy()
t1 = x_var.gradient()
return y_np, t1
def __init__(self):
super(NetworkC, self).__init__()
self.down1 = nn.Sequential(
nn.Pad3D((1, 1, 1, 1, 0, 0), mode='replicate'),
TempConv(1, 64, stride=(1, 2, 2), padding=(0, 0, 0)),
TempConv(64, 128), TempConv(128, 128),
TempConv(128, 256, stride=(1, 2, 2)), TempConv(256, 256),
TempConv(256, 256), TempConv(256, 512, stride=(1, 2, 2)),
TempConv(512, 512), TempConv(512, 512))
self.flat = nn.Sequential(TempConv(512, 512), TempConv(512, 512))
self.down2 = nn.Sequential(
TempConv(512, 512, stride=(1, 2, 2)),
TempConv(512, 512),
)
self.stattn1 = SourceReferenceAttention(
512, 512) # Source-Reference Attention
self.stattn2 = SourceReferenceAttention(
512, 512) # Source-Reference Attention
self.selfattn1 = SourceReferenceAttention(512, 512) # Self Attention
self.conv1 = TempConv(512, 512)
self.up1 = UpsampleConcat(512, 512, 512) # 1/8
self.selfattn2 = SourceReferenceAttention(512, 512) # Self Attention
self.conv2 = TempConv(512,
256,
kernel_size=(3, 3, 3),
stride=(1, 1, 1),
padding=(1, 1, 1))
self.up2 = nn.Sequential(
Upsample(256, 128), # 1/4
TempConv(128,
64,
kernel_size=(3, 3, 3),
stride=(1, 1, 1),
padding=(1, 1, 1)))
self.up3 = nn.Sequential(
Upsample(64, 32), # 1/2
TempConv(32,
16,
kernel_size=(3, 3, 3),
stride=(1, 1, 1),
padding=(1, 1, 1)))
self.up4 = nn.Sequential(
Upsample(16, 8), # 1/1
nn.Conv3D(8,
2,
kernel_size=(3, 3, 3),
stride=(1, 1, 1),
padding=(1, 1, 1)))
self.reffeatnet1 = nn.Sequential(
TempConv(3, 64, stride=(1, 2, 2)),
TempConv(64, 128),
TempConv(128, 128),
TempConv(128, 256, stride=(1, 2, 2)),
TempConv(256, 256),
TempConv(256, 256),
TempConv(256, 512, stride=(1, 2, 2)),
TempConv(512, 512),
TempConv(512, 512),
)
self.reffeatnet2 = nn.Sequential(
TempConv(512, 512, stride=(1, 2, 2)),
TempConv(512, 512),
TempConv(512, 512),
)
def func_test_layer_str(self):
module = nn.ELU(0.2)
self.assertEqual(str(module), 'ELU(alpha=0.2)')
module = nn.CELU(0.2)
self.assertEqual(str(module), 'CELU(alpha=0.2)')
module = nn.GELU(True)
self.assertEqual(str(module), 'GELU(approximate=True)')
module = nn.Hardshrink()
self.assertEqual(str(module), 'Hardshrink(threshold=0.5)')
module = nn.Hardswish(name="Hardswish")
self.assertEqual(str(module), 'Hardswish(name=Hardswish)')
module = nn.Tanh(name="Tanh")
self.assertEqual(str(module), 'Tanh(name=Tanh)')
module = nn.Hardtanh(name="Hardtanh")
self.assertEqual(str(module),
'Hardtanh(min=-1.0, max=1.0, name=Hardtanh)')
module = nn.PReLU(1, 0.25, name="PReLU", data_format="NCHW")
self.assertEqual(
str(module),
'PReLU(num_parameters=1, data_format=NCHW, init=0.25, dtype=float32, name=PReLU)'
)
module = nn.ReLU()
self.assertEqual(str(module), 'ReLU()')
module = nn.ReLU6()
self.assertEqual(str(module), 'ReLU6()')
module = nn.SELU()
self.assertEqual(
str(module),
'SELU(scale=1.0507009873554805, alpha=1.6732632423543772)')
module = nn.LeakyReLU()
self.assertEqual(str(module), 'LeakyReLU(negative_slope=0.01)')
module = nn.Sigmoid()
self.assertEqual(str(module), 'Sigmoid()')
module = nn.Hardsigmoid()
self.assertEqual(str(module), 'Hardsigmoid()')
module = nn.Softplus()
self.assertEqual(str(module), 'Softplus(beta=1, threshold=20)')
module = nn.Softshrink()
self.assertEqual(str(module), 'Softshrink(threshold=0.5)')
module = nn.Softsign()
self.assertEqual(str(module), 'Softsign()')
module = nn.Swish()
self.assertEqual(str(module), 'Swish()')
module = nn.Tanhshrink()
self.assertEqual(str(module), 'Tanhshrink()')
module = nn.ThresholdedReLU()
self.assertEqual(str(module), 'ThresholdedReLU(threshold=1.0)')
module = nn.LogSigmoid()
self.assertEqual(str(module), 'LogSigmoid()')
module = nn.Softmax()
self.assertEqual(str(module), 'Softmax(axis=-1)')
module = nn.LogSoftmax()
self.assertEqual(str(module), 'LogSoftmax(axis=-1)')
module = nn.Maxout(groups=2)
self.assertEqual(str(module), 'Maxout(groups=2, axis=1)')
module = nn.Linear(2, 4, name='linear')
self.assertEqual(
str(module),
'Linear(in_features=2, out_features=4, dtype=float32, name=linear)'
)
module = nn.Upsample(size=[12, 12])
self.assertEqual(
str(module),
'Upsample(size=[12, 12], mode=nearest, align_corners=False, align_mode=0, data_format=NCHW)'
)
module = nn.UpsamplingNearest2D(size=[12, 12])
self.assertEqual(
str(module),
'UpsamplingNearest2D(size=[12, 12], data_format=NCHW)')
module = nn.UpsamplingBilinear2D(size=[12, 12])
self.assertEqual(
str(module),
'UpsamplingBilinear2D(size=[12, 12], data_format=NCHW)')
module = nn.Bilinear(in1_features=5, in2_features=4, out_features=1000)
self.assertEqual(
str(module),
'Bilinear(in1_features=5, in2_features=4, out_features=1000, dtype=float32)'
)
module = nn.Dropout(p=0.5)
self.assertEqual(str(module),
'Dropout(p=0.5, axis=None, mode=upscale_in_train)')
module = nn.Dropout2D(p=0.5)
self.assertEqual(str(module), 'Dropout2D(p=0.5, data_format=NCHW)')
module = nn.Dropout3D(p=0.5)
self.assertEqual(str(module), 'Dropout3D(p=0.5, data_format=NCDHW)')
module = nn.AlphaDropout(p=0.5)
self.assertEqual(str(module), 'AlphaDropout(p=0.5)')
module = nn.Pad1D(padding=[1, 2], mode='constant')
self.assertEqual(
str(module),
'Pad1D(padding=[1, 2], mode=constant, value=0.0, data_format=NCL)')
module = nn.Pad2D(padding=[1, 0, 1, 2], mode='constant')
self.assertEqual(
str(module),
'Pad2D(padding=[1, 0, 1, 2], mode=constant, value=0.0, data_format=NCHW)'
)
module = nn.ZeroPad2D(padding=[1, 0, 1, 2])
self.assertEqual(str(module),
'ZeroPad2D(padding=[1, 0, 1, 2], data_format=NCHW)')
module = nn.Pad3D(padding=[1, 0, 1, 2, 0, 0], mode='constant')
self.assertEqual(
str(module),
'Pad3D(padding=[1, 0, 1, 2, 0, 0], mode=constant, value=0.0, data_format=NCDHW)'
)
module = nn.CosineSimilarity(axis=0)
self.assertEqual(str(module), 'CosineSimilarity(axis=0, eps=1e-08)')
module = nn.Embedding(10, 3, sparse=True)
self.assertEqual(str(module), 'Embedding(10, 3, sparse=True)')
module = nn.Conv1D(3, 2, 3)
self.assertEqual(str(module),
'Conv1D(3, 2, kernel_size=[3], data_format=NCL)')
module = nn.Conv1DTranspose(2, 1, 2)
self.assertEqual(
str(module),
'Conv1DTranspose(2, 1, kernel_size=[2], data_format=NCL)')
module = nn.Conv2D(4, 6, (3, 3))
self.assertEqual(str(module),
'Conv2D(4, 6, kernel_size=[3, 3], data_format=NCHW)')
module = nn.Conv2DTranspose(4, 6, (3, 3))
self.assertEqual(
str(module),
'Conv2DTranspose(4, 6, kernel_size=[3, 3], data_format=NCHW)')
module = nn.Conv3D(4, 6, (3, 3, 3))
self.assertEqual(
str(module),
'Conv3D(4, 6, kernel_size=[3, 3, 3], data_format=NCDHW)')
module = nn.Conv3DTranspose(4, 6, (3, 3, 3))
self.assertEqual(
str(module),
'Conv3DTranspose(4, 6, kernel_size=[3, 3, 3], data_format=NCDHW)')
module = nn.PairwiseDistance()
self.assertEqual(str(module), 'PairwiseDistance(p=2.0)')
module = nn.InstanceNorm1D(2)
self.assertEqual(str(module),
'InstanceNorm1D(num_features=2, epsilon=1e-05)')
module = nn.InstanceNorm2D(2)
self.assertEqual(str(module),
'InstanceNorm2D(num_features=2, epsilon=1e-05)')
module = nn.InstanceNorm3D(2)
self.assertEqual(str(module),
'InstanceNorm3D(num_features=2, epsilon=1e-05)')
module = nn.GroupNorm(num_channels=6, num_groups=6)
self.assertEqual(
str(module),
'GroupNorm(num_groups=6, num_channels=6, epsilon=1e-05)')
module = nn.LayerNorm([2, 2, 3])
self.assertEqual(
str(module),
'LayerNorm(normalized_shape=[2, 2, 3], epsilon=1e-05)')
module = nn.BatchNorm1D(1)
self.assertEqual(
str(module),
'BatchNorm1D(num_features=1, momentum=0.9, epsilon=1e-05, data_format=NCL)'
)
module = nn.BatchNorm2D(1)
self.assertEqual(
str(module),
'BatchNorm2D(num_features=1, momentum=0.9, epsilon=1e-05)')
module = nn.BatchNorm3D(1)
self.assertEqual(
str(module),
'BatchNorm3D(num_features=1, momentum=0.9, epsilon=1e-05, data_format=NCDHW)'
)
module = nn.SyncBatchNorm(2)
self.assertEqual(
str(module),
'SyncBatchNorm(num_features=2, momentum=0.9, epsilon=1e-05)')
module = nn.LocalResponseNorm(size=5)
self.assertEqual(
str(module),
'LocalResponseNorm(size=5, alpha=0.0001, beta=0.75, k=1.0)')
module = nn.AvgPool1D(kernel_size=2, stride=2, padding=0)
self.assertEqual(str(module),
'AvgPool1D(kernel_size=2, stride=2, padding=0)')
module = nn.AvgPool2D(kernel_size=2, stride=2, padding=0)
self.assertEqual(str(module),
'AvgPool2D(kernel_size=2, stride=2, padding=0)')
module = nn.AvgPool3D(kernel_size=2, stride=2, padding=0)
self.assertEqual(str(module),
'AvgPool3D(kernel_size=2, stride=2, padding=0)')
module = nn.MaxPool1D(kernel_size=2, stride=2, padding=0)
self.assertEqual(str(module),
'MaxPool1D(kernel_size=2, stride=2, padding=0)')
module = nn.MaxPool2D(kernel_size=2, stride=2, padding=0)
self.assertEqual(str(module),
'MaxPool2D(kernel_size=2, stride=2, padding=0)')
module = nn.MaxPool3D(kernel_size=2, stride=2, padding=0)
self.assertEqual(str(module),
'MaxPool3D(kernel_size=2, stride=2, padding=0)')
module = nn.AdaptiveAvgPool1D(output_size=16)
self.assertEqual(str(module), 'AdaptiveAvgPool1D(output_size=16)')
module = nn.AdaptiveAvgPool2D(output_size=3)
self.assertEqual(str(module), 'AdaptiveAvgPool2D(output_size=3)')
module = nn.AdaptiveAvgPool3D(output_size=3)
self.assertEqual(str(module), 'AdaptiveAvgPool3D(output_size=3)')
module = nn.AdaptiveMaxPool1D(output_size=16, return_mask=True)
self.assertEqual(
str(module), 'AdaptiveMaxPool1D(output_size=16, return_mask=True)')
module = nn.AdaptiveMaxPool2D(output_size=3, return_mask=True)
self.assertEqual(str(module),
'AdaptiveMaxPool2D(output_size=3, return_mask=True)')
module = nn.AdaptiveMaxPool3D(output_size=3, return_mask=True)
self.assertEqual(str(module),
'AdaptiveMaxPool3D(output_size=3, return_mask=True)')
module = nn.SimpleRNNCell(16, 32)
self.assertEqual(str(module), 'SimpleRNNCell(16, 32)')
module = nn.LSTMCell(16, 32)
self.assertEqual(str(module), 'LSTMCell(16, 32)')
module = nn.GRUCell(16, 32)
self.assertEqual(str(module), 'GRUCell(16, 32)')
module = nn.PixelShuffle(3)
self.assertEqual(str(module), 'PixelShuffle(upscale_factor=3)')
module = nn.SimpleRNN(16, 32, 2)
self.assertEqual(
str(module),
'SimpleRNN(16, 32, num_layers=2\n (0): RNN(\n (cell): SimpleRNNCell(16, 32)\n )\n (1): RNN(\n (cell): SimpleRNNCell(32, 32)\n )\n)'
)
module = nn.LSTM(16, 32, 2)
self.assertEqual(
str(module),
'LSTM(16, 32, num_layers=2\n (0): RNN(\n (cell): LSTMCell(16, 32)\n )\n (1): RNN(\n (cell): LSTMCell(32, 32)\n )\n)'
)
module = nn.GRU(16, 32, 2)
self.assertEqual(
str(module),
'GRU(16, 32, num_layers=2\n (0): RNN(\n (cell): GRUCell(16, 32)\n )\n (1): RNN(\n (cell): GRUCell(32, 32)\n )\n)'
)
module1 = nn.Sequential(
('conv1', nn.Conv2D(1, 20, 5)), ('relu1', nn.ReLU()),
('conv2', nn.Conv2D(20, 64, 5)), ('relu2', nn.ReLU()))
self.assertEqual(
str(module1),
'Sequential(\n '\
'(conv1): Conv2D(1, 20, kernel_size=[5, 5], data_format=NCHW)\n '\
'(relu1): ReLU()\n '\
'(conv2): Conv2D(20, 64, kernel_size=[5, 5], data_format=NCHW)\n '\
'(relu2): ReLU()\n)'
)
module2 = nn.Sequential(
nn.Conv3DTranspose(4, 6, (3, 3, 3)),
nn.AvgPool3D(kernel_size=2, stride=2, padding=0),
nn.Tanh(name="Tanh"), module1, nn.Conv3D(4, 6, (3, 3, 3)),
nn.MaxPool3D(kernel_size=2, stride=2, padding=0), nn.GELU(True))
self.assertEqual(
str(module2),
'Sequential(\n '\
'(0): Conv3DTranspose(4, 6, kernel_size=[3, 3, 3], data_format=NCDHW)\n '\
'(1): AvgPool3D(kernel_size=2, stride=2, padding=0)\n '\
'(2): Tanh(name=Tanh)\n '\
'(3): Sequential(\n (conv1): Conv2D(1, 20, kernel_size=[5, 5], data_format=NCHW)\n (relu1): ReLU()\n'\
' (conv2): Conv2D(20, 64, kernel_size=[5, 5], data_format=NCHW)\n (relu2): ReLU()\n )\n '\
'(4): Conv3D(4, 6, kernel_size=[3, 3, 3], data_format=NCDHW)\n '\
'(5): MaxPool3D(kernel_size=2, stride=2, padding=0)\n '\
'(6): GELU(approximate=True)\n)'
)
