我们从Python开源项目中，提取了以下8个代码示例，用于说明如何使用torch.nn.ConvTranspose1d()。
def __init__(self, in_channels, out_channels, kernel_size, bias=True): super().__init__() self.conv_t = nn.ConvTranspose1d( in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=kernel_size, bias=False ) if bias: self.bias = nn.Parameter( torch.FloatTensor(out_channels, kernel_size) ) else: self.register_parameter('bias', None) self.reset_parameters()
def __init__(self, noise_input_size, cond_input_size): super(_netG, self).__init__() self.noise_input_size = noise_input_size self.cond_input_size = cond_input_size # first dense block # input shape [batch_size x 147] self.fc1 = nn.Sequential( nn.Linear(self.noise_input_size + self.cond_input_size, 100 * 10), nn.BatchNorm1d(100 * 10), nn.LeakyReLU(0.2, inplace=True) ) # Convolutional block self.conv1 = nn.Sequential( # input shape [batch_size x 10 x 100] nn.ConvTranspose1d(10, 250, 13, stride=2, padding=6, output_padding=1, bias=True), nn.BatchNorm1d(250), nn.LeakyReLU(0.2, inplace=True), # input shape [batch_size x 250 x 200] nn.ConvTranspose1d(250, 100, 13, stride=2, padding=6, output_padding=1, bias=True), nn.BatchNorm1d(100), nn.LeakyReLU(0.2, inplace=True), # input shape [batch_size x 100 x 400] nn.ConvTranspose1d(100, 1, 13, stride=1, padding=6, bias=True), nn.BatchNorm1d(1), # input shape [batch_size x 1 x 400] nn.Tanh() )
def conv_transpose(in_ch, out_ch, kernel_size, stride=1, padding=0, out_padding=0, dilation=1, groups=1, bias=True, dim=2): #TODO: in the future some preprocessing goes here in_dim = dim if in_dim == 1: return nn.ConvTranspose1d(in_ch, out_ch, kernel_size, stride=stride, padding=padding, output_padding=out_padding, dilation=dilation, groups=groups, bias=bias) elif in_dim == 2: return nn.ConvTranspose2d(in_ch, out_ch, kernel_size, stride=stride, padding=padding, output_padding=out_padding, dilation=dilation, groups=groups, bias=bias) elif in_dim == 3: return nn.ConvTranspose3d(in_ch, out_ch, kernel_size, stride=stride, padding=padding, output_padding=out_padding, dilation=dilation, groups=groups, bias=bias) # pooling
def test_conv_modules_raise_error_on_incorrect_input_size(self): modules = [nn.Conv1d(3, 8, 3), nn.ConvTranspose1d(3, 8, 3), nn.Conv2d(3, 8, 3), nn.ConvTranspose2d(3, 8, 3), nn.Conv3d(3, 8, 3), nn.ConvTranspose3d(3, 8, 3)] invalid_input_dims = [(2, 4), (2, 4), (3, 5), (3, 5), (4, 6), (4, 6)] for invalid_dims, module in zip(invalid_input_dims, modules): for dims in invalid_dims: input = Variable(torch.Tensor(torch.Size((3, ) * dims))) self.assertRaises(ValueError, lambda: module(input))
def __init__(self, num_points = 2500): super(PointGenC, self).__init__() self.conv1 = nn.ConvTranspose1d(100, 1024, 2,2,0) self.conv2 = nn.ConvTranspose1d(1024, 512, 5,5,0) self.conv3 = nn.ConvTranspose1d(512, 256, 5,5,0) self.conv4 = nn.ConvTranspose1d(256, 128, 2,2,0) self.conv5 = nn.ConvTranspose1d(128, 64, 5,5,0) self.conv6 = nn.ConvTranspose1d(64, 3, 5,5,0) self.bn1 = torch.nn.BatchNorm1d(1024) self.bn2 = torch.nn.BatchNorm1d(512) self.bn3 = torch.nn.BatchNorm1d(256) self.bn4 = torch.nn.BatchNorm1d(128) self.bn5 = torch.nn.BatchNorm1d(64) self.th = nn.Tanh()
def is_sparseable(m): return True if hasattr(m, 'weight') and isinstance(m, ( nn.Conv1d, nn.Conv2d, nn.Conv3d, nn.ConvTranspose1d, nn.ConvTranspose2d, nn.ConvTranspose3d, nn.Linear)) else False
def __init__(self): super(Generator, self).__init__() self.deconv0 = nn.ConvTranspose1d(nz, ngf * 8, 4, 1, 0, bias=False) self.deconv1 = nn.ConvTranspose1d(ngf * 8, ngf * 4, 4, 2, 1, bias=False) self.deconv2 = nn.ConvTranspose1d(ngf * 4, ngf * 2, 4, 2, 1, bias=False) self.deconv3 = nn.ConvTranspose1d(ngf * 2, ngf * 1, 4, 2, 1, bias=False) self.deconv4 = nn.ConvTranspose1d(ngf * 1, ngf / 2, 4, 2, 1, bias=False) self.deconv5 = nn.ConvTranspose1d(ngf / 2, ngf / 4, 4, 2, 1, bias=False) self.deconv6 = nn.ConvTranspose1d(ngf / 4, ngf / 8, 4, 2, 1, bias=False) self.deconv7 = nn.ConvTranspose1d(ngf / 8, ngf / 16, 4, 2, 1, bias=False) self.deconv8 = nn.ConvTranspose1d(ngf / 16, ngf / 32, 4, 2, 1, bias=False) self.deconv9 = nn.ConvTranspose1d(ngf / 32, nc, 4, 2, 1, bias=False) self.bn0 = nn.BatchNorm1d(ngf * 8) self.bn1 = nn.BatchNorm1d(ngf * 4) self.bn2 = nn.BatchNorm1d(ngf * 2) self.bn3 = nn.BatchNorm1d(ngf * 1) self.bn4 = nn.BatchNorm1d(ngf / 2) self.bn5 = nn.BatchNorm1d(ngf / 4) self.bn6 = nn.BatchNorm1d(ngf / 8) self.bn7 = nn.BatchNorm1d(ngf / 16) self.bn8 = nn.BatchNorm1d(ngf / 32) self.relu = nn.ReLU(True) self.tanh = nn.Tanh() self.apply(weights_init) self.optimizer = optim.Adam(self.parameters(), lr=learning_rate, betas=(beta_1, beta_2)) #self.optimizer = optim.RMSprop(self.parameters(), lr=learning_rate, alpha=beta_2)
