ConvTranspose2d

class torch.ao.nn.quantized.dynamic.modules.conv.ConvTranspose2d(in_channels, out_channels, kernel_size, stride=1, padding=0, output_padding=0, groups=1, bias=True, dilation=1, padding_mode='zeros', device=None, dtype=None)

一种动态量化的转置卷积模块，其输入和输出为浮点张量。

有关输入参数、参数设置和实现的详细信息，请参阅 ConvTranspose2d。

有关特别注意事项，请参阅 Conv2d

变量:

• weight (Tensor) – 来自可学习权重参数的打包张量。

• scale (Tensor) – 输出尺度的标量

• zero_point (Tensor) – 输出零点的标量

有关其他属性，请参阅 ConvTranspose2d。

示例

>>> # With square kernels and equal stride
>>> m = nnq.ConvTranspose2d(16, 33, 3, stride=2)
>>> # non-square kernels and unequal stride and with padding
>>> m = nnq.ConvTranspose2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2))
>>> output = m(input)
>>> # exact output size can be also specified as an argument
>>> downsample = nnq.Conv2d(16, 16, 3, stride=2, padding=1)
>>> upsample = nnq.ConvTranspose2d(16, 16, 3, stride=2, padding=1)
>>> h = downsample(input)
>>> h.size()
torch.Size([1, 16, 6, 6])
>>> output = upsample(h, output_size=input.size())
>>> output.size()
torch.Size([1, 16, 12, 12])