ConvTranspose2d

class torch.ao.nn.quantized.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)

在由多個輸入平面組成的輸入圖像上應用 2D 轉置卷積運算符。 有關輸入參數、參數和實現的詳細訊息，請參閱ConvTranspose2d。

有關特殊注意事項，請參閱Conv2d

變數

• weight (Tensor) – 從可學習的權重參數衍生的封裝張量。

• scale (Tensor) – 輸出縮放的純量

• zero_point (Tensor) – 輸出零點的純量

有關其他屬性，請參閱ConvTranspose2d。

範例

>>> # QNNPACK or FBGEMM as backend
>>> torch.backends.quantized.engine = 'qnnpack'
>>> # With square kernels and equal stride
>>> import torch.ao.nn.quantized as nnq
>>> 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))
>>> input = torch.randn(20, 16, 50, 100)
>>> q_input = torch.quantize_per_tensor(input, scale=1.0, zero_point=0, dtype=torch.quint8)
>>> output = m(q_input)
>>> # exact output size can be also specified as an argument
>>> input = torch.randn(1, 16, 12, 12)
>>> q_input = torch.quantize_per_tensor(input, scale=1.0, zero_point=0, dtype=torch.quint8)
>>> downsample = nnq.Conv2d(16, 16, 3, stride=2, padding=1)
>>> upsample = nnq.ConvTranspose2d(16, 16, 3, stride=2, padding=1)
>>> h = downsample(q_input)
>>> h.size()
torch.Size([1, 16, 6, 6])
>>> output = upsample(h, output_size=input.size())
>>> output.size()
torch.Size([1, 16, 12, 12])