File size: 9,910 Bytes
9c6594c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 |
# mypy: allow-untyped-defs
"""Gradient interface."""
import torch
from torch.nn.modules.utils import _pair, _single, _triple
def conv1d_input(
input_size,
weight,
grad_output,
stride=1,
padding=0,
dilation=1,
groups=1,
):
r"""Compute the gradient of conv1d with respect to the input of the convolution.
This is same as the 1D transposed convolution operator under the hood but requires
the shape of the gradient w.r.t. input to be specified explicitly.
Args:
input_size : Shape of the input gradient tensor
weight: weight tensor (out_channels x in_channels/groups x kW)
grad_output : output gradient tensor (minibatch x out_channels x oW)
stride (int or tuple, optional): Stride of the convolution. Default: 1
padding (int or tuple, optional): Zero-padding added to both sides of the input. Default: 0
dilation (int or tuple, optional): Spacing between kernel elements. Default: 1
groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1
Examples::
>>> input = torch.randn(1, 1, 3, requires_grad=True)
>>> weight = torch.randn(1, 1, 1, requires_grad=True)
>>> output = F.conv1d(input, weight)
>>> grad_output = torch.randn(output.shape)
>>> grad_input = torch.autograd.grad(output, input, grad_output)
>>> F.grad.conv1d_input(input.shape, weight, grad_output)
"""
input = grad_output.new_empty(1).expand(input_size)
return torch.ops.aten.convolution_backward(
grad_output,
input,
weight,
None,
_single(stride),
_single(padding),
_single(dilation),
False,
[0],
groups,
(True, False, False),
)[0]
def conv1d_weight(
input,
weight_size,
grad_output,
stride=1,
padding=0,
dilation=1,
groups=1,
):
r"""Compute the gradient of conv1d with respect to the weight of the convolution.
Args:
input: input tensor of shape (minibatch x in_channels x iW)
weight_size : Shape of the weight gradient tensor
grad_output : output gradient tensor (minibatch x out_channels x oW)
stride (int or tuple, optional): Stride of the convolution. Default: 1
padding (int or tuple, optional): Zero-padding added to both sides of the input. Default: 0
dilation (int or tuple, optional): Spacing between kernel elements. Default: 1
groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1
Examples::
>>> input = torch.randn(1, 1, 3, requires_grad=True)
>>> weight = torch.randn(1, 1, 1, requires_grad=True)
>>> output = F.conv1d(input, weight)
>>> grad_output = torch.randn(output.shape)
>>> # xdoctest: +SKIP
>>> grad_weight = torch.autograd.grad(output, filter, grad_output)
>>> F.grad.conv1d_weight(input, weight.shape, grad_output)
"""
weight = grad_output.new_empty(1).expand(weight_size)
return torch.ops.aten.convolution_backward(
grad_output,
input,
weight,
None,
_single(stride),
_single(padding),
_single(dilation),
False,
[0],
groups,
(False, True, False),
)[1]
def conv2d_input(
input_size,
weight,
grad_output,
stride=1,
padding=0,
dilation=1,
groups=1,
):
r"""Compute the gradient of conv2d with respect to the input of the convolution.
This is same as the 2D transposed convolution operator under the hood but requires
the shape of the gradient w.r.t. input to be specified explicitly.
Args:
input_size : Shape of the input gradient tensor
weight: weight tensor (out_channels x in_channels/groups x kH x kW)
grad_output : output gradient tensor (minibatch x out_channels x oH x oW)
stride (int or tuple, optional): Stride of the convolution. Default: 1
padding (int or tuple, optional): Zero-padding added to both sides of the input. Default: 0
dilation (int or tuple, optional): Spacing between kernel elements. Default: 1
groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1
Examples::
>>> input = torch.randn(1, 1, 3, 3, requires_grad=True)
>>> weight = torch.randn(1, 1, 1, 2, requires_grad=True)
>>> output = F.conv2d(input, weight)
>>> grad_output = torch.randn(output.shape)
>>> grad_input = torch.autograd.grad(output, input, grad_output)
>>> F.grad.conv2d_input(input.shape, weight, grad_output)
"""
input = grad_output.new_empty(1).expand(input_size)
return torch.ops.aten.convolution_backward(
grad_output,
input,
weight,
None,
_pair(stride),
_pair(padding),
_pair(dilation),
False,
[0],
groups,
(True, False, False),
)[0]
def conv2d_weight(
input,
weight_size,
grad_output,
stride=1,
padding=0,
dilation=1,
groups=1,
):
r"""Compute the gradient of conv2d with respect to the weight of the convolution.
Args:
input: input tensor of shape (minibatch x in_channels x iH x iW)
weight_size : Shape of the weight gradient tensor
grad_output : output gradient tensor (minibatch x out_channels x oH x oW)
stride (int or tuple, optional): Stride of the convolution. Default: 1
padding (int or tuple, optional): Zero-padding added to both sides of the input. Default: 0
dilation (int or tuple, optional): Spacing between kernel elements. Default: 1
groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1
Examples::
>>> input = torch.randn(1, 1, 3, 3, requires_grad=True)
>>> weight = torch.randn(1, 1, 1, 2, requires_grad=True)
>>> output = F.conv2d(input, weight)
>>> grad_output = torch.randn(output.shape)
>>> # xdoctest: +SKIP
>>> grad_weight = torch.autograd.grad(output, filter, grad_output)
>>> F.grad.conv2d_weight(input, weight.shape, grad_output)
"""
weight = grad_output.new_empty(1).expand(weight_size)
return torch.ops.aten.convolution_backward(
grad_output,
input,
weight,
None,
_pair(stride),
_pair(padding),
_pair(dilation),
False,
[0],
groups,
(False, True, False),
)[1]
def conv3d_input(
input_size,
weight,
grad_output,
stride=1,
padding=0,
dilation=1,
groups=1,
):
r"""Compute the gradient of conv3d with respect to the input of the convolution.
This is same as the 3D transposed convolution operator under the hood but requires
the shape of the gradient w.r.t. input to be specified explicitly.
Args:
input_size : Shape of the input gradient tensor
weight: weights tensor (out_channels x in_channels/groups x kT x kH x kW)
grad_output : output gradient tensor (minibatch x out_channels x oT x oH x oW)
stride (int or tuple, optional): Stride of the convolution. Default: 1
padding (int or tuple, optional): Zero-padding added to both sides of the input. Default: 0
dilation (int or tuple, optional): Spacing between kernel elements. Default: 1
groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1
Examples::
>>> input = torch.randn(2, 8, 10, 10, 20, requires_grad=True)
>>> weight = torch.randn(4, 8, 2, 3, 3, requires_grad=True)
>>> output = F.conv3d(input, weight)
>>> grad_output = torch.randn(output.shape)
>>> grad_input = torch.autograd.grad(output, input, grad_output)
>>> F.grad.conv3d_input(input.shape, weight, grad_output)
"""
input = grad_output.new_empty(1).expand(input_size)
return torch.ops.aten.convolution_backward(
grad_output,
input,
weight,
None,
_triple(stride),
_triple(padding),
_triple(dilation),
False,
[0],
groups,
(True, False, False),
)[0]
def conv3d_weight(
input,
weight_size,
grad_output,
stride=1,
padding=0,
dilation=1,
groups=1,
):
r"""Compute the gradient of conv3d with respect to the weight of the convolution.
Args:
input: input tensor of shape (minibatch x in_channels x iT x iH x iW)
weight_size : Shape of the weight gradient tensor
grad_output : output gradient tensor (minibatch x out_channels x oT x oH x oW)
stride (int or tuple, optional): Stride of the convolution. Default: 1
padding (int or tuple, optional): Zero-padding added to both sides of the input. Default: 0
dilation (int or tuple, optional): Spacing between kernel elements. Default: 1
groups (int, optional): Number of blocked connections from input channels to output channels. Default: 1
Examples::
>>> input = torch.randn(2, 8, 10, 10, 20, requires_grad=True)
>>> weight = torch.randn(4, 8, 2, 3, 3, requires_grad=True)
>>> output = F.conv3d(input, weight)
>>> grad_output = torch.randn(output.shape)
>>> grad_weight = torch.autograd.grad(output, weight, grad_output)
>>> F.grad.conv3d_weight(input, weight.shape, grad_output)
"""
weight = grad_output.new_empty(1).expand(weight_size)
return torch.ops.aten.convolution_backward(
grad_output,
input,
weight,
None,
_triple(stride),
_triple(padding),
_triple(dilation),
False,
[0],
groups,
(False, True, False),
)[1]
|