Shortcuts

mmedit.models.base_archs.conv2d_gradfix

Custom replacement for torch.nn.functional.conv2d that supports arbitrarily high order gradients with zero performance penalty.

Module Contents

Functions

no_weight_gradients([disable])

conv2d(input, weight[, bias, stride, padding, ...])

conv_transpose2d(input, weight[, bias, stride, ...])

_should_use_custom_op(input)

_tuple_of_ints(xs, ndim)

_conv2d_gradfix(transpose, weight_shape, stride, ...)

Attributes

enabled

weight_gradients_disabled

_conv2d_gradfix_cache

_null_tensor

mmedit.models.base_archs.conv2d_gradfix.enabled = True[source]
mmedit.models.base_archs.conv2d_gradfix.weight_gradients_disabled = False[source]
mmedit.models.base_archs.conv2d_gradfix.no_weight_gradients(disable=True)[source]
mmedit.models.base_archs.conv2d_gradfix.conv2d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1)[source]
mmedit.models.base_archs.conv2d_gradfix.conv_transpose2d(input, weight, bias=None, stride=1, padding=0, output_padding=0, groups=1, dilation=1)[source]
mmedit.models.base_archs.conv2d_gradfix._should_use_custom_op(input)[source]
mmedit.models.base_archs.conv2d_gradfix._tuple_of_ints(xs, ndim)[source]
mmedit.models.base_archs.conv2d_gradfix._conv2d_gradfix_cache[source]
mmedit.models.base_archs.conv2d_gradfix._null_tensor[source]
mmedit.models.base_archs.conv2d_gradfix._conv2d_gradfix(transpose, weight_shape, stride, padding, output_padding, dilation, groups)[source]
Read the Docs v: latest
Versions
master
latest
stable
zyh-re-docs
zyh-doc-notfound-extend
zyh-api-rendering
Downloads
pdf
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.