Ei
S SK Jr S SKJrJrJrJr S SKrS SKJ r S SKJ
r
SSK J r SSK
Jr SS KJrJrJr SS
KJr SS KJrJr / S QrSES
\S\S\S\S\S\ R4 4 S jjrSFS
\S\S\S\ R4 4S jjr " S S\ R: 5 r " S S\ R: 5 r " S S\ R: 5 r S\!\\ \ 4 S \"\ S \\ S \#S \S\ 4 S jr$S!\S".r% " S# S$\5 r& " S% S&\5 r' " S' S(\5 r( " S) S*\5 r) " S+ S,\5 r* " S- S.\5 r+ " S/ S0\5 r, " S1 S2\5 r- " S3 S4\5 r. " S5 S6\5 r/\" 5 \" S7\&R` 4S89SS9S:.S \\& S \#S \S\ 4S; jj5 5 r1\" 5 \" S7\'R` 4S89SS9S:.S \\' S \#S \S\ 4S< jj5 5 r2\" 5 \" S7\(R` 4S89SS9S:.S \\( S \#S \S\ 4S= jj5 5 r3\" 5 \" S7\)R` 4S89SS9S:.S \\) S \#S \S\ 4S> jj5 5 r4\" 5 \" S7\*R` 4S89SS9S:.S \\* S \#S \S\ 4S? jj5 5 r5\" 5 \" S7\+R` 4S89SS9S:.S \\+ S \#S \S\ 4S@ jj5 5 r6\" 5 \" S7\,R` 4S89SS9S:.S \\, S \#S \S\ 4SA jj5 5 r7\" 5 \" S7\-R` 4S89SS9S:.S \\- S \#S \S\ 4SB jj5 5 r8\" 5 \" S7\.R` 4S89SS9S:.S \\. S \#S \S\ 4SC jj5 5 r9\" 5 \" S7\/R` 4S89SS9S:.S \\/ S \#S \S\ 4SD jj5 5 r:g)G )partial)AnyCallableOptionalUnionN)Tensor )ImageClassification)_log_api_usage_once )register_modelWeights WeightsEnum)_IMAGENET_CATEGORIES)_ovewrite_named_paramhandle_legacy_interface)ResNetResNet18_WeightsResNet34_WeightsResNet50_WeightsResNet101_WeightsResNet152_WeightsResNeXt50_32X4D_WeightsResNeXt101_32X8D_WeightsResNeXt101_64X4D_WeightsWide_ResNet50_2_WeightsWide_ResNet101_2_Weightsresnet18resnet34resnet50 resnet101 resnet152resnext50_32x4dresnext101_32x8dresnext101_64x4dwide_resnet50_2wide_resnet101_2 in_planes
out_planesstridegroupsdilationreturnc 8 [ R " U USUUUSUS9$ )z 3x3 convolution with padding F) kernel_sizer* paddingr+ biasr, nnConv2d)r( r) r* r+ r, s V/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/models/resnet.pyconv3x3r7 ( s+
99
c 0 [ R " XSUSS9$ )z1x1 convolutionr F)r0 r* r2 r3 )r( r) r* s r6 conv1x1r: 6 s
99Y&u UUr8 c ^ \ rS rSr% Sr\\S' SS\S\S\S\\R S \S
\S \S \\
S
\R 4 SS4U 4S jjjr S\ S\ 4S jr
SrU =r$ )
BasicBlock; r expansionNinplanesplanesr*
downsampler+
base_widthr,
norm_layer.r- c X > [ T U ] 5 Uc [ R nUS:w d US:w a [ S5 eUS: a [ S5 e[
XU5 U l U" U5 U l [ R " SS9U l
[
X"5 U l U" U5 U l X@l
X0l g )Nr @ z3BasicBlock only supports groups=1 and base_width=64z(Dilation > 1 not supported in BasicBlockTinplace)super__init__r4 BatchNorm2d
ValueErrorNotImplementedErrorr7 conv1bn1ReLUreluconv2bn2rA r* )
selfr? r@ r* rA r+ rB r, rC __class__s
r6 rI BasicBlock.__init__> s J Q;** RS S a<%&PQ Q Xv6
f%GGD) V,
f%$ r8 xc UnU R U5 nU R U5 nU R U5 nU R U5 nU R U5 nU R
b U R U5 nX2-
nU R U5 nU$ N)rM rN rP rQ rR rA rS rV identityouts r6 forwardBasicBlock.forwardY sy jjmhhsmiinjjohhsm ?? &q)H iin
r8 )rN rR rM rQ rA rP r* r Nr rE r N__name__
__module__ __qualname____firstlineno__r> int__annotations__r r4 Moduler rI r r\ __static_attributes__
__classcell__rT s @r6 r< r< ; s Is *. 9=
RYY'
Xc299n 56
6 F r8 r< c ^ \ rS rSr% Sr\\S' SS\S\S\S\\R S \S
\S \S \\
S
\R 4 SS4U 4S jjjr S\ S\ 4S jr
SrU =r$ )
Bottleneckl r> Nr? r@ r* rA r+ rB r, rC .r- c > [ T
U ] 5 Uc [ R n[ X&S- - 5 U- n [ X5 U l U" U 5 U l [ XX5U5 U l U" U 5 U l
[ XU R - 5 U l U" X R - 5 U l
[ R " SS9U l X@l X0l g )Ng P@TrF )rH rI r4 rJ rd r: rM rN r7 rQ rR r> conv3bn3rO rP rA r* ) rS r? r@ r* rA r+ rB r, rC widthrT s r6 rI Bottleneck.__init__u s JF4 /01F: X-
e$ U68D
e$ UT^^$;<
f~~ 56GGD) $ r8 rV c UnU R U5 nU R U5 nU R U5 nU R U5 nU R U5 nU R U5 nU R U5 nU R
U5 nU R b U R U5 nX2-
nU R U5 nU$ rX )rM rN rP rQ rR ro rp rA rY s r6 r\ Bottleneck.forward s jjmhhsmiinjjohhsmiinjjohhsm ?? &q)H iin
r8 ) rN rR rp rM rQ ro rA rP r* r^ r_ ri s @r6 rk rk l s Is *. 9=
RYY'
Xc299n 56
4 F r8 rk c ^ \ rS rSr SS\\\\4 S\\ S\ S\
S\ S\ S \ \\
S
\ \ S \
R 4 S S4U 4S
jjjr SS\\\\4 S\ S\ S\ S\
S \
R 4 S jjrS\S \4S jrS\S \4S jrSrU =r$ )r Nblocklayers num_classeszero_init_residualr+ width_per_group replace_stride_with_dilationrC .r- c > [ T
U ] 5 [ U 5 Uc [ R nXl SU l SU l Uc / SQn[ U5 S:w a [ SU 35 eXPl
X`l [ R " SU R SSSSS 9U l
U" U R 5 U l [ R " S
S 9U l [ R" " SSSS 9U l U R' USUS
5 U l U R' USUS SUS
S9U l U R' USUS SUS S9U l U R' USUS SUS S9U l [ R0 " S5 U l [ R4 " SUR6 - U5 U l U R; 5 H n [= U [ R 5 ( a+ [ R> RA U RB SSS9 MM [= U [ R [ RD 45 ( d M~ [ R> RG U RB S5 [ R> RG U RH S
5 M U( a U R; 5 H n [= U [J 5 ( aM U RL RB b6 [ R> RG U RL RB S
5 Me [= U [N 5 ( d M| U RP RB c M [ R> RG U RP RB S
5 M g g )NrE r )FFFr/ zFreplace_stride_with_dilation should be None or a 3-element tuple, got r F)r0 r* r1 r2 TrF )r0 r* r1 r )r* dilate i r r fan_outrP )mode nonlinearity))rH rI r r4 rJ _norm_layerr? r, lenrK r+ rB r5 rM rN rO rP MaxPool2dmaxpool _make_layerlayer1layer2layer3layer4AdaptiveAvgPool2davgpoolLinearr> fcmodules
isinstanceinitkaiming_normal_weight GroupNorm constant_r2 rk rp r< rR ) rS rw rx ry rz r+ r{ r| rC mrT s r6 rI ResNet.__init__ s D! J%
' / ,A ( + , 1 --I,JL
)YYq$--QqRSZ_`
dmm,GGD) ||!QG &&ub&)< &&uc6!9QOklmOn&o &&uc6!9QOklmOn&o &&uc6!9QOklmOn&o ++F3 ))C%// 1;? A!RYY''''yv'VA =>>!!!((A.!!!&&!, \\^ a,, 1IGG%%aeellA6 :..155<<3KGG%%aeellA6 $ r8 r@ blocksr* r c U R nS nU R nU( a U =R U- sl SnUS:w d U R X!R - :w aJ [ R
" [
U R X!R - U5 U" X!R - 5 5 n/ n U R U" U R X$XpR U R X5 5 X!R - U l [ SU5 HE n
U R U" U R UU R U R U R US95 MG [ R
" U 6 $ )Nr )r+ rB r, rC ) r r, r? r> r4
Sequentialr: appendr+ rB range) rS rw r@ r r* r rC rA previous_dilationrx _s r6 r ResNet._make_layer s %%
MM MMV #MF Q;$--6OO+CC
v'?H6OO34J
vz;;Yj
0
q&!A MMMM ;; # !]] )
" }}f%%r8 rV c U R U5 nU R U5 nU R U5 nU R U5 nU R U5 nU R U5 nU R
U5 nU R U5 nU R U5 n[ R " US5 nU R U5 nU$ )Nr ) rM rN rP r r r r r r torchflattenr rS rV s r6
_forward_implResNet._forward_impl
s JJqM HHQK IIaL LLO KKN KKN KKN KKN LLO MM!Q GGAJr8 c $ U R U5 $ rX )r r s r6 r\ ResNet.forward s !!!$$r8 )r r rB rN rM r, r r+ r? r r r r r rP )i Fr rE NN)r F)r` ra rb rc typer r< rk listrd boolr r r4 rf rI r r r r r\ rg rh ri s @r6 r r s.
#( !=A9=87E*j01287 S 87 87
! 87
87 87 '/tDz&:87 Xc299n 5687
87 87~
'&E*j012'& '& '&
'&
'&
'&Rv & $% %F % %r8 r rw rx weightsprogresskwargsc Ub# [ US[ UR S 5 5 [ X40 UD6nUb UR UR USS95 U$ )Nry
categoriesT)r
check_hash)r r metar load_state_dictget_state_dict)rw rx r r r models r6 _resnetr s] fmS l9S5TU 5 +F +E
g 4 4hSW 4 XY Lr8 r )min_sizer c R \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\r Sr
g)r i8 z9https://download.pytorch.org/models/resnet18-f37072fd.pth crop_sizei(^ Lhttps://github.com/pytorch/vision/tree/main/references/classification#resnet ImageNet-1KgnpQ@gEDV@zacc@1zacc@5g/$?gS㥛TF@XThese weights reproduce closely the results of the paper using a simple training recipe.
num_paramsrecipe_metrics_ops
_file_size_docsurl
transformsr N r` ra rb rc r r r
_COMMON_META
IMAGENET1K_V1DEFAULTrg r r8 r6 r r 8 W G.#>
"d # # s
M$ Gr8 r c R \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\r Sr
g)r iN z9https://download.pytorch.org/models/resnet34-b627a593.pthr r i(Lr r gjtTR@g{GV@r g Zd;O
@gT@r r r r Nr r r8 r6 r r N r r8 r c \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\" S\" \SSS90 \ESSSSSS
.0S SSS.ES9r \ r
Sr g)r id z9https://download.pytorch.org/models/resnet50-0676ba61.pthr r i(r r g QS@gI +7W@r gB`"[@gDlqX@r r r z9https://download.pytorch.org/models/resnet50-11ad3fa6.pth r resize_sizezEhttps://github.com/pytorch/vision/issues/3995#issuecomment-1013906621gx6T@gW@g(\rX@
These weights improve upon the results of the original paper by using TorchVision's `new training recipe
`_.
r N r` ra rb rc r r r
r r
IMAGENET1K_V2r rg r r8 r6 r r d s G.#>
"d # # s
M$ G.#3O
"] # #
M* Gr8 r c \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\" S\" \SSS90 \ESSSSSS
.0S SSS.ES9r \ r
Sr g)r i z:https://download.pytorch.org/models/resnet101-63fe2227.pthr r i(ħr r g-WS@gmbW@r gNbX94 @g1 ZPe@r r r z:https://download.pytorch.org/models/resnet101-cd907fc2.pthr r 8https://github.com/pytorch/vision/issues/3995#new-recipegbX9xT@gR W@g)\Pe@r r Nr r r8 r6 r r s H.#>
"d # # !s
M$ H.#3O
"P # #
M* Gr8 r c \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\" S\" \SSS90 \ESSSSSS
.0S SSS.ES9r \ r
Sr g)r i z:https://download.pytorch.org/models/resnet152-394f9c45.pthr r i(xr r gS@gmW@r gI +'@gSl@r r r z:https://download.pytorch.org/models/resnet152-f82ba261.pthr r r gV-T@g㥛 X@gI +l@r r Nr r r8 r6 r r s H.#>
"d # # !s
M$ H.#3O
"P # # !
M* Gr8 r c \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\" S\" \SSS90 \ESSSSSS
.0S SSS.ES9r \ r
Sr g)r i z@https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pthr r i(}Mhttps://github.com/pytorch/vision/tree/main/references/classification#resnextr gd;OgS@g&1lW@r gQ @g"~W@r r r z@https://download.pytorch.org/models/resnext50_32x4d-1a0047aa.pthr r r g&1LT@g(\W@gZd;OW@r r Nr r r8 r6 r r s N.#>
"e # # s
M$ N.#3O
"P # #
M* Gr8 r c \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\" S\" \SSS90 \ESSSSSS
.0S SSS.ES9r \ r
Sr g)r i zAhttps://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pthr r i(Jr r gS@glW@r gDli0@gL7A`9u@r r r zAhttps://download.pytorch.org/models/resnext101_32x8d-110c445d.pthr r Dhttps://github.com/pytorch/vision/issues/3995#new-recipe-with-fixresgL7A`T@g;OX@gT㥛:u@r r Nr r r8 r6 r r s O.#>
"e # # !s
M$ O.#3O
"\ # # !
M* Gr8 r c T \ rS rSr\" S\" \SSS90 \ESSSS S
S .0S S
SS.ES9r\r Sr
g)r i; zAhttps://download.pytorch.org/models/resnext101_64x4d-173b62eb.pthr r r i(mz+https://github.com/pytorch/vision/pull/5935r g9vT@gV X@r gQ .@g +s@z
These weights were trained from scratch by using TorchVision's `new training recipe
`_.
r r r Nr r r8 r6 r r ; s[ O.#3O
"C # # !
M* Gr8 r c \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\" S\" \SSS90 \ESSSSSS
.0S SSS.ES9r \ r
Sr g)r iT z@https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pthr r i(:https://github.com/pytorch/vision/pull/912#issue-445437439r gˡES@g/$W@r g&@g
ףp=z`@r r r z@https://download.pytorch.org/models/wide_resnet50_2-9ba9bcbe.pthr r r gJ +fT@gnW@gDlqp@r r Nr r r8 r6 r r T s N.#>
"R # # s
M$ N.#3O
"\ # # !
M* Gr8 r c \ rS rSr\" S\" \SS90 \ESSSSS S
.0S S S
S.ES9r\" S\" \SSS90 \ESSSSSS
.0S SSS.ES9r \ r
Sr g)r i zAhttps://download.pytorch.org/models/wide_resnet101_2-32ee1156.pthr r i(#r r gʡES@gV-W@r gT㥛6@g&1\n@r r r zAhttps://download.pytorch.org/models/wide_resnet101_2-d733dc28.pthr r r gq=
ףT@gzGX@gˡEK~@r r Nr r r8 r6 r r s O.#>
#R # # !s
M$ O.#3O
#P # # !
M* Gr8 r
pretrained)r T)r r c T [ R U 5 n [ [ / SQX40 UD6$ )a4 ResNet-18 from `Deep Residual Learning for Image Recognition `__.
Args:
weights (:class:`~torchvision.models.ResNet18_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.ResNet18_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.ResNet18_Weights
:members:
)r r r r )r verifyr r< r r r s r6 r r ( * %%g.G :|W I& IIr8 c T [ R U 5 n [ [ / SQX40 UD6$ )a4 ResNet-34 from `Deep Residual Learning for Image Recognition `__.
Args:
weights (:class:`~torchvision.models.ResNet34_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.ResNet34_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.ResNet34_Weights
:members:
r/ rm r/ )r r r r< r s r6 r r r r8 c T [ R U 5 n [ [ / SQX40 UD6$ )a ResNet-50 from `Deep Residual Learning for Image Recognition `__.
.. note::
The bottleneck of TorchVision places the stride for downsampling to the second 3x3
convolution while the original paper places it to the first 1x1 convolution.
This variant improves the accuracy and is known as `ResNet V1.5
`_.
Args:
weights (:class:`~torchvision.models.ResNet50_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.ResNet50_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.ResNet50_Weights
:members:
r )r r r rk r s r6 r r s( 6 %%g.G :|W I& IIr8 c T [ R U 5 n [ [ / SQX40 UD6$ )a ResNet-101 from `Deep Residual Learning for Image Recognition `__.
.. note::
The bottleneck of TorchVision places the stride for downsampling to the second 3x3
convolution while the original paper places it to the first 1x1 convolution.
This variant improves the accuracy and is known as `ResNet V1.5
`_.
Args:
weights (:class:`~torchvision.models.ResNet101_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.ResNet101_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.ResNet101_Weights
:members:
r/ rm r/ )r r r rk r s r6 r! r! ( 6 &&w/G :}g J6 JJr8 c T [ R U 5 n [ [ / SQX40 UD6$ )a ResNet-152 from `Deep Residual Learning for Image Recognition `__.
.. note::
The bottleneck of TorchVision places the stride for downsampling to the second 3x3
convolution while the original paper places it to the first 1x1 convolution.
This variant improves the accuracy and is known as `ResNet V1.5
`_.
Args:
weights (:class:`~torchvision.models.ResNet152_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.ResNet152_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.ResNet152_Weights
:members:
)r/ $ r/ )r r r rk r s r6 r" r" r r8 c [ R U 5 n [ USS5 [ USS5 [ [ / SQX40 UD6$ )ac ResNeXt-50 32x4d model from
`Aggregated Residual Transformation for Deep Neural Networks `_.
Args:
weights (:class:`~torchvision.models.ResNeXt50_32X4D_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.ResNext50_32X4D_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.ResNeXt50_32X4D_Weights
:members:
r+ r{ rm r )r r r r rk r s r6 r# r# > sA . &,,W5G&(B/&"3Q7 :|W I& IIr8 c [ R U 5 n [ USS5 [ USS5 [ [ / SQX40 UD6$ )ag ResNeXt-101 32x8d model from
`Aggregated Residual Transformation for Deep Neural Networks `_.
Args:
weights (:class:`~torchvision.models.ResNeXt101_32X8D_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.ResNeXt101_32X8D_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.ResNeXt101_32X8D_Weights
:members:
r+ r r{ r r )r r r r rk r s r6 r$ r$ \ A . '--g6G&(B/&"3Q7 :}g J6 JJr8 c [ R U 5 n [ USS5 [ USS5 [ [ / SQX40 UD6$ )ag ResNeXt-101 64x4d model from
`Aggregated Residual Transformation for Deep Neural Networks `_.
Args:
weights (:class:`~torchvision.models.ResNeXt101_64X4D_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.ResNeXt101_64X4D_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.ResNeXt101_64X4D_Weights
:members:
r+ rE r{ rm r )r r r r rk r s r6 r% r% z r r8 c n [ R U 5 n [ USS5 [ [ / SQX40 UD6$ )aU Wide ResNet-50-2 model from
`Wide Residual Networks `_.
The model is the same as ResNet except for the bottleneck number of channels
which is twice larger in every block. The number of channels in outer 1x1
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
Args:
weights (:class:`~torchvision.models.Wide_ResNet50_2_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.Wide_ResNet50_2_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.Wide_ResNet50_2_Weights
:members:
r{ r r )r r r r rk r s r6 r& r& s5 8 &,,W5G&"3V< :|W I& IIr8 c n [ R U 5 n [ USS5 [ [ / SQX40 UD6$ )a[ Wide ResNet-101-2 model from
`Wide Residual Networks `_.
The model is the same as ResNet except for the bottleneck number of channels
which is twice larger in every block. The number of channels in outer 1x1
convolutions is the same, e.g. last block in ResNet-101 has 2048-512-2048
channels, and in Wide ResNet-101-2 has 2048-1024-2048.
Args:
weights (:class:`~torchvision.models.Wide_ResNet101_2_Weights`, optional): The
pretrained weights to use. See
:class:`~torchvision.models.Wide_ResNet101_2_Weights` below for
more details, and possible values. By default, no pre-trained
weights are used.
progress (bool, optional): If True, displays a progress bar of the
download to stderr. Default is True.
**kwargs: parameters passed to the ``torchvision.models.resnet.ResNet``
base class. Please refer to the `source code
`_
for more details about this class.
.. autoclass:: torchvision.models.Wide_ResNet101_2_Weights
:members:
r{ r r )r r r r rk r s r6 r' r' s5 8 '--g6G&"3V< :}g J6 JJr8 )r r r )r ); functoolsr typingr r r r r torch.nnr4 r transforms._presetsr
utilsr _apir
r r _metar _utilsr r __all__rd r5 r7 r: rf r< rk r r r r r r r r r r r r r r r r r r r r r! r" r# r$ r% r& r' r r8 r6 r st 1 1 5 ' 6 6 ' B 2 s S c Y\ egenen Vs V VS V V
. .b7 7tw%RYY w%t j*,- . I k
"
& & { , { ,( { ( V( ( V( ( V( k ( V( { ( V { 2( k ( V( { ( V ,0@0N0N!OP6:T J"23 Jd J]` Jek J Q J0 ,0@0N0N!OP6:T J"23 Jd J]` Jek J Q J0 ,0@0N0N!OP6:T J"23 Jd J]` Jek J Q J< ,0A0O0O!PQ8