Ei. * %SSKrSSKJr SSKJr SSKJrJrJr SSK r SSK J r J r SSK J r Jr SSKJrJr SS KJr S S KJrJrJr S S KJr S S KJrJrJr /SQr"SS\ 5r"SS\ R@5r!"SS\ RD5r#"SS\ R@5r$"SS5r%"SS\ RD5r&S\%S\\S\'S\S\&4 S jr(S!\S".r)\*\+\4\,S#'0\)ES$S%S&.Er-"S'S(\5r."S)S*\5r/"S+S,\5r0"S-S.\5r1"S/S0\5r2"S1S2\5r3"S3S4\5r4"S5S6\5r5"S7S8\5r6"S9S:\5r7"S;S<\5r8"S=S>\5r9"S?S@\5r:"SASB\5r;"SCSD\5r<\"5\"SE\.Rz4SF9SSGSH.S\\.S\'S\S\&4SIjj55r>\"5\"SE\/Rz4SF9SSGSH.S\\/S\'S\S\&4SJjj55r?\"5\"SE\0Rz4SF9SSGSH.S\\0S\'S\S\&4SKjj55r@\"5\"SE\1Rz4SF9SSGSH.S\\1S\'S\S\&4SLjj55rA\"5\"SE\2Rz4SF9SSGSH.S\\2S\'S\S\&4SMjj55rB\"5\"SE\3Rz4SF9SSGSH.S\\3S\'S\S\&4SNjj55rC\"5\"SE\4Rz4SF9SSGSH.S\\4S\'S\S\&4SOjj55rD\"5\"SPSF9SSGSH.S\\5S\'S\S\&4SQjj55rE\"5\"SE\6Rz4SF9SSGSH.S\\6S\'S\S\&4SRjj55rF\"5\"SE\7Rz4SF9SSGSH.S\\7S\'S\S\&4SSjj55rG\"5\"SE\8Rz4SF9SSGSH.S\\8S\'S\S\&4STjj55rH\"5\"SE\9Rz4SF9SSGSH.S\\9S\'S\S\&4SUjj55rI\"5\"SE\:Rz4SF9SSGSH.S\\:S\'S\S\&4SVjj55rJ\"5\"SE\;Rz4SF9SSGSH.S\\;S\'S\S\&4SWjj55rK\"5\"SE\[TU]XSSX4S9 g)Nr  kernel_sizestrider<r=)super__init__)selfr:r;r<r= __class__s V/home/mande/repo/quber/.venv/lib/python3.13/site-packages/torchvision/models/regnet.pyrESimpleStemIN.__init__7s   QqZ  ) __name__ __module__ __qualname____firstlineno____doc__intrrModulerE__static_attributes__ __classcell__rGs@rHr8r84sZ2      S"))^,  #3 >2     rJr8c^\rSrSrSrS\S\S\S\S\R4S\S\R4S \S \ S \ \ S S 4U4Sjjr Sr U=r $)BottleneckTransformCz/Bottleneck transformation: 1x1, 3x3 [+SE], 1x1.r:r;rCr<.r= group_widthbottleneck_multiplierse_ratior>Nc >[5n [[X'-55n X-n [XSSXES9U S'[XSX;XES9U S'U(a$[[X-55n [ U U US9U S'[XSSUSS9U S '[ T U]U 5 g) NrrAar@)rBrCgroupsr<r=b)input_channelssqueeze_channels activationsec)rrQroundr r rDrE)rFr:r;rCr<r=rYrZr[layersw_bg width_se_outrGs rHrEBottleneckTransform.__init__Fs/:m% 9:;  * qz s + !F s  uX%89:L,"!-+F4L + ! ]a s   rJrKrLrMrNrOrPrQrrrRfloatrrErSrTrUs@rHrWrWCs9#!#!#! #! S"))^, #! #3 >2 #!#! %#!5/#! #!#!rJrWc^\rSrSrSrSS\S\S\S\S\R4S \S\R4S \S \ S \ \ S S4U4Sjjjr S\ S \ 4Sjr SrU=r$)ResBottleneckBlocklz>Residual bottleneck block: x + F(x), F = bottleneck transform.Nr:r;rCr<.r=rYrZr[r>c >[T U]5 SUlX:g=(d US:gn U (a[XSX4SS9Ul[ UUUUUUUU5UlU"SS9Ulg)NrrAT)inplace)rDrEprojr rWfrb) rFr:r;rCr<r=rYrZr[ should_projrGs rHrEResBottleneckBlock.__init__osw  ,>&A+ ,6koDI%       !   +48rJxcURb$URU5URU5-nOXRU5-nURU5$N)rrrsrbrFrvs rHforwardResBottleneckBlock.forwardsD 99  ! tvvay(AFF1I Aq!!rJ)rbrsrr)r?N)rLrMrNrOrPrQrrrRrlrrEr rzrSrTrUs@rHrnrnlsH'*$(999 9 S"))^, 9 #3 >2 99 %95/9 99@""F""rJrnc^\rSrSrSrSS\S\S\S\S\S \R4S \S \R4S \S \R4S \S \ S\ \ S\SS4U4Sjjjr Sr U=r $)AnyStagez;AnyNet stage (sequence of blocks w/ the same output shape).Nr:r;rCdepthblock_constructor.r<r=rYrZr[ stage_indexr>c >[TU]5 [U5H:n U"U S:XaUOUUU S:XaUOSUUUU U 5n URSU SU 3U 5 M< g)Nrrblock-)rDrErange add_module)rFr:r;rCrrr<r=rYrZr[rirrGs rHrEAnyStage.__init__sm uA%F q&a % E OOeK=!5u =rJrK)NrrkrUs@rHr~r~sE%)>>> >  > $CN3 >S"))^,>#3 >2>> %>5/>> >>rJr~c\rSrSrSS\\S\\S\\S\\S\\S\\S S4S jjr\ SS \S \S \S\S\S\S\\S\ S S4Sjj5r Sr \ S\\S\\S\\S \\\\\44Sj5rSrg) BlockParamsNdepthswidths group_widthsbottleneck_multipliersstridesr[r>cLXlX lX0lX@lXPlX`lgrxrrrrrr[)rFrrrrrr[s rHrEBlockParams.__init__s$  (&<#  rJrw_0w_aw_mrYrZkwargsc VSn Sn US:dUS::dUS::d US-S:wa [S5e[R"U5U-U-n [R"[R"X- 5[ R"U5- 5n [R"[R "U[R"XL5-U 55U -R5R5n [[U 55n[U S/-S/U -U S/-S/U -5nUVVVVs/sHunnnnUU:g=(d UU:gPM nnnnn[U USS5VVs/sHunnU(dMUPM nnn[R"[R"[U5VVs/sHunnU(dMUPM snn55R5R5nU /U-nU/U-nU/U-nUR!UUU5unnU"UUUUUUS9$s snnnnfs snnfs snnf) a Programmatically compute all the per-block settings, given the RegNet parameters. The first step is to compute the quantized linear block parameters, in log space. Key parameters are: - `w_a` is the width progression slope - `w_0` is the initial width - `w_m` is the width stepping in the log space In other terms `log(block_width) = log(w_0) + w_m * block_capacity`, with `bock_capacity` ramping up following the w_0 and w_a params. This block width is finally quantized to multiples of 8. The second step is to compute the parameters per stage, taking into account the skip connection and the final 1x1 convolutions. We use the fact that the output width is constant within a stage. r rrzInvalid RegNet settingsNr) ValueErrortorcharangerelogmathdividepowrQtolistlensetzipdifftensor enumerate"_adjust_widths_groups_compatibilty)clsrrrrrYrZr[rQUANTSTRIDE widths_contblock_capacity block_widths num_stages split_helperwwprrpsplitst stage_widthsd stage_depthsrrrs rHfrom_init_paramsBlockParams.from_init_paramss @ 7cQh#(cAgl67 7ll5)C/#5 UYY{/@%ADHHSM%QR ELLuyy7U1UW\$]^affkkmttv \*+  A3  C,  A3  C,   :FFB2!r'$Q"W$F&),s &DJ&Dda&D Jzz%,,i>O/U>OdaST>O/U"VW[[]ddf (Z'"7!8:!E#}z1 &)%K%K 0,& " l%#9   GJ/Us$ H H-H$H%6H%c[URURURURUR 5$rx)rrrrrr)rFs rH_get_expanded_params BlockParams._get_expanded_paramss-4;; dkk4;L;LdNiNijjrJrbottleneck_ratiosc[X5VVs/sHup4[X4-5PM nnn[X%5VVs/sHupg[Xg5PM nnn[XX5VVs/sHupv[Xv5PM n nn[X5VVs/sHupt[Xt- 5PM nnnX4$s snnfs snnfs snnfs snnf)zT Adjusts the compatibility of widths and groups, depending on the bottleneck ratio. )rrQminr) rrrrr_rrhw_botgroup_widths_minws_bots rHr.BlockParams._adjust_widths_groups_compatibiltys*-\)MN)M#ae*)MN:=l:ST:ShaCM:ST=@c`>[TU]5 [U5 Uc[nUc[R nUc[ nUc[RnU"SUUU5UlUn/n [UR55HEun un n n nnU RSU S-3[UU U U UUUUUURU S-S9 45 U nMG [R"[U 55Ul[R""S5Ul[R&"XS9UlUR+5GHyn[-U[R.5(anUR0SUR0S-UR2-n[R4R7UR8S[:R<"S U- 5S 9 M[-U[R 5(aU[R4R?UR85 [R4RAURB5 GM[-U[R&5(dGM'[R4R7UR8SS S 9 [R4RAURB5 GM| g) Nr@rr)rrr) in_features out_featuresrg@)meanstdg{Gz?)"rDrErr8r BatchNorm2drnReLUstemrrappendr~r[ Sequentialr trunk_outputAdaptiveAvgPool2davgpoolLinearfcmodules isinstanceConv2drB out_channelsinitnormal_weightrsqrtones_zeros_bias)rFrrrrrr<rb current_widthblocksrr;rCrrYrZmfan_outrGs rHrERegNet.__init__)s D!  $I  J  +J  J      # |88: ;  A     ! MMAaC5M%!"""#-$--$%E  &&M)<,MM+f*=>++F3 )) PA!RYY''--*Q]]1-==Ns #-8PQAr~~.. ahh'qvv&Aryy))s=qvv& rJrvcURU5nURU5nURU5nURSS9nUR U5nU$)Nr) start_dim)rrrflattenrrys rHrzRegNet.forwardxsN IIaL   a  LLO III " GGAJrJ)rrrr)i NNNN)rLrMrNrOrrQrrrrRrEr rzrSrTrUs@rHrr(s 8<9=9=9=M'!M'M' M' HS"))^45 M' Xc299n56 M'Xc299n56M'Xc299n56M' M'M'^FrJrrweightsprogressrr>c Ub#[US[URS55 URS[ [ R SSS95n[U4SU0UD6nUbURURUSS95 U$) Nr categoriesr<gh㈵>g?)epsmomentumT)r check_hash) rrmetapoprrrrload_state_dictget_state_dict)rrrrr<models rH_regnetrs fmSl9S5TUL'"..eVY*Z[J < AJ A& AE g44hSW4XY LrJr)min_sizer _COMMON_METAz(https://github.com/facebookresearch/SWAGz:https://github.com/facebookresearch/SWAG/blob/main/LICENSE)recipelicensec \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)riz?https://download.pytorch.org/models/regnet_y_400mf-c65dace8.pth crop_sizeiPIBRhttps://github.com/pytorch/vision/tree/main/references/classification#small-models ImageNet-1KgmR@gV@zacc@1zacc@5g|?5^?guV0@XThese weights reproduce closely the results of the paper using a simple training recipe. num_paramsr_metrics_ops _file_size_docsurl transformsrz?https://download.pytorch.org/models/regnet_y_400mf-e6988f5f.pthr  resize_size8https://github.com/pytorch/vision/issues/3995#new-recipeg~jtR@gsh|/W@$ These weights improve upon the results of the original paper by using a modified version of TorchVision's `new training recipe `_. rKN rLrMrNrOrrr r IMAGENET1K_V1 IMAGENET1K_V2DEFAULTrSrKrJrHrr M.#>    !j##   s  M$ M.#3O  !P##    M,GrJrc \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)riz?https://download.pytorch.org/models/regnet_y_800mf-1b27b58c.pthr r i'br rg{GS@gbX9HW@rg㥛 ?g/$8@rrrz?https://download.pytorch.org/models/regnet_y_800mf-58fc7688.pthrrrgES@g㥛 W@rrKNrrKrJrHrrr#rJrc \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)riz?https://download.pytorch.org/models/regnet_y_1_6gf-b11a554e.pthr r i~r rg|S@g}W@rgn?g~jtE@rrrz?https://download.pytorch.org/models/regnet_y_1_6gf-0d7bc02a.pthrrrgMb8T@g#~jW@rrKNrrKrJrHrrs M.#>    "j##   s  M$ M.#3O  "P##    M,GrJrc \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)ri%z?https://download.pytorch.org/models/regnet_y_3_2gf-b5a9779c.pthr r i2(Shttps://github.com/pytorch/vision/tree/main/references/classification#medium-modelsrg&1S@g/ݤW@rg rh @g?5^IR@rrrz?https://download.pytorch.org/models/regnet_y_3_2gf-9180c971.pthrrrg+~T@g|?5W@rrKNrrKrJrHrr% M.#>    "k##   s  M$ M.#3O  "P##    M,GrJrc \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)riQz=https://download.pytorch.org/models/regnet_y_8gf-d0d0e4a8.pthr r iXr'rg5^I T@gPnW@rgV- @gOnb@rrrz=https://download.pytorch.org/models/regnet_y_8gf-dc2b1b54.pthrrrgET@gQX@rrKNrrKrJrHrrQ K.#>    "k##  !s  M$ K.#3O  "P##  ! M,GrJrc 0\rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \"S\"\SS\ RS90\ ESSSSS .0SS SS.ES9r \"S\"\SS\ RS90\ ES SSS!S"S .0S S S#S$.ES9r\ rS%rg&)'ri}z>https://download.pytorch.org/models/regnet_y_16gf-9e6ed7dd.pthr r i{Rhttps://github.com/pytorch/vision/tree/main/references/classification#large-modelsrgB`"T@g(\W@rgm/@gp= s@rrrz>https://download.pytorch.org/models/regnet_y_16gf-3e4a00f9.pthrrrgbX9T@gEX@rzChttps://download.pytorch.org/models/regnet_y_16gf_swag-43afe44d.pthr r interpolationgT㥛ĀU@g~jtX@gGz^G@ These weights are learnt via transfer learning by end-to-end fine-tuning the original `SWAG `_ weights on ImageNet-1K data. rrrrrzFhttps://download.pytorch.org/models/regnet_y_16gf_lc_swag-f3ec0043.pth+https://github.com/pytorch/vision/pull/5793gX9vT@gV-OX@ These weights are composed of the original frozen `SWAG `_ trunk weights and a linear classifier learnt on top of them trained on ImageNet-1K data. rrrrrrrKNrLrMrNrOrrr rr r!rBICUBIC_COMMON_SWAG_METAIMAGENET1K_SWAG_E2E_V1IMAGENET1K_SWAG_LINEAR_V1r"rSrKrJrHrr}sh L.#>    "j##   s  M$ L.#3O  "P##    M,% Q 3CO`OhOh   "##    ,!( T 3CO`OhOh   C"##    !.GrJrc 0\rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \"S\"\SS\ RS90\ ESSSSS .0SS SS.ES9r \"S\"\SS\ RS90\ ES SSS!S"S .0S S S#S$.ES9r\ rS%rg&)'riz>https://download.pytorch.org/models/regnet_y_32gf-4dee3f7a.pthr r i<r,rgx&18T@g(\W@rgp= #@@gS㥛P@rrrz>https://download.pytorch.org/models/regnet_y_32gf-8db6d4b5.pthrrrgd;OT@gZd;X@rzChttps://download.pytorch.org/models/regnet_y_32gf_swag-04fdfa75.pthr-r.gʡU@gI +X@g/ݴW@r0r1zFhttps://download.pytorch.org/models/regnet_y_32gf_lc_swag-e1583746.pthr2g+'U@gQ^X@r3r4rKNr5rKrJrHrrsh L.#>    #j##  !s  M$ L.#3O  #P##  ! M,% Q 3CO`OhOh   ###  ! ,!( T 3CO`OhOh   C###  ! !.GrJrc \rSrSr\"S\"\SS\RS90\ ESSSSS .0S S S S .ES9r \"S\"\SS\RS90\ ESSSSSS .0SS SS.ES9r \ r Sr g)r i/zDhttps://download.pytorch.org/models/regnet_y_128gf_swag-c8ce3e52.pthr-r.i^o&rg;OV@gS㥫X@rgQiw@g㥛 ;@r0r1rzGhttps://download.pytorch.org/models/regnet_y_128gf_lc_swag-cbe8ce12.pthr r2g1ZU@gtvX@gx&_@r3r4rKN)rLrMrNrOrrr rr6r7r8r9r"rSrKrJrHr r /s$ R 3CO`OhOh   ###  " ,!( U 3CO`OhOh   C###  " !.%GrJr c \rSrSr\"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/regnet_x_400mf-adf1edd5.pthr r iSr rgL7A`5R@g̼V@rg"~?g5^I B5@rrrz?https://download.pytorch.org/models/regnet_x_400mf-62229a5f.pthrrDhttps://github.com/pytorch/vision/issues/3995#new-recipe-with-fixresgKR@gS㥛W@goA5@rrKNrrKrJrHr!r!` M.#>    !j##   s  M$ M.#3O  !\##    M,GrJr!c \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)r"iz?https://download.pytorch.org/models/regnet_x_800mf-ad17e45c.pthr r inr rg!rhR@gʡEW@rg?gR;@rrrz?https://download.pytorch.org/models/regnet_x_800mf-94a99ebd.pthrrr=g rhaS@g/tW@rrKNrrKrJrHr"r"s M.#>    !j##   s  M$ M.#3O  !\##    M,GrJr"c \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)r#iz?https://download.pytorch.org/models/regnet_x_1_6gf-e3633e7f.pthr r i:r rg(\BS@g\(\W@rgS?gZdA@rrrz?https://download.pytorch.org/models/regnet_x_1_6gf-a12f2b72.pthrrr=gnS@g^I W@rrKNrrKrJrHr#r#r>rJr#c \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)r$iz?https://download.pytorch.org/models/regnet_x_3_2gf-f342aeae.pthr r i(hr'rgKS@gsh|W@rg"~j @gT㥛`M@rrrz?https://download.pytorch.org/models/regnet_x_3_2gf-7071aa85.pthrrrgCLT@gQW@rrKNrrKrJrHr$r$r(rJr$c \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)r%iz=https://download.pytorch.org/models/regnet_x_8gf-03ceed89.pthr r i[r'rgtS@gClW@rg{G@g;Ob@rrrz=https://download.pytorch.org/models/regnet_x_8gf-2b70d774.pthrrrgSkT@gZdW@rrKNrrKrJrHr%r%r*rJr%c \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)r&i<z>https://download.pytorch.org/models/regnet_x_16gf-2007eb11.pthr r i9<r'rgʡET@g#~jW@rgo/@gMbi@rrrz>https://download.pytorch.org/models/regnet_x_16gf-ba3796d7.pthrrrgҭT@gC X@rrKNrrKrJrHr&r&<s L.#>    "k##  !s  M$ L.#3O  "P##  ! M,GrJr&c \rSrSr\"S\"\SS90\ESSSSS S .0S S S S.ES9r\"S\"\SSS90\ESSSSSS .0S S SS.ES9r \ r Sr g)r'ihz>https://download.pytorch.org/models/regnet_x_32gf-9d47f8d0.pthr r imr,rg+'T@gZd;W@rg#~j?@gvy@rrrz>https://download.pytorch.org/models/regnet_x_32gf-6eb8fdc6.pthrrrg7A`T@gOnX@rrKNrrKrJrHr'r'hs L.#>    #j##  !s  M$ L.#3O  #P##  ! M,GrJr' pretrained)rT)rrc [RU5n[R"SSSSSSSS.UD6n[ X0U40UD6$) ah Constructs a RegNetY_400MF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_Y_400MF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_Y_400MF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_Y_400MF_Weights :members: 0gp= ;@gQ@r?rrrrrYr[rK)rverifyrrrrrrparamss rHr(r(sK(%++G4G  ) ) x4]^im xqw xF 6H 7 77rJc [RU5n[R"SSSSSSSS.UD6n[ X0U40UD6$) ah Constructs a RegNetY_800MF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_Y_800MF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_Y_800MF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_Y_800MF_Weights :members: 8gQkC@g333333@rGrIrJrK)rrKrrrrLs rHr)r)sK(%++G4G  ) ) x3\^im xqw xF 6H 7 77rJc [RU5n[R"SSSSSSSS.UD6n[ X0U40UD6$) ah Constructs a RegNetY_1.6GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_Y_1_6GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_Y_1_6GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_Y_1_6GF_Weights :members: rHg(\µ4@g333333@rIrJrK)rrKrrrrLs rHr*r*R(%++G4G  ) )be2PVF 6H 7 77rJc [RU5n[R"SSSSSSSS.UD6n[ X0U40UD6$) ah Constructs a RegNetY_3.2GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_Y_3_2GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_Y_3_2GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_Y_3_2GF_Weights :members: Pgq= ףPE@gHzG@rSrIrJrK)rrKrrrrLs rHr+r+rTrJc [RU5n[R"SSSSSSSS.UD6n[ X0U40UD6$) a` Constructs a RegNetY_8GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_Y_8GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_Y_8GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_Y_8GF_Weights :members: gGz4S@gQ@rPrIrJrK)rrKrrrrLs rHr,r,sR(#))'2G  ) )cu$BQWF 6H 7 77rJc [RU5n[R"SSSSSSSS.UD6n[ X0U40UD6$) ad Constructs a RegNetY_16GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_Y_16GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_Y_16GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_Y_16GF_Weights :members: gQZ@gףp= @prIrJrK)rrKrrrrLs rHr-r-R($**73G  ) )cv4S4SYF 6H 7 77rJc [RU5n[R"SSSSSSSS.UD6n[ X0U40UD6$)ad Constructs a RegNetY_32GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_Y_32GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_Y_32GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_Y_32GF_Weights :members: rg)\\@g= ףp=@rIrJrK)rrKrrrrLs rHr.r.8r_rJ)rENc [RU5n[R"SSSSSSSS.UD6n[ X0U40UD6$) ah Constructs a RegNetY_128GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_Y_128GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_Y_128GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_Y_128GF_Weights :members: rRig(\d@g)\(@irIrJrK)r rKrrrrLs rHr/r/TsR(%++G4G  ) )cv4S4SYF 6H 7 77rJc ~[RU5n[R"SSSSSSS.UD6n[ X0U40UD6$)ah Constructs a RegNetX_400MF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_X_400MF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_X_400MF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_X_400MF_Weights :members: rSg{Gz8@gRQ@rGrrrrrYrK)r!rKrrrrLs rHr0r0pH(%++G4G  ) ) j4]_ jci jF 6H 7 77rJc ~[RU5n[R"SSSSSSS.UD6n[ X0U40UD6$)ah Constructs a RegNetX_800MF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_X_800MF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_X_800MF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_X_800MF_Weights :members: rGrPg= ףpA@g= ףp=@rerK)r"rKrrrrLs rHr1r1rfrJc ~[RU5n[R"SSSSSSS.UD6n[ X0U40UD6$)ah Constructs a RegNetX_1.6GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_X_1_6GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_X_1_6GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_X_1_6GF_Weights :members: r\rWgzGA@@rSrerK)r#rKrrrrLs rHr2r2rfrJc ~[RU5n[R"SSSSSSS.UD6n[ X0U40UD6$)ah Constructs a RegNetX_3.2GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_X_3_2GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_X_3_2GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_X_3_2GF_Weights :members: Xg(\O:@rirHrerK)r$rKrrrrLs rHr3r3rfrJc ~[RU5n[R"SSSSSSS.UD6n[ X0U40UD6$)a` Constructs a RegNetX_8GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_X_8GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_X_8GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_X_8GF_Weights :members: rWgHzH@g ףp= @xrerK)r%rKrrrrLs rHr4r4sH(#))'2G  ) ) k4]` kdj kF 6H 7 77rJc ~[RU5n[R"SSSSSSS.UD6n[ X0U40UD6$)ad Constructs a RegNetX_16GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_X_16GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_X_16GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_X_16GF_Weights :members: rdgQK@g@rerK)r&rKrrrrLs rHr5r5H($**73G  ) ) kC]` kdj kF 6H 7 77rJc ~[RU5n[R"SSSSSSS.UD6n[ X0U40UD6$)ad Constructs a RegNetX_32GF architecture from `Designing Network Design Spaces `_. Args: weights (:class:`~torchvision.models.RegNet_X_32GF_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.RegNet_X_32GF_Weights` below for more details and possible values. By default, no pretrained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to either ``torchvision.models.regnet.RegNet`` or ``torchvision.models.regnet.BlockParams`` class. Please refer to the `source code `_ for more detail about the classes. .. autoclass:: torchvision.models.RegNet_X_32GF_Weights :members: rni@gףp= wQ@rrerK)r'rKrrrrLs rHr6r6 rsrJ)Mr collectionsr functoolsrtypingrrrrrr ops.miscr r transforms._presetsr rutilsr_apirrr_metar_utilsrrr__all__r8rrWrRrnr~rrboolrrdictstr__annotations__r7rrrrrrrr r!r"r#r$r%r&r'r r(r)r*r+r,r-r.r/r0r1r2r3r4r5r6rKrJrHrs( #** >H'66'SS F  '  &!"--&!R("("V>r}}>Dl.l.^XRYYXv k "   &&  d38n 8K)[)X)[)X)[)X)[)X);)XVKVrVKVr.%[.%b)[)X)[)X)[)X)[)X);)X)K)X)K)X,0F0T0T!UVBFY]8x(>?8RV8il8qw8W80,0F0T0T!UVBFY]8x(>?8RV8il8qw8W80,0F0T0T!UVBFY]8x(>?8RV8il8qw8W84,0F0T0T!UVBFY]8x(>?8RV8il8qw8W84,0D0R0R!ST>BUY8X&:;8d8eh8ms8U84,0E0S0S!TU@DW[8h'<=8PT8gj8ou8V84,0E0S0S!TU@DW[8h'<=8PT8gj8ou8V84!56BFY]8x(>?8RV8il8qw8784,0F0T0T!UVBFY]8x(>?8RV8il8qw8W80,0F0T0T!UVBFY]8x(>?8RV8il8qw8W80,0F0T0T!UVBFY]8x(>?8RV8il8qw8W80,0F0T0T!UVBFY]8x(>?8RV8il8qw8W80,0D0R0R!ST>BUY8X&:;8d8eh8ms8U80,0E0S0S!TU@DW[8h'<=8PT8gj8ou8V80,0E0S0S!TU@DW[8h'<=8PT8gj8ou8V8rJ