o )i; @shddlmZddlmZmZmZmZmZddlZddlm Z m Z ddl m Z ddlmZmZddlmZdd lmZdd lmZd d lmZmZmZd d lmZd dlmZmZgdZ Gddde j!Z"Gddde j#Z$GdddZ%Gddde j#Z&dee%de'deede(dede&f ddZ)d ed!d"d#Z*Gd$d%d%eZ+Gd&d'd'eZ,Gd(d)d)eZ-Gd*d+d+eZ.eed,e+j/fd-dd.d/dee+de(dede&fd0d1Z0eed,e,j/fd-dd.d/dee,de(dede&fd2d3Z1eed,e-j/fd-dd.d/dee-de(dede&fd4d5Z2eed,e.j/fd-dd.d/dee.de(dede&fd6d7Z3dS)8)partial)AnyCallableListOptionalSequenceN)nnTensor) functional)Conv2dNormActivationPermute)StochasticDepth)ImageClassification)_log_api_usage_once)register_modelWeights WeightsEnum)_IMAGENET_CATEGORIES)_ovewrite_named_paramhandle_legacy_interface) ConvNeXtConvNeXt_Tiny_WeightsConvNeXt_Small_WeightsConvNeXt_Base_WeightsConvNeXt_Large_Weights convnext_tinyconvnext_small convnext_baseconvnext_largec@seZdZdedefddZdS) LayerNorm2dxreturncCs>|dddd}t||j|j|j|j}|dddd}|S)Nrr r)ZpermuteFZ layer_normZnormalized_shapeweightbiasepsselfr"r+j/var/www/html/eduruby.in/lip-sync/lip-sync-env/lib/python3.10/site-packages/torchvision/models/convnext.pyforwardszLayerNorm2d.forwardN)__name__ __module__ __qualname__r r-r+r+r+r,r!sr!c sReZdZ d dededeedejfddffdd Zd e de fd d Z Z S) CNBlockN layer_scalestochastic_depth_prob norm_layer.r#c st|durttjdd}ttj||dd|ddtgd||tj|d|dd t tjd||dd tgd |_ t t |d d ||_t|d |_dS) Nư>r(r$T) kernel_sizepaddinggroupsr')rr r$r)Z in_featuresZ out_featuresr')rr$rr rrow)super__init__rr LayerNorm SequentialConv2dr LinearZGELUblock ParametertorchZonesr2rstochastic_depth)r*dimr2r3r4 __class__r+r,r>'s    zCNBlock.__init__inputcCs&|j||}||}||7}|SN)r2rCrF)r*rJresultr+r+r,r->s zCNBlock.forwardrK) r.r/r0floatrrrModuler>r r- __classcell__r+r+rHr,r1&sr1c@s8eZdZdedeededdfddZdefdd ZdS) CNBlockConfiginput_channels out_channels num_layersr#NcCs||_||_||_dSrK)rQrRrS)r*rQrRrSr+r+r,r>Gs zCNBlockConfig.__init__cCs>|jjd}|d7}|d7}|d7}|d7}|jdi|jS)N(zinput_channels={input_channels}z, out_channels={out_channels}z, num_layers={num_layers})r+)rIr.format__dict__)r*sr+r+r,__repr__Qs zCNBlockConfig.__repr__)r.r/r0intrr>strrYr+r+r+r,rPEs  rPcseZdZ     ddeedededed eed e j fd eed e j fd e d dffdd Z de d e fddZde d e fddZZS)rr5N block_settingr3r2 num_classesrC.r4kwargsr#c stt||stdt|trtdd|Ds!td|dur't}|dur1t t dd}g}|dj } | t d| d d d|dd d td d |D} d} |D]D} g} t| jD]}|| | d}| || j ||| d7} q]| tj| | jdur| t|| j tj| j | jdddqTtj||_td|_|d}|jdur|jn|j }t||tdt|||_|D] }t|tjtjfrtjj|jdd|jdurtj |jqdS)Nz%The block_setting should not be emptycSsg|]}t|tqSr+) isinstancerP).0rXr+r+r, jsz%ConvNeXt.__init__..z/The block_setting should be List[CNBlockConfig]r5r6rr$r;T)r8strider9r4Zactivation_layerr'css|]}|jVqdSrK)rS)rbcnfr+r+r, sz$ConvNeXt.__init__..g?rr )r8rdg{Gz?)Zstd)!r=r>r ValueErrorrarall TypeErrorr1rr!rQappendr sumrangerSrr@rRrAfeaturesZAdaptiveAvgPool2davgpoolZFlattenrB classifiermodulesinitZ trunc_normal_r&r'Zzeros_)r*r^r3r2r_rCr4r`ZlayersZfirstconv_output_channelsZtotal_stage_blocksZstage_block_idreZstage_Zsd_probZ lastblockZlastconv_output_channelsmrHr+r,r>[sp          zConvNeXt.__init__r"cCs"||}||}||}|SrK)rnrorpr)r+r+r, _forward_impls   zConvNeXt._forward_implcCs ||SrK)rur)r+r+r,r-s zConvNeXt.forward)r\r5r]NN)r.r/r0rrPrMrZrrrrNrr>r rur-rOr+r+rHr,rZs2 Nrr^r3weightsprogressr`r#cKsR|durt|dt|jdt|fd|i|}|dur'||j|dd|S)Nr_ categoriesr3T)rwZ check_hash)rlenmetarZload_state_dictZget_state_dict)r^r3rvrwr`modelr+r+r, _convnexts r|) r}zNhttps://github.com/pytorch/vision/tree/main/references/classification#convnexta These weights improve upon the results of the original paper by using a modified version of TorchVision's `new training recipe `_. )Zmin_sizerxZrecipeZ_docsc @DeZdZedeedddieddddd id d d d ZeZdS)rz>https://download.pytorch.org/models/convnext_tiny-983f1562.pthZ crop_sizeZ resize_sizeiH< ImageNet-1KgzGT@gMbX X@zacc@1zacc@5gm@gV-G[@Z num_paramsZ_metricsZ_ops _file_sizeurlZ transformsrzN r.r/r0rrr _COMMON_META IMAGENET1K_V1DEFAULTr+r+r+r,r$ rc @r~)rz?https://download.pytorch.org/models/convnext_small-0c510722.pthrriHZrgClT@g)X@rg|?5^!@g"~g@rrNrr+r+r+r,rrrc @r~)rz>https://download.pytorch.org/models/convnext_base-6075fbad.pthrrihGrgU@gHz7X@rg(\µ.@g/$!u@rrNrr+r+r+r,rrrc @r~)rz?https://download.pytorch.org/models/convnext_large-ea097f82.pthrrri rg"~U@gX9v>X@rg|?5.A@gK@rrNrr+r+r+r,r rrZ pretrained)rvT)rvrwcKXt|}tdddtdddtdddtdddg}|dd }t||||fi|S) aConvNeXt Tiny model architecture from the `A ConvNet for the 2020s `_ paper. Args: weights (:class:`~torchvision.models.convnext.ConvNeXt_Tiny_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.convnext.ConvNeXt_Tiny_Weights` below for more details and possible values. By default, no pre-trained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to the ``torchvision.models.convnext.ConvNext`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.ConvNeXt_Tiny_Weights :members: `r$ Nr3g?)rverifyrPpopr|rvrwr`r^r3r+r+r,r!      rcKr) aConvNeXt Small model architecture from the `A ConvNet for the 2020s `_ paper. Args: weights (:class:`~torchvision.models.convnext.ConvNeXt_Small_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.convnext.ConvNeXt_Small_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.convnext.ConvNext`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.ConvNeXt_Small_Weights :members: rrr$rrNr3g?)rrrPrr|rr+r+r,r@      rcKr) aConvNeXt Base model architecture from the `A ConvNet for the 2020s `_ paper. Args: weights (:class:`~torchvision.models.convnext.ConvNeXt_Base_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.convnext.ConvNeXt_Base_Weights` below for more details and possible values. By default, no pre-trained weights are used. progress (bool, optional): If True, displays a progress bar of the download to stderr. Default is True. **kwargs: parameters passed to the ``torchvision.models.convnext.ConvNext`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.ConvNeXt_Base_Weights :members: r$iirNr3?)rrrPrr|rr+r+r,rarrcKr) aConvNeXt Large model architecture from the `A ConvNet for the 2020s `_ paper. Args: weights (:class:`~torchvision.models.convnext.ConvNeXt_Large_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.convnext.ConvNeXt_Large_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.convnext.ConvNext`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.ConvNeXt_Large_Weights :members: rrr$rirNr3r)rrrPrr|rr+r+r,r rr )4 functoolsrtypingrrrrrrErr Ztorch.nnr r%Zops.miscr r Zops.stochastic_depthrZtransforms._presetsrutilsrZ_apirrr_metar_utilsrr__all__r?r!rNr1rPrrMboolr|rrrrrrrrrr r+r+r+r,s       Y  **