a PSicl<@sddlmZddlmZmZmZmZddlZddlm Z ddlm Z ddl m Z ddl mZdd lmZmZdd lmZdd lmZmZgd Ze ee d ddZGddde jZGddde jZeeeeeedddZdeddZGdddeZ GdddeZ!GdddeZ"Gd d!d!eZ#ed"e j$fd#dd$d%ee eeed&d'd(Z%ed"e!j$fd#dd$d%ee!eeed&d)d*Z&ed"e"j$fd#dd$d%ee"eeed&d+d,Z'ed"e#j$fd#dd$d%ee#eeed&d-d.Z(dd/lm)Z)e)e j$j*e!j$j*ddd0Z+dS)1)partial)CallableAnyListOptionalN)Tensor)ImageClassification)_log_api_usage_once) WeightsEnumWeights)_IMAGENET_CATEGORIES)handle_legacy_interface_ovewrite_named_param) ShuffleNetV2ShuffleNet_V2_X0_5_WeightsShuffleNet_V2_X1_0_WeightsShuffleNet_V2_X1_5_WeightsShuffleNet_V2_X2_0_Weightsshufflenet_v2_x0_5shufflenet_v2_x1_0shufflenet_v2_x1_5shufflenet_v2_x2_0)xgroupsreturncCsP|\}}}}||}||||||}t|dd}||d||}|S)Nr r)sizeviewtorch transpose contiguous)rrZ batchsize num_channelsheightwidthZchannels_per_groupr&[/var/www/html/django/DPS/env/lib/python3.9/site-packages/torchvision/models/shufflenetv2.pychannel_shuffles r(c sZeZdZeeeddfdd Zedeeeeeeejdd d Z e e d d d Z Z S)InvertedResidualN)inpoupstridercsNtd|krdks(ntd||_|d}|jdkrh||d>krhtd|d|d|d|jdkrt|j||d|jdd t|tj||ddd d d t|tj d d|_ n t|_ ttj|jdkr|n||ddd d d t|tj d d|j||d|jdd t|tj||ddd d d t|tj d d|_ dS)Nr zillegal stride valuerzInvalid combination of stride z, inp z and oup zB values. If stride == 1 then inp should be equal to oup // 2 << 1. kernel_sizer,paddingrF)r/r,r0biasTinplace) super__init__ ValueErrorr,nn Sequentialdepthwise_conv BatchNorm2dConv2dReLUbranch1branch2)selfr*r+r,Zbranch_features __class__r&r'r5,sF      zInvertedResidual.__init__r rF)ior/r,r0r1rc Cstj|||||||dS)N)r1r)r7r;)rBrCr/r,r0r1r&r&r'r9VszInvertedResidual.depthwise_convrrcCsb|jdkr6|jddd\}}tj|||fdd}ntj||||fdd}t|d}|S)Nr r)dim)r,chunkr catr>r=r()r?rx1x2outr&r&r'forward\s   zInvertedResidual.forward)r rF) __name__ __module__ __qualname__intr5 staticmethodboolr7r;r9rrK __classcell__r&r&r@r'r)+s* r)csbeZdZdefeeeeeedejfddfdd Z e e ddd Z e e dd d Z Z S) ri.N)stages_repeatsstages_out_channels num_classesinverted_residualrc sdtt|t|dkr&tdt|dkr:td||_d}|jd}ttj||ddddd t |tj d d |_ |}tj dddd |_ |||d ddD}t|||jddD]R\}} }|||dg} t| dD]} | |||dqt||tj| |}q|jd}ttj||ddddd t |tj d d |_t|||_dS)Nr-z2expected stages_repeats as list of 3 positive intsz7expected stages_out_channels as list of 5 positive intsrrr F)r1Tr2r.cSsg|]}d|qS)stager&).0rBr&r&r' z)ShuffleNetV2.__init__..)rr-r)r4r5r lenr6Z_stage_out_channelsr7r8r;r:r<conv1 MaxPool2dmaxpoolziprangeappendsetattrconv5Linearfc) r?rSrTrUrVinput_channelsZoutput_channelsZ stage_namesnamerepeatsseqrBr@r&r'r5isB        zShuffleNetV2.__init__rDcCsX||}||}||}||}||}||}|ddg}||}|S)Nrr-)r^r`Zstage2Zstage3Zstage4remeanrgr?rr&r&r' _forward_impls       zShuffleNetV2._forward_implcCs ||S)N)rnrmr&r&r'rKszShuffleNetV2.forward)rLrMrNr)rrOrr7Moduler5rrnrKrRr&r&r@r'rhs 0 r)weightsprogressargskwargsrcOsJ|durt|dt|jdt|i|}|durF||j|d|S)NrU categories)rq)rr]metarload_state_dictget_state_dict)rprqrrrsmodelr&r&r' _shufflenetv2s ry)r r z2https://github.com/ericsun99/Shufflenet-v2-Pytorch)min_sizertrecipec @s@eZdZedeeddiedddddid d d ZeZd S) rzDhttps://download.pytorch.org/models/shufflenetv2_x0.5-f707e7126e.pth crop_sizei ImageNet-1Kg-FN@g9voT@zacc@1zacc@5VThese weights were trained from scratch to reproduce closely the results of the paper. num_params_metrics_docsurl transformsruN rLrMrNr rr _COMMON_META IMAGENET1K_V1DEFAULTr&r&r&r'rs  rc @s@eZdZedeeddiedddddid d d ZeZd S) rzBhttps://download.pytorch.org/models/shufflenetv2_x1-5666bf0f80.pthr|r}i"rgI +WQ@gNbX9V@rrrrNrr&r&r&r'rs  rc @sDeZdZedeedddieddddd d id d d ZeZdS)rzBhttps://download.pytorch.org/models/shufflenetv2_x1_5-3c479a10.pthr|r~ resize_size+https://github.com/pytorch/vision/pull/5906iv5rg9v?R@g/$V@r These weights were trained from scratch by using TorchVision's `new training recipe `_. r{rrrrNrr&r&r&r'rs" rc @sDeZdZedeedddieddddd d id d d ZeZdS)rzBhttps://download.pytorch.org/models/shufflenetv2_x2_0-8be3c8ee.pthr|rrriprgQS@gMb@W@rrrrNrr&r&r&r'rs" r pretrained)rpT)rprq)rprqrsrcKs(t|}t||gdgdfi|S)a  Constructs a ShuffleNetV2 architecture with 0.5x output channels, as described in `ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design `__. Args: weights (:class:`~torchvision.models.ShuffleNet_V2_X0_5_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.ShuffleNet_V2_X0_5_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.shufflenetv2.ShuffleNetV2`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.ShuffleNet_V2_X0_5_Weights :members: r\r\)0`)rverifyryrprqrsr&r&r'rs rcKs(t|}t||gdgdfi|S)a  Constructs a ShuffleNetV2 architecture with 1.0x output channels, as described in `ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design `__. Args: weights (:class:`~torchvision.models.ShuffleNet_V2_X1_0_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.ShuffleNet_V2_X1_0_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.shufflenetv2.ShuffleNetV2`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.ShuffleNet_V2_X1_0_Weights :members: r)rtrir)rrryrr&r&r'r5s rcKs(t|}t||gdgdfi|S)a  Constructs a ShuffleNetV2 architecture with 1.5x output channels, as described in `ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design `__. Args: weights (:class:`~torchvision.models.ShuffleNet_V2_X1_5_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.ShuffleNet_V2_X1_5_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.shufflenetv2.ShuffleNetV2`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.ShuffleNet_V2_X1_5_Weights :members: r)ri`ir)rrryrr&r&r'rSs rcKs(t|}t||gdgdfi|S)a  Constructs a ShuffleNetV2 architecture with 2.0x output channels, as described in `ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design `__. Args: weights (:class:`~torchvision.models.ShuffleNet_V2_X2_0_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.ShuffleNet_V2_X2_0_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.shufflenetv2.ShuffleNetV2`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.ShuffleNet_V2_X2_0_Weights :members: r)riii)rrryrr&r&r'rqs r) _ModelURLs)zshufflenetv2_x0.5zshufflenetv2_x1.0zshufflenetv2_x1.5zshufflenetv2_x2.0), functoolsrtypingrrrrr torch.nnr7rZtransforms._presetsr utilsr _apir r _metar_utilsrr__all__rOr(ror)rrQryrrrrrrrrrrrr model_urlsr&r&r&r'sv       =B