U ʹjR@sUddlZddlZddlmZddlmZddlmZmZm Z m Z m Z m Z m Z mZddlZddlmZmZddlmZddlmZmZdd lmZmZdd lmZd d lmZmZmZd d l m!Z!d dl"m#Z#m$Z$m%Z%dddddddddddddddddd d!d"d#d$d%gZ&eGd&d'd'Z'Gd(d)d)e'Z(Gd*d+d+e'Z)Gd,d-d-ej*Z+Gd.d/d/ej*Z,Gd0ddej*Z-e ee(e)fe.e e/e ee0ee-d1d2d3Z1e2ee e ee(e)fe e/fd4d5d6Z3d7e!iZ4e e2efe5d8<e4d9d:d;Z6e4dddeZ8Gd?ddeZ9Gd@ddeZ:GdAddeZ;GdBddeZGdEddeZ?GdFddeZ@GdGddeZAGdHddeZBee%dIe8jCfdJddKdLe e8e0ee-dMdNdZDee%dIe9jCfdJddKdLe e9e0ee-dMdOdZEee%dIe:jCfdJddKdLe e:e0ee-dMdPdZFee%dIe;jCfdJddKdLe e;e0ee-dMdQdZGee%dIejCfdJddKdLe e>e0ee-dMdTd!ZJee%dIe?jCfdJddKdLe e?e0ee-dMdUd"ZKee%dIe@jCfdJddKdLe e@e0ee-dMdVd#ZLee%dIeAjCfdJddKdLe eAe0ee-dMdWd$ZMee%dIeBjCfdJddKdLe eBe0ee-dMdXd%ZNdS)YN) dataclass)partial)AnyCallableDictListOptionalSequenceTupleUnion)nnTensor)StochasticDepth)Conv2dNormActivationSqueezeExcitation)ImageClassificationInterpolationMode)_log_api_usage_once)register_modelWeights WeightsEnum)_IMAGENET_CATEGORIES)_make_divisible_ovewrite_named_paramhandle_legacy_interface EfficientNetEfficientNet_B0_WeightsEfficientNet_B1_WeightsEfficientNet_B2_WeightsEfficientNet_B3_WeightsEfficientNet_B4_WeightsEfficientNet_B5_WeightsEfficientNet_B6_WeightsEfficientNet_B7_WeightsEfficientNet_V2_S_WeightsEfficientNet_V2_M_WeightsEfficientNet_V2_L_Weightsefficientnet_b0efficientnet_b1efficientnet_b2efficientnet_b3efficientnet_b4efficientnet_b5efficientnet_b6efficientnet_b7efficientnet_v2_sefficientnet_v2_mefficientnet_v2_lc@sneZdZUeed<eed<eed<eed<eed<eed<edejfed<e d eee eed d d Z d S) _MBConvConfig expand_ratiokernelstrideinput_channels out_channels num_layers.blockN)channels width_mult min_valuereturncCst||d|S)N)r)r<r=r>rA^/var/www/html/bwave/python/venv/lib/python3.8/site-packages/torchvision/models/efficientnet.pyadjust_channels8sz_MBConvConfig.adjust_channels)N) __name__ __module__ __qualname__float__annotations__intrr Module staticmethodrrCrArArArBr4.s r4c sXeZdZd eeeeeeeeeedejfdd fdd Z e eeddd Z Z S) MBConvConfig?N.) r5r6r7r8r9r:r= depth_multr;r?c sL|||}|||}|||}| dkr0t} t||||||| dSN)rC adjust_depthMBConvsuper__init__) selfr5r6r7r8r9r:r=rNr; __class__rArBrS?s   zMBConvConfig.__init__r:rNcCstt||SrO)rImathceilrWrArArBrPRszMBConvConfig.adjust_depth)rMrMN) rDrErFrGrIrrr rJrSrKrP __classcell__rArArUrBrL=s" rLc s@eZdZdeeeeeeeedejfddfdd Z Z S)FusedMBConvConfigN.)r5r6r7r8r9r:r;r?c s(|dkr t}t|||||||dSrO) FusedMBConvrRrS)rTr5r6r7r8r9r:r;rUrArBrSYs zFusedMBConvConfig.__init__)N) rDrErFrGrIrrr rJrSrZrArArUrBr[Ws r[csReZdZefeeedejfedejfddfdd Z e e dddZ Z S) rQ.N)cnfstochastic_depth_prob norm_layerse_layerr?c s td|jkr dks*ntd|jdko>|j|jk|_g}tj}| |j|j }||jkr| t |j|d||d| t |||j |j|||dtd|jd}| |||ttjddd | t ||jd|ddtj||_t|d |_|j|_dS) Nrrillegal stride value kernel_sizer_activation_layer)rcr7groupsr_rdT)inplace)Z activationrow)rRrSr7 ValueErrorr8r9use_res_connectr SiLUrCr5appendrr6maxr Sequentialr;rstochastic_depth) rTr]r^r_r`layersrdexpanded_channelsZsqueeze_channelsrUrArBrSisT      zMBConv.__init__inputr?cCs&||}|jr"||}||7}|SrOr;rjrorTrsresultrArArBforwards   zMBConv.forward) rDrErFrrLrGrr rJrSr rwrZrArArUrBrQhs  :rQcsBeZdZeeedejfddfdd Ze e dddZ Z S) r\.N)r]r^r_r?c std|jkr dks*ntd|jdko>|j|jk|_g}tj}| |j|j }||jkr| t |j||j |j||d| t ||jd|ddn"| t |j|j|j |j||dtj||_t|d|_|j|_dS)Nrrrarcr7r_rdrbrh)rRrSr7rir8r9rjr rkrCr5rlrr6rnr;rro)rTr]r^r_rprdrqrUrArBrSsP     zFusedMBConv.__init__rrcCs&||}|jr"||}||7}|SrOrtrurArArBrws   zFusedMBConv.forward) rDrErFr[rGrr rJrSr rwrZrArArUrBr\s  4r\c sneZdZd eeeefeeee e de j fe eddfdd Z eedd d Zeedd d ZZS)r皙?N.)inverted_residual_settingdropoutr^ num_classesr_ last_channelr?c s<tt||s tdn$t|trsz)EfficientNet.__init__..z:The inverted_residual_setting should be List[MBConvConfig]Nrrrxcss|] }|jVqdSrO)r:)rr]rArArB sz(EfficientNet.__init__..rrfrbT)prgZfan_out)moderM)*rRrSrrirr all TypeErrorr BatchNorm2dr8rlrrksumranger:copyr9r7rGr;rnfeaturesZAdaptiveAvgPool2davgpoolZDropoutZLinear classifiermodulesZConv2dinitZkaiming_normal_weightZbiasZzeros_Z GroupNormZones_rXsqrtZ out_featuresZuniform_)rTr{r|r^r}r_r~rpZfirstconv_output_channelsZtotal_stage_blocksZstage_block_idr]Zstage_Z block_cnfZsd_probZlastconv_input_channelsZlastconv_output_channelsmZ init_rangerUrArBrSs            zEfficientNet.__init__)xr?cCs.||}||}t|d}||}|S)Nr)rrtorchflattenrrTrrArArB _forward_implLs     zEfficientNet._forward_implcCs ||SrO)rrrArArBrwVszEfficientNet.forward)ryrzNN)rDrErFr r rLr[rGrIrrr rJrSr rrwrZrArArUrBrsc )r{r|r~weightsprogresskwargsr?cKsT|dk rt|dt|jdt||fd|i|}|dk rP||j|dd|S)Nr} categoriesr~T)rZ check_hash)rlenmetarZload_state_dictZget_state_dict)r{r|r~rrrmodelrArArB _efficientnetZs r)archrr?c Ks:|drtt|d|dd}|dddddd|d dd dd d |d d d d d d |d dd d dd|d d dddd|d d d ddd|d dddddg}d}n|drtdddd d d tddd d ddtddd dddtddd ddd td dddddtd dd dddg}d}n|drtdddd d dtddd d dd tddd ddd tddd dddtd dddddtd dd dd d!td ddd d"d g}d}n|d#r$tddddddtddd dddtddd dd$dtddd d$dd%td dddd&d'td dd d&d(d)td ddd(d*dg}d}ntd+|||fS),NZefficientnet_br=rNr=rNrr r(Pprf@r10@ ir2i0ir3` izUnsupported model type ) startswithrrLpopr[ri)rrZ bneck_confr{r~rArArB_efficientnet_confmsT       rr _COMMON_META)rrzUhttps://github.com/pytorch/vision/tree/main/references/classification#efficientnet-v1)Zmin_sizerecipe)!rzUhttps://github.com/pytorch/vision/tree/main/references/classification#efficientnet-v2c @sFeZdZedeeddejdeddddd id d d d dZ e Z dS)rzJhttps://download.pytorch.org/models/efficientnet_b0_rwightman-7f5810bc.pthrr crop_size resize_size interpolationidP ImageNet-1Kg?5^IlS@g5^I bW@zacc@1zacc@5gNbX9?g~jts4@1These weights are ported from the original paper. num_params_metrics_ops _file_size_docsurlZ transformsrN rDrErFrrrrBICUBIC_COMMON_META_V1 IMAGENET1K_V1DEFAULTrArArArBrs*c @s~eZdZedeeddejdeddddd id d d d dZ edeeddej dedddddd id ddddZ e Z dS)rzJhttps://download.pytorch.org/models/efficientnet_b1_rwightman-bac287d4.pthrrivrg +S@gClW@rgCl?gM">@rrrz@https://download.pytorch.org/models/efficientnet_b1-c27df63c.pthzOhttps://github.com/pytorch/vision/issues/3995#new-recipe-with-lr-wd-crop-tuninggʡS@gƻW@gA`">@$ These weights improve upon the results of the original paper by using a modified version of TorchVision's `new training recipe `_. )rrrrrrN) rDrErFrrrrrrrBILINEARZ IMAGENET1K_V2rrArArArBrsTc @sFeZdZedeeddejdedddddid d d d d Z e Z dS)r zJhttps://download.pytorch.org/models/efficientnet_b2_rwightman-c35c1473.pthi rirgx&T@gp= W@rg rh?gʡEA@rrrNrrArArArBr s*c @sFeZdZedeeddejdeddddd id d d d dZ e Z dS)r!zJhttps://download.pytorch.org/models/efficientnet_b3_rwightman-b3899882.pthi,rrirgnT@g~jtX@rgZd;?gd;OG@rrrNrrArArArBr!s*c @sFeZdZedeeddejdeddddd id d d d dZ e Z dS)r"zJhttps://download.pytorch.org/models/efficientnet_b4_rwightman-23ab8bcd.pthi|rri0!'rgjtT@gt&X@rg~jt@gKR@rrrNrrArArArBr"/s*c @sFeZdZedeeddejdedddddid d d d d Z e Z dS)r#zJhttps://download.pytorch.org/models/efficientnet_b5_lukemelas-1a07897c.pthirirg#~jT@gx&1(X@rgx&1$@gK7]@rrrNrrArArArBr#Gs*c @sFeZdZedeeddejdedddddid d d d d Z e Z dS)r$zJhttps://download.pytorch.org/models/efficientnet_b6_lukemelas-24a108a5.pthirirgnU@gv:X@rg rh3@g$d@rrrNrrArArArBr$_s*c @sFeZdZedeeddejdedddddid d d d d Z e Z dS)r%zJhttps://download.pytorch.org/models/efficientnet_b7_lukemelas-c5b4e57e.pthiXricrg+U@g'1:X@rgsh|B@go@rrrNrrArArArBr%ws*c @sFeZdZedeeddejdedddddid d d d d Z e Z dS)r&zBhttps://download.pytorch.org/models/efficientnet_v2_s-dd5fe13b.pthrri8nGrg;OU@gx&18X@rgZd @gVT@rrrN rDrErFrrrrr_COMMON_META_V2rrrArArArBr&s*c @sFeZdZedeeddejdedddddid d d d d Z e Z dS)r'zBhttps://download.pytorch.org/models/efficientnet_v2_m-dc08266a.pthri:rgI +GU@gDlIX@rgE8@gQj@rrrNrrArArArBr's*c @sJeZdZedeeddejdddeddddd id d d d dZ e Z dS)r(zBhttps://download.pytorch.org/models/efficientnet_v2_l-59c71312.pthr)?rr)rrrZmeanZstdiHfrgʡEsU@gOnrX@rg ףp= L@gI +i|@rrrN) rDrErFrrrrrrrrrArArArBr(s. Z pretrained)rT)rr)rrrr?cKs8t|}tdddd\}}t||dd|||f|S)aEfficientNet B0 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B0_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B0_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B0_Weights :members: r)rMrr|ry)rverifyrrrrrrr{r~rArArBr)s  cKs8t|}tdddd\}}t||dd|||f|S)aEfficientNet B1 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B1_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B1_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B1_Weights :members: r*rM皙?rr|ry)rrrrrrrArArBr*s  cKs8t|}tdddd\}}t||dd|||f|S)aEfficientNet B2 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B2_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B2_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B2_Weights :members: r+r333333?rr|333333?)r rrrrrrArArBr+&s  cKs8t|}tdddd\}}t||dd|||f|S)aEfficientNet B3 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B3_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B3_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B3_Weights :members: r,rffffff?rr|r)r!rrrrrrArArBr,Es  cKs8t|}tdddd\}}t||dd|||f|S)aEfficientNet B4 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B4_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B4_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B4_Weights :members: r-r?rr|皙?)r"rrrrrrArArBr-is  cKsLt|}tdddd\}}t||dd|||fdttjdd d i|S) aEfficientNet B5 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B5_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B5_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B5_Weights :members: r.g?g@rr|rr_MbP?{Gz?epsZmomentum)r#rrrrrr rrrArArBr.s  cKsLt|}tdddd\}}t||dd|||fdttjdd d i|S) aEfficientNet B6 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B6_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B6_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B6_Weights :members: r/rg@rr|rr_rrr)r$rrrrrr rrrArArBr/s  cKsLt|}tdddd\}}t||dd|||fdttjdd d i|S) aEfficientNet B7 model architecture from the `EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks `_ paper. Args: weights (:class:`~torchvision.models.EfficientNet_B7_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_B7_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_B7_Weights :members: r0g@g@rr|rr_rrr)r%rrrrrr rrrArArBr0s  cKsDt|}td\}}t||dd|||fdttjddi|S)a Constructs an EfficientNetV2-S architecture from `EfficientNetV2: Smaller Models and Faster Training `_. Args: weights (:class:`~torchvision.models.EfficientNet_V2_S_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_V2_S_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_V2_S_Weights :members: r1r|ryr_rr)r&rrrrrr rrrArArBr1s    cKsDt|}td\}}t||dd|||fdttjddi|S)a Constructs an EfficientNetV2-M architecture from `EfficientNetV2: Smaller Models and Faster Training `_. Args: weights (:class:`~torchvision.models.EfficientNet_V2_M_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_V2_M_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_V2_M_Weights :members: r2r|rr_rr)r'rrrrrr rrrArArBr2"s    cKsDt|}td\}}t||dd|||fdttjddi|S)a Constructs an EfficientNetV2-L architecture from `EfficientNetV2: Smaller Models and Faster Training `_. Args: weights (:class:`~torchvision.models.EfficientNet_V2_L_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.EfficientNet_V2_L_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.efficientnet.EfficientNet`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.EfficientNet_V2_L_Weights :members: r3r|rr_rr)r(rrrrrr rrrArArBr3Hs    )OrrX dataclassesr functoolsrtypingrrrrrr r r rr r Ztorchvision.opsrZops.miscrrZtransforms._presetsrrutilsrZ_apirrr_metarZ_utilsrrr__all__r4rLr[rJrQr\rrGrIboolrstrrrrHrrrrr r!r"r#r$r%r&r'r(rr)r*r+r,r-r.r/r0r1r2r3rArArArBsz  (   C=s  80""###$$