o V h3@s`ddlZddlmZddlmZddlmZmZmZm Z m Z m Z ddl Z ddl m Z mZddlmZddlmZdd lmZd d lmZd d lmZmZmZd d lmZd dlmZmZd dl m!Z!m"Z"ddlmZ#ddl$m%Z%ddl&m'Z'ddl(m)Z)m*Z*ddgZ+de,de,de,dede j-fde j.f ddZ/de,de,dede j-fde j.fdd Z0d!e j-fd"d#Z1Gd$d%d%e j-Z2Gd&d'd'e*Z3Gd(d)d)e*Z4Gd*d+d+e j-Z5d,e ej6ej7fd-e,dede j-ffd.d/Z8Gd0ddeZ9eed1e9j:fd2e"j;fd3dd4de"j;ddd5d6e e9d7esz;SSDLiteFeatureExtractorMobileNet.__init__..i)rErFruse_res_connect ValueErrorr r)blockfeaturesrZr2r#r@extra)rKrerfr%rgrh get_depthrtrLrkr-rFus$  $* z)SSDLiteFeatureExtractorMobileNet.__init__rNr&cCsVg}|jD] }||}||q|jD] }||}||qtddt|DS)NcSsg|] \}}t||fqSr,)rW).0ivr,r,r- sz.)rsr\rtr enumerate)rKrNoutputrrr,r,r-rQs    z(SSDLiteFeatureExtractorMobileNet.forward)rcrd)rRrSrTr rVrUrfloatrFr rrWrQrXr,r,rLr-rbts "!rbretrainable_layerscCs|j}dgddt|Dt|dg}t|}d|kr'|ks,tdtd|dkr4t|n|||}|d|D]}|D]}|dqFq@t||d|S)NrcSs g|] \}}t|ddr|qS)_is_cnF)getattr)rvrwbr,r,r-rys z(_mobilenet_extractor..rzYtrainable_layers should be in the range [0, {num_stages}], instead got {trainable_layers}F)rsrzlenrq parametersrequires_grad_rb)rer}r% stage_indices num_stages freeze_beforer parameterr,r,r-_mobilenet_extractors&  rc @s8eZdZedededddddiidd d d d ZeZd S)r zShttps://download.pytorch.org/models/ssdlite320_mobilenet_v3_large_coco-a79551df.pthi}4)rrz]https://github.com/pytorch/vision/tree/main/references/detection#ssdlite320-mobilenetv3-largez COCO-val2017box_mapgL5@g-?gt*@zSThese weights were produced by following a similar training recipe as on the paper.) num_params categoriesmin_sizerecipe_metrics_ops _file_size_docs)url transformsmetaN)rRrSrTrrrCOCO_V1DEFAULTr,r,r,r-r s$ pretrainedpretrained_backbone)weightsweights_backboneT)rprogressrCrtrainable_backbone_layersr%rrrCrrkwargscKst|}t|}d|vrtd|dur%d}td|t|jd}n|dur+d}t|dup3|du|dd}|du}|durHt t j dd d }t d||||d |}|dur\t |t|||}d } td dtdDddd} t|| } | } t| t| jkrtdt| dt| jddddgdgdd} i| |}t|| | |fdt| | ||i|}|dur||j|dd|S)aSSDlite model architecture with input size 320x320 and a MobileNetV3 Large backbone, as described at `Searching for MobileNetV3 `__ and `MobileNetV2: Inverted Residuals and Linear Bottlenecks `__. .. betastatus:: detection module See :func:`~torchvision.models.detection.ssd300_vgg16` for more details. Example: >>> model = torchvision.models.detection.ssdlite320_mobilenet_v3_large(weights=SSDLite320_MobileNet_V3_Large_Weights.DEFAULT) >>> model.eval() >>> x = [torch.rand(3, 320, 320), torch.rand(3, 500, 400)] >>> predictions = model(x) Args: weights (:class:`~torchvision.models.detection.SSDLite320_MobileNet_V3_Large_Weights`, optional): The pretrained weights to use. See :class:`~torchvision.models.detection.SSDLite320_MobileNet_V3_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. num_classes (int, optional): number of output classes of the model (including the background). weights_backbone (:class:`~torchvision.models.MobileNet_V3_Large_Weights`, optional): The pretrained weights for the backbone. trainable_backbone_layers (int, optional): number of trainable (not frozen) layers starting from final block. Valid values are between 0 and 6, with 6 meaning all backbone layers are trainable. If ``None`` is passed (the default) this value is set to 6. norm_layer (callable, optional): Module specifying the normalization layer to use. **kwargs: parameters passed to the ``torchvision.models.detection.ssd.SSD`` base class. Please refer to the `source code `_ for more details about this class. .. autoclass:: torchvision.models.detection.SSDLite320_MobileNet_V3_Large_Weights :members: sizez?The size of the model is already fixed; ignoring the parameter.NrCr[gMbP?r4)epsmomentum)rrr% reduced_tail)@rcSsg|]}ddgqS)rr r,)rv_r,r,r-ry,sz1ssdlite320_mobilenet_v3_large..g?gffffff?) min_ratio max_ratioz4The length of the output channels from the backbone z? do not match the length of the anchor generator aspect ratios g?i,)?rr) score_thresh nms_threshdetections_per_imgtopk_candidates image_mean image_stdheadT)r check_hashr,)r verifyrwarningswarnrrrrrr BatchNorm2drr@rrrange det_utilsretrieve_out_channelsnum_anchors_per_location aspect_ratiosrqrrAload_state_dictget_state_dict)rrrCrrr%r reduce_tailreranchor_generatorr#rBdefaultsmodelr,r,r-r!sp 8      )>r collectionsr functoolsrtypingrrrrrr r9r r ops.miscr transforms._presetsrutilsrr_apirrr_metarrrr mobilenetv3rrr anchor_utilsrbackbone_utilsrssdrr__all__rUrVr)r.r2r@rArGrIrb MobileNetV2 MobileNetV3rr r IMAGENET1K_V1boolr!r,r,r,r-s             &  0