o h3@sXddlZddlmZddlmZddlmZmZmZm Z ddl Z ddl m Z m Z ddl mZddlmZdd lmZd d lmZd d lmZmZmZd d lmZd dlmZmZd dlmZm Z ddlmZ!ddl"m#Z#ddl$m%Z%ddl&m'Z'm(Z(ddgZ)de*de*de*dede j+fde j,f ddZ-de*de*dede j+fde j,fdd Z.d!e j+fd"d#Z/Gd$d%d%e j+Z0Gd&d'd'e(Z1Gd(d)d)e(Z2Gd*d+d+e j+Z3d,e ej4ej5fd-e*dede j+ffd.d/Z6Gd0ddeZ7eed1e7j8fd2e j9fd3dd4de j9ddd5d6ee7d7e:d8ee*d9ee d:ee*deede j+fd;ede'fdr r9r:r#.csNt}t||D]\}}|t|||d|q t|t||dS)Nr r ModuleListzipappendr,r7r<r=)rBr r9r:r#rFchannelsanchorsrCr*r+r=as z"SSDLiteClassificationHead.__init__ rHrIrJrKrLrrrMr=rPr*r*rCr+r>`s r>cs<eZdZdeedeededejfffdd ZZ S)r@r r9r#.csNt}t||D]\}}|t|d|d|q t|t|ddS)Nr rQ)rBr r9r#Zbbox_regrUrVrCr*r+r=ls zSSDLiteRegressionHead.__init__rWr*r*rCr+r@ks4r@c s^eZdZ  ddejdededejfdedef fd d Zd e d e e e ffd dZ Z S) SSDLiteFeatureExtractorMobileNet?backbonec4_posr#. width_mult min_depthc stt|||jrtdttjg|d|||jdRtj||jddg||ddR|_fdd}t t |dj |d|t |d|d|t |d|d|t |d|d |g}t |||_ dS) Nz0backbone[c4_pos].use_res_connect should be Falserrcstt|Sr;)maxrL)dr_r^r*r+sz;SSDLiteFeatureExtractorMobileNet.__init__..i)r<r=r Zuse_res_connect ValueErrorrr'blockfeaturesrRr-r!r7extra)rBr\r]r#r^r_Z get_depthrjrCrbr+r=us$  $* z)SSDLiteFeatureExtractorMobileNet.__init__rEr$cCsVg}|jD] }||}||q|jD] }||}||qtddt|DS)NcSsg|] \}}t||fqSr*)rO).0ivr*r*r+ sz.)rirTrjr enumerate)rBrEoutputrhr*r*r+rGs    z(SSDLiteFeatureExtractorMobileNet.forward)rZr[)rHrIrJrrMrLrfloatr=r rNrOrGrPr*r*rCr+rYts "!rYr\trainable_layerscCs|j}dgddt|Dt|dg}t|}d|kr'|ks,tdtd|dkr4t|n|||}|d|D]}|D]}|dqFq@t||d|S)NrcSs g|] \}}t|ddr|qS)Z_is_cnF)getattr)rkrlbr*r*r+rns z(_mobilenet_extractor..rzYtrainable_layers should be in the range [0, {num_stages}], instead got {trainable_layers}F)rirolenrg parametersZrequires_grad_rY)r\rrr#Z stage_indicesZ num_stagesZ freeze_beforertZ parameterr*r*r+_mobilenet_extractors&  rxc @s8eZdZedededddddiidd d d d ZeZd S)rzShttps://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-val2017Zbox_mapgL5@g-?gt*@zSThese weights were produced by following a similar training recipe as on the paper.)Z num_params categoriesZmin_sizeZrecipeZ_metricsZ_ops _file_sizeZ_docs)urlZ transformsmetaN)rHrIrJrr rCOCO_V1DEFAULTr*r*r*r+rs$Z pretrainedZpretrained_backbone)weightsweights_backboneT)rprogressr:rtrainable_backbone_layersr#rrr:rrkwargscKst|}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.Nr:ry[gMbP?r/)epsZmomentum)rrr#Z reduced_tail)@rcSsg|]}ddgqS)rr r*)rk_r*r*r+rn,sz1ssdlite320_mobilenet_v3_large..g?gffffff?)Z min_ratioZ 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)Z score_threshZ nms_threshZdetections_per_imgZtopk_candidatesZ image_meanZ image_stdheadT)rZ check_hashr*)rverifyrwarningswarnrrvr|rrrZ BatchNorm2drr7rxrrange det_utilsZretrieve_out_channelsZnum_anchors_per_locationZ aspect_ratiosrgrr8Zload_state_dictZget_state_dict)rrr:rrr#rZ reduce_tailr\rZanchor_generatorr!r9defaultsmodelr*r*r+rsp 8      )r@rYZ MobileNetV2Z MobileNetV3rxrr}Z IMAGENET1K_V1boolrr*r*r*r+s            &  0