tj0-dZddlmZddlZddlmZddlmZddlm Z ddl m Z dd l m Z dd lmZdd lmZmZmZmZdd lmZd dlmZejeZedeGddeZeGdde ZddZGddejZ GddejZ!edGddeZ"ddgZ#dS)zPyTorch VitPose model.) dataclassN)nn)initialization) load_backbone)BackboneOutput)PreTrainedModel)Unpack) ModelOutputTransformersKwargsauto_docstringlogging)can_return_tuple) VitPoseConfigz6 Class for outputs of pose estimation models. ) custom_introceZdZUdZdZejdzed<dZejdzed<dZ e ejdfdzed<dZ e ejdfdzed<dS)VitPoseEstimatorOutputaH loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided): Loss is not supported at this moment. See https://github.com/ViTAE-Transformer/ViTPose/tree/main/mmpose/models/losses for further detail. heatmaps (`torch.FloatTensor` of shape `(batch_size, num_keypoints, height, width)`): Heatmaps as predicted by the model. hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`): Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each stage) of shape `(batch_size, sequence_length, hidden_size)`. Hidden-states (also called feature maps) of the model at the output of each stage. Nlossheatmaps. hidden_states attentions) __name__ __module__ __qualname____doc__rtorch FloatTensor__annotations__rrtuplerj/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/vitpose/modeling_vitpose.pyrr$s  &*D% d "))))-He$&---:>M5*C/047>>>7;Je',-4;;;;;r"rceZdZUeed<dZdZdZdZe j de j e j ze jzffd ZxZS)VitPosePreTrainedModelconfigvit pixel_values)imageTmodulec*t|t|tjtjfrHt j|jd|j j |j t j |j dSdSdS)zInitialize the weightsg)meanstdN) super _init_weights isinstancerLinearConv2dinit trunc_normal_weightr&initializer_rangebiaszeros_)selfr* __class__s r#r/z$VitPosePreTrainedModel._init_weightsDs f%%% fry")4 5 5 )  v}3DKqqq-QT?T0U<,-1?Q ]b]i        r"r\cTeZdZdZdeffd ZddejdejdzfdZxZ S) VitPoseClassicDecoderz Classic decoding head consisting of a 2 deconvolutional blocks, followed by a 1x1 convolution layer, turning the feature maps into heatmaps. r&cttj|jjddddd|_tjd|_tj |_ tjdddddd|_ tjd|_ tj |_ tjd|jddd|_dS) NrFrF)rcrdrer7rrb)r.rfrConvTranspose2drkrldeconv1 BatchNorm2d batchnorm1rgrelu1deconv2 batchnorm2relu2r2rmrnros r#rfzVitPoseClassicDecoder.__init__s )  " .1VW^c    .--WYY )#s!UV]bccc .--WYY Ic6#4!AWXYYY r"NrprPcP||}||}||}||}||}||}||}|t||}|Srs)r~rrrrrrnrZrts r#ruzVitPoseClassicDecoder.forwards||L11 |44 zz,// ||L11 |44 zz,// 99\**  ! :66Hr"rsrvrBs@r#ryrys Z} Z Z Z Z Z ZELelT>Qr"ryz? The VitPose model with a pose estimation head on top. ceZdZdeffd Zee d dejdejdzdejdzdejdzde e d e f d Z xZ S) VitPoseForPoseEstimationr&ct|t||_t |jjdst dt |jjdst dt |jjdst d|jrt|nt||_ | dS)Nrlz0The backbone should have a hidden_size attribute image_sizez0The backbone should have an image_size attribute patch_sizez/The backbone should have a patch_size attribute) r.rfrbackbonehasattrr&rHuse_simple_decoderr\ryhead post_initros r#rfz!VitPoseForPoseEstimation.__init__s    %f-- t}+];; QOPP Pt}+\:: QOPP Pt}+\:: PNOO O4:4Mp(000ShioSpSp  r"Nr( dataset_indexrPlabelskwargsrqc ,d}|td|jj|fd|i|}|jd}|jd} |jjjd|jjjdz} |jjjd|jjjdz} | ddd}| | d| |  }| ||} t|| |j|j S) a dataset_index (`torch.Tensor` of shape `(batch_size,)`): Index to use in the Mixture-of-Experts (MoE) blocks of the backbone. This corresponds to the dataset index used during training, e.g. For the single dataset index 0 refers to the corresponding dataset. For the multiple datasets index 0 refers to dataset A (e.g. MPII) and index 1 refers to dataset B (e.g. CrowdPose). flip_pairs (`torch.tensor`, *optional*): Whether to mirror pairs of keypoints (for example, left ear -- right ear). Examples: ```python >>> from transformers import AutoImageProcessor, VitPoseForPoseEstimation >>> import torch >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> processor = AutoImageProcessor.from_pretrained("usyd-community/vitpose-base-simple") >>> model = VitPoseForPoseEstimation.from_pretrained("usyd-community/vitpose-base-simple") >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> boxes = [[[412.8, 157.61, 53.05, 138.01], [384.43, 172.21, 15.12, 35.74]]] >>> inputs = processor(image, boxes=boxes, return_tensors="pt") >>> with torch.no_grad(): ... outputs = model(**inputs) >>> heatmaps = outputs.heatmaps ```NzTraining is not yet supportedrrGrrr|)rP)rrrr)NotImplementedErrorrforward_with_filtered_kwargs feature_mapsrJr&rkrrpermuterL contiguousrrrr) r9r(rrPrrroutputssequence_outputrR patch_height patch_widthrs r#ruz VitPoseForPoseEstimation.forwards0R  %&EFF F"L$-"L # # '# # # ".r2$*1- {2=a@DKD_DjklDmm k1rsY!!!!!! &&&&&&++++++......------&&&&&&MMMMMMMMMMMM------000000  H % %   <<<<<[<<   <$)))))_)))"''''T296#####BI###L U U U U U 5U U  U p $%? @r"