`iTdZddlmZmZddlZddlmZmZddl m Z m Z m Z ddl mZmZddlmZmZmZmZmZmZmZmZmZmZmZmZdd lmZmZm Z erddl!Z!erddl"Z"dd l"m#Z#m$Z$d d l%m&Z&ej'e(Z) dd ej*deee+effdZ, dd edeee+efdefdZ-defdZ.Gdde Z/dgZ0dS)z%Image processor class for SuperPoint.)OptionalUnionN)is_torch_availableis_vision_available)BaseImageProcessor BatchFeature get_size_dict)resizeto_channel_dimension_format) ChannelDimension ImageInput ImageTypePILImageResamplingget_image_typeinfer_channel_dimension_format is_pil_imageis_scaled_imageis_valid_imageto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypeloggingrequires_backends)Image ImageDraw)KeypointMatchingOutputimageinput_data_formatc|tjkr[|jddkrdStj|d|dko#tj|d|dkS|tjkr[|jddkrdStj|d|d ko#tj|d |d kSdS) NrrTr.r...r.r.r&)r FIRSTshapenpallLAST)r r!s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/efficientloftr/image_processing_efficientloftr.py is_grayscaler15s,222 ;q>Q  4veFmuV}455`"&vRWX^R_A_:`:`` .3 3 3 ;r?a  4veFmuV}455`"&vRWX^R_A_:`:`` 4 3returnc2ttdgt|tjrt ||r|S|t jkr>|ddz|ddzz|ddzz}tj|gd zd }nM|t j kr=|d dz|d dzz|ddzz}tj|gd zd }|St|tj j s|S| d}|S)ao Converts an image to grayscale format using the NTSC formula. Only support numpy and PIL Image. TODO support torch and tensorflow grayscale conversion This function is supposed to return a 1-channel image, but it returns a 3-channel image with the same value in each channel, because of an issue that is discussed in : https://github.com/huggingface/transformers/pull/25786#issuecomment-1730176446 Args: image (Image): The image to convert. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. visionr!r#gŏ1w-!?r$gbX9?r%gv/?rr)axisr(r)r*r'L) rconvert_to_grayscale isinstancer-ndarrayr1r r+stackr/PILrconvert)r r! gray_images r0r9r9Ds+$*XJ777%$$  1B C C C L  0 6 6 6v/%-&2HH5QW=[aKaaJ:,"2;;;JJ "2"7 7 7v/%-&2HH5QW=[aKaaJ:,"2<<._is_valid_imagetsNE"" 5 ! ! fnU&;&;y}&L fQTUZU`QaQaefQf r2r&c3.K|]}|VdSN.0r rDs r0 z2validate_and_format_image_pairs..{s-#Q#Q__U%;%;#Q#Q#Q#Q#Q#Qr2c3K|]G}t|to-t|dkotfd|DVHdS)r&c3.K|]}|VdSrFrGrHs r0rJz..s-CCuOOE**CCCCCCr2N)r:listrCr.)rI image_pairrDs r0rJz2validate_and_format_image_pairs..}s}   z4 ( ( DJ1$ DCCCC CCCCC      r2cg|] }|D]}| SrGrG)rIrNr s r0 z3validate_and_format_image_pairs..s%KKKj KKuEKKKKr2)r:rMrCr. ValueError)r@ error_messagerDs @r0validate_and_format_image_pairsrSksM   &$ L v;;!  #Q#Q#Q#Q&#Q#Q#Q Q Q M     %       L LKFKKK K ] # ##r2creZdZdZdgZddejdddfdedee e e fded ed e d ed dffd Z ddejde e e fdeee efdeee effdZdddddddejdf deedee e e fdeed eed ee d eedeee efdedeee efd efdZ d dddeeeefde d ee e ejffdZdedee e ejfd edfdZdZxZS)!EfficientLoFTRImageProcessorau Constructs a EfficientLoFTR image processor. Args: do_resize (`bool`, *optional*, defaults to `True`): Controls whether to resize the image's (height, width) dimensions to the specified `size`. Can be overridden by `do_resize` in the `preprocess` method. size (`Dict[str, int]` *optional*, defaults to `{"height": 480, "width": 640}`): Resolution of the output image after `resize` is applied. Only has an effect if `do_resize` is set to `True`. Can be overridden by `size` in the `preprocess` method. resample (`PILImageResampling`, *optional*, defaults to `Resampling.BILINEAR`): Resampling filter to use if resizing the image. Can be overridden by `resample` in the `preprocess` method. do_rescale (`bool`, *optional*, defaults to `True`): Whether to rescale the image by the specified scale `rescale_factor`. Can be overridden by `do_rescale` in the `preprocess` method. rescale_factor (`int` or `float`, *optional*, defaults to `1/255`): Scale factor to use if rescaling the image. Can be overridden by `rescale_factor` in the `preprocess` method. do_grayscale (`bool`, *optional*, defaults to `True`): Whether to convert the image to grayscale. Can be overridden by `do_grayscale` in the `preprocess` method. pixel_valuesTNgp? do_resizesizeresample do_rescalerescale_factor do_grayscaler3c tjdi|||nddd}t|d}||_||_||_||_||_||_dS)Nii)heightwidthFdefault_to_squarerG) super__init__r rWrXrYrZr[r\) selfrWrXrYrZr[r\kwargs __class__s r0rcz%EfficientLoFTRImageProcessor.__init__s| ""6"""'ttc-J-JTU;;;"   $,(r2r data_formatr!c bt|d}t|f|d|df||d|S)aL Resize an image. Args: image (`np.ndarray`): Image to resize. size (`dict[str, int]`): Dictionary of the form `{"height": int, "width": int}`, specifying the size of the output image. data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the output image. If not provided, it will be inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. Fr`r^r_)rXrgr!)r r )rdr rXrgr!res r0r z#EfficientLoFTRImageProcessor.resizesU:TU;;;  x.$w-0#/       r2return_tensorsc  >||n|j}||n|j}||n|j}||n|j}||n|j}||n|j}t |d}t|}t|stdt|||||d|D}t|dr|rt d| t|d} g|D]q} |r|| ||| } |r|| || } |rt#| | } t%| | | } | rfd t)dt+dD} d| i}t-||S)a Preprocess an image or batch of images. Args: images (`ImageInput`): Image pairs to preprocess. Expects either a list of 2 images or a list of list of 2 images list with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. do_resize (`bool`, *optional*, defaults to `self.do_resize`): Whether to resize the image. size (`dict[str, int]`, *optional*, defaults to `self.size`): Size of the output image after `resize` has been applied. If `size["shortest_edge"]` >= 384, the image is resized to `(size["shortest_edge"], size["shortest_edge"])`. Otherwise, the smaller edge of the image will be matched to `int(size["shortest_edge"]/ crop_pct)`, after which the image is cropped to `(size["shortest_edge"], size["shortest_edge"])`. Only has an effect if `do_resize` is set to `True`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): Resampling filter to use if resizing the image. This can be one of `PILImageResampling`, filters. Only has an effect if `do_resize` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether to rescale the image values between [0 - 1]. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): Rescale factor to rescale the image by if `do_rescale` is set to `True`. do_grayscale (`bool`, *optional*, defaults to `self.do_grayscale`): Whether to convert the image to grayscale. return_tensors (`str` or `TensorType`, *optional*): The type of tensors to return. Can be one of: - Unset: Return a list of `np.ndarray`. - `TensorType.TENSORFLOW` or `'tf'`: Return a batch of type `tf.Tensor`. - `TensorType.PYTORCH` or `'pt'`: Return a batch of type `torch.Tensor`. - `TensorType.NUMPY` or `'np'`: Return a batch of type `np.ndarray`. - `TensorType.JAX` or `'jax'`: Return a batch of type `jax.numpy.ndarray`. data_format (`ChannelDimension` or `str`, *optional*, defaults to `ChannelDimension.FIRST`): The channel dimension format for the output image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - Unset: Use the channel dimension format of the input image. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of: - `"channels_first"` or `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `"channels_last"` or `ChannelDimension.LAST`: image in (height, width, num_channels) format. - `"none"` or `ChannelDimension.NONE`: image in (height, width) format. NFr`zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.)rWrXrYrZr[c,g|]}t|SrGrrIr s r0rPz;EfficientLoFTRImageProcessor.preprocess..3 <<.Ns&SSSz!a!e),SSSr2r&rV)data tensor_type)rWrYrZr[r\rXr rSrrQrrlogger warning_oncerr rescaler9r appendrangerCr )rdr@rWrXrYrZr[r\rirgr!rer image_pairsrurts @r0 preprocessz'EfficientLoFTRImageProcessor.preprocesss,t"+!6IIDN '388#-#9ZZt +9+E4K^'3'?||TEV 'ttTYTU;;;188F## :  &!)     =vay I I   % %E t %dXar ss m 5Zk ll Y,UFWXXX/{VghhhE   e $ $ $ $TSSSeAs:PQ6R6RSSS  ,>BBBBr2outputsr target_sizes thresholdc|jjdt|krtdt d|Dstdt |t r!tj||jj }n3|jddks|jddkrtd|}|j }|| d ddddz}|tj}g}t!||j|jD]x\}}} tj| |k|dk} |d| d} |d| d} | d| d} || | | d y|S) a Converts the raw output of [`KeypointMatchingOutput`] into lists of keypoints, scores and descriptors with coordinates absolute to the original image sizes. Args: outputs ([`KeypointMatchingOutput`]): Raw outputs of the model. target_sizes (`torch.Tensor` or `List[Tuple[Tuple[int, int]]]`, *optional*): Tensor of shape `(batch_size, 2, 2)` or list of tuples of tuples (`Tuple[int, int]`) containing the target size `(height, width)` of each image in the batch. This must be the original image size (before any processing). threshold (`float`, *optional*, defaults to 0.0): Threshold to filter out the matches with low scores. Returns: `List[Dict]`: A list of dictionaries, each dictionary containing the keypoints in the first and second image of the pair, the matching scores and the matching indices. rzRMake sure that you pass in as many target sizes as the batch dimension of the maskc3<K|]}t|dkVdS)r&N)rC)rI target_sizes r0rJzNEfficientLoFTRImageProcessor.post_process_keypoint_matching..ls/II[3{##q(IIIIIIr2zTEach element of target_sizes must contain the size (h, w) of each image of the batch)devicerr&r') keypoints0 keypoints1matching_scores)matchesr,rCrQr.r:rMtorchtensorr keypointscloneflipreshapetoint32zipr logical_andrz)rdrrrimage_pair_sizesrresultskeypoints_pairrscores valid_matchesmatched_keypoints0matched_keypoints1rs r0post_process_keypoint_matchingz;EfficientLoFTRImageProcessor.post_process_keypoint_matchingTs, ?  #s<'8'8 8 8qrr rIILIIIII ustt t lD ) ) ,$|LAWXXX  !!$))\-?-Ba-G-G j , %++--  0 5 5b 9 9 A A"aA N NN LL-- /29gowOf/g/g   +NGV!-fy.@'B,OOM!/!2=3C!D !/!2=3C!D $Qi a(89O NN"4"4'6    r2r@keypoint_matching_outputz Image.Imagec tdDfdtdtdD}g}t||D]\}}|djdd\}}|djdd\} } t jt|| || zdft j} |d| d|d|f<|d| d| |df<tj | } tj | } |d  d\}}|d  d\}}t|||||d D]\}}}}}||}| ||||z|f|d | |dz |dz |dz|dzfd | ||zdz |dz ||zdz|dzfd || |S)a Plots the image pairs side by side with the detected keypoints as well as the matching between them. Args: images (`ImageInput`): Image pairs to plot. Same as `EfficientLoFTRImageProcessor.preprocess`. Expects either a list of 2 images or a list of list of 2 images list with pixel values ranging from 0 to 255. keypoint_matching_output (List[Dict[str, torch.Tensor]]]): A post processed keypoint matching output Returns: `List[PIL.Image.Image]`: A list of PIL images, each containing the image pairs side by side with the detected keypoints as well as the matching between them. c,g|]}t|SrGrlrms r0rPzLEfficientLoFTRImageProcessor.visualize_keypoint_matching..rnr2c*g|]}||dzSrrrG)rIrsr@s r0rPzLEfficientLoFTRImageProcessor.visualize_keypoint_matching..s&KKKQva!a%i(KKKr2rr&Nrr)dtyperrr)fillr_black)r)rSr{rCrr,r-zerosmaxuint8r fromarrayrDrawunbind _get_colorlineellipserz)rdr@rr|rrN pair_outputheight0width0height1width1 plot_imageplot_image_pildraw keypoints0_x keypoints0_y keypoints1_x keypoints1_y keypoint0_x keypoint0_y keypoint1_x keypoint1_ymatching_scorecolors ` r0visualize_keypoint_matchingz8EfficientLoFTRImageProcessor.visualize_keypoint_matchings}&188<.11D)4\)B)I)I!)L)L &L,)4\)B)I)I!)L)L &L,VYlL, TeHfWW  R [+{N77  +{V/C[Q  kAo{Q aQ\_`Q`aho ppp  6)A-{Q f@TWX@XZehiZij  NN> * * * *r2c^tdd|z z}td|z}d}|||fS)zMaps a score to a color.rr)int)rdscorergbs r0rz'EfficientLoFTRImageProcessor._get_colors: q5y! " " e   1ayr2)NN)r~) __name__ __module__ __qualname____doc__model_input_namesrBILINEARboolrdictstrrfloatrcr-r;rr r r+rr r}rMtuplerTensorrrrr __classcell__)rfs@r0rUrUs,(()-'9'B '!)))tCH~&)% )  )  )) ))))))4?CDH % % z% 38n% eC)9$9:; % $E#/?*?$@A % % % % V%))-15%)*.'+;?(8(>DHtCtCD>tCtCH~& tC -. tC TN tC!tCtntC!sJ!78tC&tC$E#/?*?$@AtC tCtCtCtCt 99)9JU 349 9 d3 $% & 9999v44#'tC,='>"?4 m  4444lr2rUrF)1rtypingrrnumpyr-rrimage_processing_utilsrr r image_transformsr r image_utilsr rrrrrrrrrrrutilsrrrrr=rrmodeling_efficientloftrr get_loggerrrwr;rr1r9rSrU__all__rGr2r0rs,+""""""""77777777UUUUUUUUUUCCCCCCCC                            <;;;;;;;;;LLL@JJJ$$$$$$$$??????  H % % AE a a : ac+;&; <= a a a a"AE## #c+;&; <=#####N$J$$$$8CCCCC#5CCCL * *r2