sgodZddlZddlmZmZmZmZmZddlZ ddl m Z m Z m Z ddlmZmZmZmZmZddlmZmZmZmZmZmZmZmZmZmZmZddl m!Z!m"Z"m#Z#m$Z$e#rddl%Z%e$jLe'Z(d Z)d Z*d Z+Gd d e Z,y)z Image processor class for OwlViTN)DictListOptionalTupleUnion)BaseImageProcessor BatchFeature get_size_dict) center_cropcenter_to_corners_formatrescaleresizeto_channel_dimension_format) OPENAI_CLIP_MEANOPENAI_CLIP_STDChannelDimension ImageInputPILImageResamplinginfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_imagesvalidate_preprocess_arguments) TensorTypefilter_out_non_signature_kwargsis_torch_availableloggingc|jr>|jtjtjfvr|S|j S|jtj tjfvr|S|jS)N) is_floating_pointdtypetorchfloat32float64floatint32int64int)ts e/var/www/html/venv/lib/python3.12/site-packages/transformers/models/owlvit/image_processing_owlvit.py_upcastr,5s`GG u}}==qL1779LGG U[[99qFquuwFcft|}|dddf|dddfz |dddf|dddfz zS)a Computes the area of a set of bounding boxes, which are specified by its (x1, y1, x2, y2) coordinates. Args: boxes (`torch.FloatTensor` of shape `(number_of_boxes, 4)`): Boxes for which the area will be computed. They are expected to be in (x1, y1, x2, y2) format with `0 <= x1 < x2` and `0 <= y1 < y2`. Returns: `torch.FloatTensor`: a tensor containing the area for each box. Nrr)r,)boxess r+box_arear2=sB ENE !Q$K%1+ %%1+ad *C DDr-c^t|}t|}tj|dddddf|ddddf}tj|dddddf|ddddf}||z j d}|dddddf|dddddfz}|dddf|z|z }||z } | |fS)Nr/r)minr0)r2r#maxr4clamp) boxes1boxes2area1area2left_top right_bottom width_heightinterunionious r+box_iourALs V E V Eyy4! ,fQUm*DT&/&;r-imagerPrQ data_formatinput_data_formatreturnc tt|d}d|vsd|vr tdt||d|dff|||d|S)a2 Resize an image to a certain size. Args: image (`np.ndarray`): Image to resize. size (`Dict[str, int]`): The size to resize the image to. Must contain height and width keys. resample (`PILImageResampling`, *optional*, defaults to `PILImageResampling.BICUBIC`): The resampling filter to use when resizing the input. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. TrHrFrGz2size dictionary must contain height and width keys)rQr]r^)r ValueErrorr)rXr\rPrQr]r^rYs r+rzOwlViTImageProcessor.resizese2TT: 4 7$#6QR R  (^T'] + #/     r-rSc rt|d}d|vsd|vr tdt||d|dff||d|S)a Center crop an image to a certain size. Args: image (`np.ndarray`): Image to center crop. crop_size (`Dict[str, int]`): The size to center crop the image to. Must contain height and width keys. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format of the input image. If not provided, it will be inferred. TrHrFrGz7crop_size dictionary must contain height and width keysr]r^)r rar )rXr\rSr]r^rYs r+r z OwlViTImageProcessor.center_cropsd,")tD 9 $y(@VW W  x )G"4 5 $/     r-rTc t||||S)a Rescale the image by the given factor. image = image * rescale_factor. Args: image (`np.ndarray`): Image to rescale. rescale_factor (`float`): The value to use for rescaling. data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. 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. input_data_format (`str` or `ChannelDimension`, *optional*): The channel dimension format for the input image. If unset, 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. rc)r)rXr\rTr]r^s r+rzOwlViTImageProcessor.rescales4un+Yjkkr-imagesrOrRrJrUrVrWreturn_tensorsc ||n |j}||n |j}||n |j}||n |j}||n |j}||n |j }||n |j }| | n |j} | | n |j} | | n |j} t|}t|s tdt||| | | ||||| |Dcgc] }t|}}t|dr|rt j#d|t%|d}|r"|Dcgc]}|j'||||}}|r!|Dcgc]}|j)|||}}|r!|Dcgc]}|j+|||}}| r"|Dcgc]}|j-|| | |}}|Dcgc]}t/|| | }}t1d |i| }|Scc}wcc}wcc}wcc}wcc}wcc}w) a Prepares an image or batch of images for the model. Args: images (`ImageInput`): The image or batch of images to be prepared. Expects a single or batch of images 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 or not to resize the input. If `True`, will resize the input to the size specified by `size`. size (`Dict[str, int]`, *optional*, defaults to `self.size`): The size to resize the input to. Only has an effect if `do_resize` is set to `True`. resample (`PILImageResampling`, *optional*, defaults to `self.resample`): The resampling filter to use when resizing the input. Only has an effect if `do_resize` is set to `True`. do_center_crop (`bool`, *optional*, defaults to `self.do_center_crop`): Whether or not to center crop the input. If `True`, will center crop the input to the size specified by `crop_size`. crop_size (`Dict[str, int]`, *optional*, defaults to `self.crop_size`): The size to center crop the input to. Only has an effect if `do_center_crop` is set to `True`. do_rescale (`bool`, *optional*, defaults to `self.do_rescale`): Whether or not to rescale the input. If `True`, will rescale the input by dividing it by `rescale_factor`. rescale_factor (`float`, *optional*, defaults to `self.rescale_factor`): The factor to rescale the input by. Only has an effect if `do_rescale` is set to `True`. do_normalize (`bool`, *optional*, defaults to `self.do_normalize`): Whether or not to normalize the input. If `True`, will normalize the input by subtracting `image_mean` and dividing by `image_std`. image_mean (`Union[float, List[float]]`, *optional*, defaults to `self.image_mean`): The mean to subtract from the input when normalizing. Only has an effect if `do_normalize` is set to `True`. image_std (`Union[float, List[float]]`, *optional*, defaults to `self.image_std`): The standard deviation to divide the input by when normalizing. Only has an effect if `do_normalize` is set to `True`. 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: - `ChannelDimension.FIRST`: image in (num_channels, height, width) format. - `ChannelDimension.LAST`: image in (height, width, num_channels) format. - Unset: defaults to 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. zkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.) rJrTrUrVrWrRrSrOrPrQrzIt looks like you are trying to rescale already rescaled images. If the input images have pixel values between 0 and 1, set `do_rescale=False` to avoid rescaling them again.)rPrQr^)rSr^)rTr^)meanstdr^)input_channel_dimrD)data tensor_type)rOrPrQrRrSrJrTrUrVrWrrrarrrlogger warning_oncerrr r normalizerr )rXrerOrPrQrRrSrJrTrUrVrWrfr]r^r\encoded_inputss r+ preprocesszOwlViTImageProcessor.preprocesss|L"+!6IDNN 'tTYY'38+9+E4K^K^!*!6IDNN #-#9Zt +9+E4K^K^'3'?|TEVEV #-#9Zt !*!6IDNN $V,F#:  &!)%!) 6<vay I  $ ExSd eF oufk  )O` aF $ U>Uf gF $u:9XijF ou ej '{N_ `  &NF+CQ_`O=     s$G*G#G(1G-G26G7c tjdt|j|j}}t |t |k7r t d|jddk7r t dtj|d}tj|j}|j}t|}|jd\}} tj| || |gdj!|j"} || dddddfz}t%|||D cgc] \} } } | | | d }} } } |Scc} } } w) a= Converts the raw output of [`OwlViTForObjectDetection`] into final bounding boxes in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format. Args: outputs ([`OwlViTObjectDetectionOutput`]): Raw outputs of the model. target_sizes (`torch.Tensor` of shape `(batch_size, 2)`): Tensor containing the size (h, w) of each image of the batch. For evaluation, this must be the original image size (before any data augmentation). For visualization, this should be the image size after data augment, but before padding. Returns: `List[Dict]`: A list of dictionaries, each dictionary containing the scores, labels and boxes for an image in the batch as predicted by the model. z`post_process` is deprecated and will be removed in v5 of Transformers, please use `post_process_object_detection` instead, with `threshold=0.` for equivalent results.TMake sure that you pass in as many target sizes as the batch dimension of the logitsr0r/TEach element of target_sizes must contain the size (h, w) of each image of the batchdimNscoreslabelsr1)warningswarn FutureWarninglogits pred_boxeslenrashaper#r5sigmoidvaluesindicesr unbindstacktodevicezip)rXoutputs target_sizesr~r1probsryrzimg_himg_w scale_fctslbresultss r+ post_processz!OwlViTImageProcessor.post_processs-"   d   (:(: v;#l+ +st t   a A %st t &b)u||,)/$**1- uKKue  thresholdrc"|j|j}}|"t|t|k7r tdt j |d}t j |j}|j}t|}|t|trMt j|D cgc]} | d c} } t j|D cgc]} | d c} } n|jd\} } t j| | | | gdj|j } || dddddfz}g} t#|||D]3\}}}|||kD}|||kD}|||kD}| j%|||d5| Scc} wcc} w)a| Converts the raw output of [`OwlViTForObjectDetection`] into final bounding boxes in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format. Args: outputs ([`OwlViTObjectDetectionOutput`]): Raw outputs of the model. threshold (`float`, *optional*): Score threshold to keep object detection predictions. target_sizes (`torch.Tensor` or `List[Tuple[int, int]]`, *optional*): Tensor of shape `(batch_size, 2)` or list of tuples (`Tuple[int, int]`) containing the target size `(height, width)` of each image in the batch. If unset, predictions will not be resized. Returns: `List[Dict]`: A list of dictionaries, each dictionary containing the scores, labels and boxes for an image in the batch as predicted by the model. Nrsrurvrr0rx)r~rrrar#r5rrrr isinstancerTensorrrrrrappend)rXrrrr~r1rryrzirrrrrrrscorelabelboxs r+post_process_object_detectionz2OwlViTImageProcessor.post_process_object_detections( (:(:  #6{c,// j &b)u||,)/  #,- L%Aqad%AB L%Aqad%AB+2215 u UE5%$@aHKKELLYIIaqj11E6651 MGAq!a)m$Ea)m$EA M"C NNeusK L  M &B%As / F F cj|j|j}}|"t|t|k7r td||jddk7r tdt j |d}t j|j}t|}|dkrt|jd D]g} t j||  D]I} || | s t|| | ddfjd || d d } d | | <d || | |kD<Ki|t|trMt j |D cgc]} | d  c} } t j |D cgc]} | d c} } n|j#d\} } t j$| | | | gdj'|j(}||dddddfz}g}t j*|}t|jd D]} || }|j-j/s'd |||k<t j |d z}||d zz |dzz }t j0|d d}||| <|| d kD}|| |}|| |}|j3|d|d|Scc} wcc} w)a Converts the output of [`OwlViTForObjectDetection.image_guided_detection`] into the format expected by the COCO api. Args: outputs ([`OwlViTImageGuidedObjectDetectionOutput`]): Raw outputs of the model. threshold (`float`, *optional*, defaults to 0.0): Minimum confidence threshold to use to filter out predicted boxes. nms_threshold (`float`, *optional*, defaults to 0.3): IoU threshold for non-maximum suppression of overlapping boxes. target_sizes (`torch.Tensor`, *optional*): Tensor of shape (batch_size, 2) where each entry is the (height, width) of the corresponding image in the batch. If set, predicted normalized bounding boxes are rescaled to the target sizes. If left to None, predictions will not be unnormalized. Returns: `List[Dict]`: A list of dictionaries, each dictionary containing the scores, labels and boxes for an image in the batch as predicted by the model. All labels are set to None as `OwlViTForObjectDetection.image_guided_detection` perform one-shot object detection. Nrsr0r/rtrurvg?rggư>皙?g?rx)r~target_pred_boxesrrarr#r5rrr rangeargsortrA unsqueezerrtensorrrrr zeros_likenonzeronumelclipr)rXrr nms_thresholdrr~ target_boxesrryidxriousrrrralphas query_scores max_score query_alphasmask box_scoresr1s r+#post_process_image_guided_detectionz8OwlViTImageProcessor.post_process_image_guided_detections, '~~w/H/H   #F s<7H(Hst t  # (:(:1(=(Bst t &b)u||,0 =  3 \//23 <s |4 "<#4QT#:#D#DQ#GVYIZ[\]^_`aD"DG8;F3K} 45 < <  #,- L%Aqad%AB L%Aqad%AB+2215 u UE5%$@aHKKLL_L_`I')AtQJ*??L!!&)++A./ SC!#;L'')//169L 1 2 ,/$6I(IO<SQL ::lC=L&F3K#;?DT*J %d+E NNjD5Q R' S*A&B%As J+/ J0)NN)rN)rg333333?N)!__name__ __module__ __qualname____doc__model_input_namesrBICUBICrNnpndarrayrstrr)rrrrr r&rrFIRSTrboolrrr rqrrrr __classcell__)r[s@r+rCrC\s<"H(( #++%QX?CDH $ zz$ 38n$ %,, $ eC)9$9:; $ $E#/?*?$@A $  $ T?CDH  zz  S>  eC)9$9:;  $E#/?*?$@A     N?CDH lzzlleC)9$9:; l $E#/?*?$@A l  l8%&%))-'+)-.2%)*.'+:>9=;?4D4J4JDHMMD>MtCH~& M % M ! MDcN+MTNM!MtnMU5$u+#567ME%e"456M!z3!78M3 001M$E#/?*?$@AM !M'M^,^_c5"'5=B:tTY{CZ=[5pQr-rC)-rr{typingrrrrrnumpyrimage_processing_utilsr r r image_transformsr r rrr image_utilsrrrrrrrrrrrutilsrrrrr# get_loggerrrmr,r2rArCrKr-r+rs'55UU    ^]   H %G E  z-zr-