sgH;^dZddlmZmZmZmZmZmZddlZ ddl m Z m Z ddl mZmZmZddlmZmZddlmZmZmZmZmZmZmZdd lmZmZmZe rddl Z erd d l!m"Z"e rddl#Z#ejHe%Z& dd ed eee'effdZ( dd ed eee'efdefdZ)GddeZ*y)z%Image processor class for SuperPoint.) TYPE_CHECKINGDictListOptionalTupleUnionN)is_torch_availableis_vision_available)BaseImageProcessor BatchFeature get_size_dict)resizeto_channel_dimension_format)ChannelDimension ImageInputinfer_channel_dimension_formatis_scaled_imagemake_list_of_imagesto_numpy_array valid_images) TensorTypeloggingrequires_backends)#SuperPointKeypointDescriptionOutputimageinput_data_formatcH|tjk(r>tj|d|dk(xrtj|d|dk(S|tjk(r>tj|d|dk(xrtj|d|dk(Sy)Nr.r...r.r.r#)rFIRSTnpallLAST)rrs m/var/www/html/venv/lib/python3.12/site-packages/transformers/models/superpoint/image_processing_superpoint.py is_grayscaler,/s,222vveFmuV}45`"&&vRWX^R_A_:`` .33 3vveFmuV}45`"&&vRWX^R_A_:`` 4returncttdgt|tjr|t j k(r7|ddz|ddzz|ddzz}tj|gdzd }|S|t jk(r5|d dz|d dzz|d dzz}tj|gdzd }St|tjjs|S|jd}|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 gŏ1w-!?r!gbX9?r"gv/?r r)axisr$r%r&L) rconvert_to_grayscale isinstancer(ndarrayrr'stackr*PILImageconvert)rr gray_images r+r4r49s$*XJ7%$  0 6 6 6v/%-&2HH5QW=[aKaaJ:,"2;J"2"7"7 7v/%-&2HH5QW=[aKaaJ:,"2= 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`. 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`. 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. FrFzkInvalid image type. Must be of type PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray.z,Size must be specified if do_resize is True.z7Rescale factor must be specified if do_rescale is True.rzIt 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.)rr@r)rscaler)r)input_channel_dimr>)data tensor_type)r?rArBr@rrr ValueErrorrrlogger warning_oncerrrescalerangelenr,r4rr ) rKimagesr?r@rArBrPrNrrLrirTs r+ preprocessz#SuperPointImageProcessor.preprocesssd"+!6IDNN #-#9Zt +9+E4K^K^'tTYYTU;$V,F#:  KL L .0VW W6<vay I  lrschdkkDL]k^sFs $ 5Rc dF  $ >vay I s6{# aAq +<=0N_`q  a ou ej '{N_ `  '>BBI=t sF FF"0F'outputsr target_sizesz torch.Tensorct|jt|k7r tdt|trt j |}n|jddk7r td|}t j|dg}|j|dddfz}|jt j}g}t|j||j|jD]O\}}}} t j|j!d} || }|| }| | } |j#||| dQ|S)a Converts the raw output of [`SuperPointForKeypointDetection`] into lists of keypoints, scores and descriptors with coordinates absolute to the original image sizes. Args: outputs ([`SuperPointKeypointDescriptionOutput`]): Raw outputs of the model containing keypoints in a relative (x, y) format, with scores and descriptors. target_sizes (`torch.Tensor` or `List[Tuple[int, int]]`): 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. This must be the original image size (before any processing). Returns: `List[Dict]`: A list of dictionaries, each dictionary containing the keypoints in absolute format according to target_sizes, scores and descriptors for an image in the batch as predicted by the model. zRMake sure that you pass in as many target sizes as the batch dimension of the maskrr#zTEach element of target_sizes must contain the size (h, w) of each image of the batchN) keypointsscores descriptors)r[maskrVr5rtorchtensorshapefliprbtoint32ziprcrdnonzerosqueezeappend) rKr_r` image_sizesmasked_keypointsresults image_maskrbrcrdindicess r+post_process_keypoint_detectionz8SuperPointImageProcessor.post_process_keypoint_detections<$ w|| L 1 1qr r lD ),,|4K!!!$) j'Kjjqc2 ",,{1d7/CC,..u{{;:= LL*GNNG(>DHlClC38n lC  lC  lC!sJ!78lC&lC$E#/?*?$@AlC lC\/</LQR\^bch^iRiLj/ d3&' (/r-r=)N)+rytypingrrrrrrnumpyr(r r image_processing_utilsr r rimage_transformsrr image_utilsrrrrrrrutilsrrrrfmodeling_superpointrr8 get_loggerrvrWr|r,r4r=rHr-r+rs,DD7UUC<;H   H % AEa ac+;&; <=aAE! !c+;&; <=!!Hj1jr-