§
    ’©ºjì"  ã                   ó˜  — d dl mZ d dlmZmZ d dlmZ d dlmZ d dl	m
Z
 d dlmZ d dlmZ d dlmZ d d	lmZ d d
lmZ d dlmZ d dlmZmZ d dlmZ d dlmZ d dlmZ 	 	 dGdedede ded         def
d„Z!	 	 dHdedede"ded         def
d„Z#dede$eef         fd„Z%	 	 	 	 dIdeded"ee"e$e"e"f         f         d#e"ded         d$eee e$e d%f         f                  defd&„Z&dJdeded(e defd)„Z'	 dKdeded(e d+e(deee         e$ee         ef         f         f
d,„Z)	 dLdededed         defd-„Z*	 	 	 	 	 	 	 	 	 dMdeded5e(d6ee"ee"         f         d7ee ee          f         ded         d"eee"e$e"e"f         f                  d8e"d9e"d:e$e"d%f         d;eed<                  defd=„Z+	 	 	 	 	 	 	 	 	 dNdeded5e(d6ee"ee"         f         d7ee ee          f         ded         d"eee"e$e"e"f         f                  d8e"d9e"d>e(d?e(deee$eef         f         fd@„Z,dOdededB         defdC„Z-	 	 	 dPdeded7ee          d6ee"         deed                  defdF„Z.d!S )Qé    )ÚSequence)ÚOptionalÚUnion)ÚTensor)ÚLiteral)Úspectral_distortion_index)Ú-error_relative_global_dimensionless_synthesis)Úimage_gradients)Úpeak_signal_noise_ratio)Úrelative_average_spectral_error)Ú,root_mean_squared_error_using_sliding_window)Úspectral_angle_mapper)Ú.multiscale_structural_similarity_index_measureÚ#structural_similarity_index_measure)Útotal_variation)Úuniversal_image_quality_index)Ú_deprecated_root_import_funcé   Úelementwise_meanÚpredsÚtargetÚpÚ	reduction)r   ÚsumÚnoneÚreturnc                 óH   — t          dd¦  «         t          | |||¬¦  «        S )zÖWrapper for deprecated import.

    >>> from torch import rand
    >>> preds = rand([16, 3, 16, 16])
    >>> target = rand([16, 3, 16, 16])
    >>> _spectral_distortion_index(preds, target)
    tensor(0.0234)

    r   Úimage©r   r   r   r   )r   r   r   s       úy/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/functional/image/_deprecated.pyÚ_spectral_distortion_indexr!      s-   € õ !Ð!<¸gÑFÔFÐFÝ$¨5¸À1ÐPYÐZÑZÔZÐZó    é   Úratio)r   r   r   Nc                 óH   — t          dd¦  «         t          | |||¬¦  «        S )zæWrapper for deprecated import.

    >>> from torch import rand
    >>> preds = rand([16, 1, 16, 16])
    >>> target = preds * 0.75
    >>> _error_relative_global_dimensionless_synthesis(preds, target).round()
    tensor(10.)

    r	   r   ©r   r   r$   r   )r   r	   r&   s       r    Ú._error_relative_global_dimensionless_synthesisr'   *   s/   € õ !Ð!PÐRYÑZÔZÐZÝ8¸uÈVÐ[`ÐluÐvÑvÔvÐvr"   Úimgc                 óB   — t          dd¦  «         t          | ¬¦  «        S )a–  Wrapper for deprecated import.

    >>> import torch
    >>> image = torch.arange(0, 1*1*5*5, dtype=torch.float32)
    >>> image = torch.reshape(image, (1, 1, 5, 5))
    >>> dy, dx = _image_gradients(image)
    >>> dy[0, 0, :, :]
    tensor([[5., 5., 5., 5., 5.],
            [5., 5., 5., 5., 5.],
            [5., 5., 5., 5., 5.],
            [5., 5., 5., 5., 5.],
            [0., 0., 0., 0., 0.]])

    r
   r   ©r(   )r   r
   r*   s    r    Ú_image_gradientsr+   =   s&   € õ !Ð!2°GÑ<Ô<Ð<Ý˜sÐ#Ñ#Ô#Ð#r"   ç      @ç      $@NÚ
data_rangeÚbaseÚdim.c                 óL   — t          dd¦  «         t          | |||||¬¦  «        S )zêWrapper for deprecated import.

    >>> from torch import tensor
    >>> pred = tensor([[0.0, 1.0], [2.0, 3.0]])
    >>> target = tensor([[3.0, 2.0], [1.0, 0.0]])
    >>> _peak_signal_noise_ratio(pred, target)
    tensor(2.5527)

    r   r   ©r   r   r.   r/   r   r0   )r   r   r2   s         r    Ú_peak_signal_noise_ratior3   P   s;   € õ" !Ð!:¸GÑDÔDÐDÝ"Ø˜F¨zÀÐPYÐ_bðñ ô ð r"   é   Úwindow_sizec                 óF   — t          dd¦  «         t          | ||¬¦  «        S )zÚWrapper for deprecated import.

    >>> from torch import rand
    >>> preds = rand(4, 3, 16, 16)
    >>> target = rand(4, 3, 16, 16)
    >>> _relative_average_spectral_error(preds, target)
    tensor(5326.40...)

    r   r   ©r   r   r5   )r   r   r7   s      r    Ú _relative_average_spectral_errorr8   g   s+   € õ !Ð!BÀGÑLÔLÐLÝ*°¸vÐS^Ð_Ñ_Ô_Ð_r"   FÚreturn_rmse_mapc                 óH   — t          dd¦  «         t          | |||¬¦  «        S )zãWrapper for deprecated import.

    >>> from torch import rand
    >>> preds = rand(4, 3, 16, 16)
    >>> target = rand(4, 3, 16, 16)
    >>> _root_mean_squared_error_using_sliding_window(preds, target)
    tensor(0.4158)

    r   r   ©r   r   r5   r9   )r   r   r;   s       r    Ú-_root_mean_squared_error_using_sliding_windowr<   u   s6   € õ !Ð!OÐQXÑYÔYÐYÝ7Ø˜F°È_ðñ ô ð r"   c                 óF   — t          dd¦  «         t          | ||¬¦  «        S )zÒWrapper for deprecated import.

    >>> from torch import rand
    >>> preds = rand([16, 3, 16, 16])
    >>> target = rand([16, 3, 16, 16])
    >>> _spectral_angle_mapper(preds, target)
    tensor(0.5914)

    r   r   ©r   r   r   )r   r   r>   s      r    Ú_spectral_angle_mapperr?   ‡   s*   € õ !Ð!8¸'ÑBÔBÐBÝ  u°VÀyÐQÑQÔQÐQr"   Tç      ø?é   ç{®Gáz„?ç¸…ëQ¸ž?©gÇº¸�ð¦?g×4ï8EGÒ?g÷äa¡Ö4Ó?g¼?Î?g9EGrùÁ?ÚreluÚgaussian_kernelÚsigmaÚkernel_sizeÚk1Úk2ÚbetasÚ	normalize)rE   Úsimplec                 óV   — t          dd¦  «         t          | |||||||||	|
¬¦  «        S )zóWrapper for deprecated import.

    >>> from torch import rand
    >>> preds = rand([3, 3, 256, 256])
    >>> target = preds * 0.75
    >>> _multiscale_structural_similarity_index_measure(preds, target, data_range=1.0)
    tensor(0.9628)

    r   r   ©r   r   rF   rG   rH   r   r.   rI   rJ   rK   rL   )r   r   rO   s              r    Ú/_multiscale_structural_similarity_index_measurerP   ™   sN   € õ, !Ð!QÐSZÑ[Ô[Ð[Ý9ØØØ'ØØØØØØØØðñ ô ð r"   Úreturn_full_imageÚreturn_contrast_sensitivityc                 óV   — t          dd¦  «         t          | |||||||||	|
¬¦  «        S )zÔWrapper for deprecated import.

    >>> import torch
    >>> preds = torch.rand([3, 3, 256, 256])
    >>> target = preds * 0.75
    >>> _structural_similarity_index_measure(preds, target)
    tensor(0.9219)

    r   r   ©r   r   rF   rG   rH   r   r.   rI   rJ   rQ   rR   )r   r   rT   s              r    Ú$_structural_similarity_index_measurerU   ¿   sM   € õ, !Ð!8¸'ÑBÔBÐBÝ.ØØØ'ØØØØØØØ+Ø$?ðñ ô ð r"   r   )Úmeanr   r   Nc                 óD   — t          dd¦  «         t          | |¬¦  «        S )z™Wrapper for deprecated import.

    >>> from torch import rand
    >>> img = rand(5, 3, 28, 28)
    >>> _total_variation(img)
    tensor(7546.8018)

    r   r   ©r(   r   )r   r   rX   s     r    Ú_total_variationrY   å   s(   € õ !Ð!2°GÑ<Ô<Ð<Ý˜s¨iÐ8Ñ8Ô8Ð8r"   ©rA   rA   ©r@   r@   c                 óJ   — t          dd¦  «         t          | ||||¬¦  «        S )zÍWrapper for deprecated import.

    >>> import torch
    >>> preds = torch.rand([16, 1, 16, 16])
    >>> target = preds * 0.75
    >>> _universal_image_quality_index(preds, target)
    tensor(0.9216)

    r   r   ©r   r   rH   rG   r   )r   r   r]   s        r    Ú_universal_image_quality_indexr^   ò   s;   € õ  !Ð!@À'ÑJÔJÐJÝ(ØØØØØðñ ô ð r"   )r   r   )r#   r   )r,   r-   r   N)r4   )r4   F)r   )	Tr@   rA   r   NrB   rC   rD   rE   )	Tr@   rA   r   NrB   rC   FF)r   )rZ   r[   r   )/Úcollections.abcr   Útypingr   r   Útorchr   Útyping_extensionsr   Ú&torchmetrics.functional.image.d_lambdar   Ú#torchmetrics.functional.image.ergasr	   Ú'torchmetrics.functional.image.gradientsr
   Ú"torchmetrics.functional.image.psnrr   Ú"torchmetrics.functional.image.raser   Ú%torchmetrics.functional.image.rmse_swr   Ú!torchmetrics.functional.image.samr   Ú"torchmetrics.functional.image.ssimr   r   Ú torchmetrics.functional.image.tvr   Ú!torchmetrics.functional.image.uqir   Útorchmetrics.utilities.printsr   Úintr!   Úfloatr'   Útupler+   r3   r8   Úboolr<   r?   rP   rU   rY   r^   © r"   r    ú<module>rs      sK  ðØ $Ð $Ð $Ð $Ð $Ð $Ø "Ð "Ð "Ð "Ð "Ð "Ð "Ð "à Ð Ð Ð Ð Ð Ø %Ð %Ð %Ð %Ð %Ð %à LÐ LÐ LÐ LÐ LÐ LØ ]Ð ]Ð ]Ð ]Ð ]Ð ]Ø CÐ CÐ CÐ CÐ CÐ CØ FÐ FÐ FÐ FÐ FÐ FØ NÐ NÐ NÐ NÐ NÐ NØ ^Ð ^Ð ^Ð ^Ð ^Ð ^Ø CÐ CÐ CÐ CÐ CÐ Cðð ð ð ð ð ð ð ð =Ð <Ð <Ð <Ð <Ð <Ø KÐ KÐ KÐ KÐ KÐ KØ FÐ FÐ FÐ FÐ FÐ Fð Ø<Nð	[ð [Øð[àð[ð ð[ð Ð8Ô9ð	[ð
 ð[ð [ð [ð [ð, ØBTð	wð wØðwàðwð ðwð Ð>Ô?ð	wð
 ðwð wð wð wð&$˜&ð $ U¨6°6¨>Ô%:ð $ð $ð $ð $ð, 58ØØBTØ15ðð Øðàðð �e˜U 5¨% <Ô0Ð0Ô1ðð ð	ð
 Ð>Ô?ðð 
�%˜˜U 3¨ 8œ_Ð,Ô-Ô	.ðð ðð ð ð ð.`ð `¨Fð `¸Fð `ÐQTð `Ð]cð `ð `ð `ð `ð RWðð ØðØ!ðØ03ðØJNðà
ˆ8�FÔ˜U 8¨FÔ#3°VÐ#;Ô<Ð<Ô=ðð ð ð ð* CUðRð RØðRàðRð Ð>Ô?ðRð ð	Rð Rð Rð Rð* !Ø+.Ø-/ØBTØ>BØØØGØ5;ð#ð #Øð#àð#ð ð#ð �˜ œÐ'Ô(ð	#ð
 �s˜H SœMÐ)Ô*ð#ð Ð>Ô?ð#ð ˜˜u e¨E°5¨LÔ&9Ð9Ô:Ô;ð#ð 	ð#ð 	ð#ð �˜�Ôð#ð ˜Ð 0Ô1Ô2ð#ð ð#ð #ð #ð #ðR !Ø+.Ø-/ØBTØ>BØØØ#Ø(-ð#ð #Øð#àð#ð ð#ð �˜ œÐ'Ô(ð	#ð
 �s˜H SœMÐ)Ô*ð#ð Ð>Ô?ð#ð ˜˜u e¨E°5¨LÔ&9Ð9Ô:Ô;ð#ð 	ð#ð 	ð#ð ð#ð "&ð#ð ˆ6�5˜ ˜Ô(Ð(Ô)ð#ð #ð #ð #ðL
9ð 
9˜&ð 
9¨WÐ5PÔ-Qð 
9Ð^dð 
9ð 
9ð 
9ð 
9ð  "*Ø'ØFXðð Øðàðð ˜#”ðð �EŒ?ð	ð
 ˜Ð AÔBÔCðð ðð ð ð ð ð r"   