Yh@n bddlZddlmZddlmZddlZddlmZddlmZ m Z gdZ ded e d e d e d eee f d ZGddeZGddejjZGddejjZGddejjZGddejjZdS)N)Enum)Optional)Tensor) functionalInterpolationMode)AutoAugmentPolicy AutoAugment RandAugmentTrivialAugmentWideAugMiximgop_name magnitude interpolationfillc |dkrHtj|dddgdtjtj|dg||ddg}n|dkrHtj|dddgddtjtj|g||ddg}n|dkr.tj|dt |dgd|ddg|}n|d kr.tj|ddt |gd|ddg|}nM|d krtj|||| }n-|d krtj|d|z}n |d krtj|d|z}n|dkrtj |d|z}n|dkrtj |d|z}n|dkr#tj |t |}n|dkrtj ||}nk|dkrtj |}nP|dkrtj|}n5|dkrtj|}n|dkrnt!d|d|S)NShearXr?)angle translatescaleshearrrcenterShearY TranslateX)rrrrrr TranslateYRotaterr BrightnessColorContrast Sharpness PosterizeSolarize AutoContrastEqualizeInvertIdentityzThe provided operator  is not recognized.)Faffinemathdegreesatanintrotateadjust_brightnessadjust_saturationadjust_contrastadjust_sharpness posterizesolarize autocontrastequalizeinvert ValueError)rrrrrs t/var/www/tools.fuzzalab.pt/emblema-extractor/venv/lib/python3.11/site-packages/torchvision/transforms/autoaugment.py _apply_opr> s(h !f< ) 4 455s;'q6     H  h !f TYy%9%9::;'q6     L h 9~~q)'*    L h #i..)'*    H  hsI]NNN L !#sY77 G  !#sY77 J  S9_55 K   cIo66 K  k#s9~~.. J  ji(( N " "nS!! J  joo H  hsmm J   N'NNNOOO JceZdZdZdZdZdZdS)r zoAutoAugment policies learned on different datasets. Available policies are IMAGENET, CIFAR10 and SVHN. imagenetcifar10svhnN)__name__ __module__ __qualname____doc__IMAGENETCIFAR10SVHNr?r=r r ]s)HG DDDr?r c beZdZdZejejdfdededee e ddffd Z dede e e e e eefe e e eefffdZd ed e eefdee e eefffd Zed ede eeeffd ZdedefdZde fdZxZS)r a?AutoAugment data augmentation method based on `"AutoAugment: Learning Augmentation Strategies from Data" `_. If the image is torch Tensor, it should be of type torch.uint8, and it is expected to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode "L" or "RGB". Args: policy (AutoAugmentPolicy): Desired policy enum defined by :class:`torchvision.transforms.autoaugment.AutoAugmentPolicy`. Default is ``AutoAugmentPolicy.IMAGENET``. interpolation (InterpolationMode): Desired interpolation enum defined by :class:`torchvision.transforms.InterpolationMode`. Default is ``InterpolationMode.NEAREST``. If input is Tensor, only ``InterpolationMode.NEAREST``, ``InterpolationMode.BILINEAR`` are supported. fill (sequence or number, optional): Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively. Npolicyrrreturnct||_||_||_|||_dSN)super__init__rMrr _get_policiespolicies)selfrMrr __class__s r=rRzAutoAugment.__init__ysJ  * **622 r?c|tjkrgdS|tjkrgdS|tjkrgdSt d|d)N)))r%皙?)r333333? )r&rZr'rZNr(皙?Nr(rZN))r%rZ)r%rZr(rXN)r&皙?)rfrrarY))r&rZrb))r%rar]r(rN))rrgrj)r&rZrY)rb)r%rXrd)rir"rXr))rrXr[rb))r(rNr`r)rZNrk)r"rZrh)r#rrY)ri)r"r))r"rarY)r&rarc))r$rXrcrn))rrZr]rk)rlrbrer\rmror_))r)皙?N)r#rgrd))rffffff?rp)r333333?r[))r$rar)r$?rj))r?rYrrsr[))r'rvNr(ruN))rrgrc)r%rtrc))r"rXrj)r!rZrc))r$rtr[)r!rsr[)rb)r(rvN))r#rZrc)r$rZr]))r"rsrc)rrvrY))r(rtN)r'rXN))rrXrj)r$rgrd))r!rurd)r"rgrY))r&rvrp)r)rN)r(rgNr^)ryrb))r"rur[rb)r'raN)r&rgrY))r!rrrj)r"rsr))r&rXr]r'ruN))rrur[rw)r{)r&rarj)r`rq)rwr{))rrurh)r)rgN)rrurYr)rsN)rb)r&rZrdr)ruNrbrb)rrurj)r|rz)r})r)rXN))rrur])r&rgrd)rrzr)r|)r&rtrj))rrarYr~)rx)rrZrdr))r#rtrjrrarh)r)raN)rrrp))rrsrd)r&rXrY)rnr))rrtrc)rrurj))rrrrdrn))r&rsrp)rrZrc))rrarhr))rrsr[)rrarj))rrar])r'rsN))rrsrprqzThe provided policy r+)r rHrIrJr<)rUrMs r=rSzAutoAugment._get_policiess &/ / / 6(0 0 0 6(- - - 8OFOOOPP Pr?num_bins image_sizectjdd|dftjdd|dftjdd|dz|dftjdd|dz|dftjdd|dftjdd|dftjdd|dftjdd|dftjdd|dfd tj||dz d z z z d ftjd d|d ftjdd ftjdd ftjdd fd S)NrrtTt?rr>@rurYrhFo@)rrrrrr!r"r#r$r%r&r'r(r))torchlinspacearangeroundr1tensorrUrrs r=_augmentation_spacezAutoAugment._augmentation_spacesw~c3994@~c3994@ >#}z!}/LhWWY]^ >#}z!}/LhWWY]^~c4::DA >#sH==tDnS#x88$?S(;;TB.c8<t|t t frt |g|z}n| d|D}|t|j \}}}| d||f} t|j |D]w\} \} } } || | krb| | \}}| 't ||  nd}|r|| dkr|dz}t|| ||j|}x|S)z img (PIL Image or Tensor): Image to be transformed. Returns: PIL Image or Tensor: AutoAugmented image. Nc,g|]}t|SrKfloat.0fs r= z'AutoAugment.forward.. ///Qa///r? rrr )rr,get_dimensions isinstancerr1rrlenrTr enumeraterr>r)rUrrchannelsheightwidth transform_idrrop_metairp magnitude_id magnitudessignedrs r=forwardzAutoAugment.forwardscy"#"23"7"7&% c6 " " 0$e -- 0d }x/!//$///%)__S5G5G%H%H" eU**2??-6t}\7R-S-S f f )A)LQx1}}%,W%5" FFRF^E*\":"?"?"A"ABBBdg &eAh!mm%IWitGY`deee r?c@|jjd|jd|jdS)Nz(policy=, fill=))rVrDrMr)rUs r=__repr__zAutoAugment.__repr__s*.)SS4;SStySSSSr?)rDrErFrGr rHrNEARESTrlistrrRtuplestrr1rSdictrboolr staticmethodrrr __classcell__rVs@r=r r hs$%6$>+<+D&* 3 3! 3) 3tE{# 3  3 3 3 3 3 3XQ'XQ eE#uhsm34eCQT `_. If the image is torch Tensor, it should be of type torch.uint8, and it is expected to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode "L" or "RGB". Args: num_ops (int): Number of augmentation transformations to apply sequentially. magnitude (int): Magnitude for all the transformations. num_magnitude_bins (int): The number of different magnitude values. interpolation (InterpolationMode): Desired interpolation enum defined by :class:`torchvision.transforms.InterpolationMode`. Default is ``InterpolationMode.NEAREST``. If input is Tensor, only ``InterpolationMode.NEAREST``, ``InterpolationMode.BILINEAR`` are supported. fill (sequence or number, optional): Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively. rpr[Nnum_opsrnum_magnitude_binsrrrNct||_||_||_||_||_dSrP)rQrRrrrrr)rUrrrrrrVs r=rRzRandAugment.__init__2sD  ""4* r?rrctjddftjdd|dftjdd|dftjdd|dz|dftjdd|dz|dftjdd|dftjdd |dftjdd |dftjdd |dftjdd |dfd tj||dz d z z z dftjd d|dftjddftjddfd S)NrFrtTrrrrrurYrhrr*rrrrrr!r"r#r$r%r&r'r(rrrrrr1rs r=rzRandAugment._augmentation_spaceAswc**E2~c3994@~c3994@ >#}z!}/LhWWY]^ >#}z!}/LhWWY]^~c4::DA >#sH==tDnS#x88$?S(;;TB.c8<t|t t frt |g|z}n| d|D}||j||f}t|j D]}t tj t|d}t||} || \} } | jdkr,t | |jnd} | rtj ddr| dz} t'|| | |j|}|S) img (PIL Image or Tensor): Image to be transformed. Returns: PIL Image or Tensor: Transformed image. Nc,g|]}t|SrKrrs r=rz'RandAugment.forward..arr?rrrrprr )rr,rrrr1rrrrangerrrrrrkeysndimrr>r) rUrrrrrr_op_indexrrrrs r=rzRandAugment.forwardTs}y"#"23"7"7&% c6 " " 0$e -- 0d }x/!//$///**4+BVUOTTt|$$ b bA5=Wt<<AACCDDH7<<>>**84G!(!1 JDNOVWDWDWj8==??@@@]`I "%-400 "T! C)4CU\`aaaCC r?c t|jjd|jd|jd|jd|jd|jd }|S)Nz (num_ops=z , magnitude=z, num_magnitude_bins=, interpolation=rr)rVrDrrrrrrUss r=rzRandAugment.__repr__osx~&  |  >  %)$;   $1    i     r?)rDrErFrGrrr1rrrrRrrrrrrrrrrs@r=r r s*("$+<+D&*      )  tE{#         C U38_ QUVY[`agimam[nVnQo    &6f6 #        r?r c eZdZdZdejdfdededeee ddffd Z d ede e e eefffd Zd edefd Zde fd ZxZS)r aDataset-independent data-augmentation with TrivialAugment Wide, as described in `"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation" `_. If the image is torch Tensor, it should be of type torch.uint8, and it is expected to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode "L" or "RGB". Args: num_magnitude_bins (int): The number of different magnitude values. interpolation (InterpolationMode): Desired interpolation enum defined by :class:`torchvision.transforms.InterpolationMode`. Default is ``InterpolationMode.NEAREST``. If input is Tensor, only ``InterpolationMode.NEAREST``, ``InterpolationMode.BILINEAR`` are supported. fill (sequence or number, optional): Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively. rNrrrrNcrt||_||_||_dSrP)rQrRrrr)rUrrrrVs r=rRzTrivialAugmentWide.__init__s6 "4* r?rctjddftjdd|dftjdd|dftjdd|dftjdd|dftjdd|dftjdd|dftjdd|dftjdd|dftjdd|dfdtj||dz d z z z dftjd d|dftjddftjddfd S) NrFgGz?Tg@@g`@rYrrdrrr)rUrs r=rz&TrivialAugmentWide._augmentation_spacescc**E2~c4::DA~c4::DA >#tX>>E >#tX>>E~c5(;;TB >#tX>>EnS$994@T8<t|t t frt |g|z}n| d|D}||j}t tj t|d }t||}||\} } | jdkrSt | tj t| dtj nd} | rtj ddr| dz} t#||| |j| S) rNc,g|]}t|SrKrrs r=rz.TrivialAugmentWide.forward..rr?rrdtyperrprr )rr,rrrr1rrrrrrrrrrlongr>r) rUrrrrrrrrrrrs r=rzTrivialAugmentWide.forwardsvy"#"23"7"7&% c6 " " 0$e -- 0d }x/!//$///**4+BCCu}S\\488==??@@w||~~&&x0$W- F"" *U]3z??D SSSTYY[[ \ \ \   emAt,,   Igy@RY]^^^^r?cT|jjd|jd|jd|jd}|S)Nz(num_magnitude_bins=rrr)rVrDrrrrs r=rzTrivialAugmentWide.__repr__sV~&  "&"9  #1  i    r?)rDrErFrGrrr1rrrrRrrrrrrrrrrs@r=r r |s  "#%+<+D&*   ) tE{#         C DeFDL>Q9Q4R    &_6_f____:#r?r cFeZdZdZdddddejdfdeded ed ed ed ed e e eddffd Z dede eefde ee eefffdZejjdefdZejjdefdZdedefdZdedefdZdefdZxZS)r aAugMix data augmentation method based on `"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty" `_. If the image is torch Tensor, it should be of type torch.uint8, and it is expected to have [..., 1 or 3, H, W] shape, where ... means an arbitrary number of leading dimensions. If img is PIL Image, it is expected to be in mode "L" or "RGB". Args: severity (int): The severity of base augmentation operators. Default is ``3``. mixture_width (int): The number of augmentation chains. Default is ``3``. chain_depth (int): The depth of augmentation chains. A negative value denotes stochastic depth sampled from the interval [1, 3]. Default is ``-1``. alpha (float): The hyperparameter for the probability distributions. Default is ``1.0``. all_ops (bool): Use all operations (including brightness, contrast, color and sharpness). Default is ``True``. interpolation (InterpolationMode): Desired interpolation enum defined by :class:`torchvision.transforms.InterpolationMode`. Default is ``InterpolationMode.NEAREST``. If input is Tensor, only ``InterpolationMode.NEAREST``, ``InterpolationMode.BILINEAR`` are supported. fill (sequence or number, optional): Pixel fill value for the area outside the transformed image. If given a number, the value is used for all bands respectively. rjrTNseverity mixture_width chain_depthalphaall_opsrrrNctd|_d|cxkr |jksntd|jd|d||_||_||_||_||_||_ ||_ dS)Nrrz!The severity must be between [1, z]. Got z instead.) rQrR_PARAMETER_MAXr<rrrrrrr) rUrrrrrrrrVs r=rRzAugMix.__init__s  X4444!44444pATpp]epppqq q  *&  * r?rrc tjdd|dftjdd|dftjd|ddz |dftjd|ddz |dftjdd|dfdtj||dz dz z z d ftjd d|d ftjdd ftjdd fd }|jrr|tjdd |dftjdd |dftjdd |dftjdd |dfd |S)NrrtTrg@rrrhFr) rrrrrr%r&r'r(ru)r!r"r#r$)rrrrr1rrupdate)rUrrrs r=rzAugMix._augmentation_spaces~c3994@~c3994@ >#z!}s/BHMMtT >#z!}s/BHMMtT~c4::DAu|H55(Q,!9KLSSUUYY[[[]bcsH==uE"\#..6c**E2  <  HH#(>#sH#E#Et"L#nS#x@@$G!&S(!C!CT J"'.c8"D"Dd!K    r?c*tj|SrP)r, pil_to_tensorrUrs r=_pil_to_tensorzAugMix._pil_to_tensorss###r?rc*tj|SrP)r, to_pil_imagers r=_tensor_to_pilzAugMix._tensor_to_pils~c"""r?paramsc*tj|SrP)r_sample_dirichlet)rUrs r=rzAugMix._sample_dirichlets&v...r?orig_imgc |j}tj|\}}}t|trA|}t|t t frt |g|z}n$| d|D}n||}||j ||f}t|j }| dgtd|jz dz|z} | dgdg| jdz zz} |t#j|j|jg| j| dd} |t#j|jg|jz| j| dd| dddf | ddgz} | dddf | | z} t/|jD]}| }|jdkr|jn5t t#jddd }t/|D]}t t#jt7|d}t||}||\}}|jdkrKt |t#j|jdt"j nd }|rt#jd dr|d z}t?||||j |}| !| dd|f | |z| |"|j# } t|ts|$| S| S)rNc,g|]}t|SrKrrs r=rz"AugMix.forward../rr?rrhr)devicerr)lowhighsizerrrprr )%rr,rrrr1rrrrrshapeviewmaxrrrrrrrexpandrrrrrrrrrr>radd_torr)rUrrrrrrr orig_dimsbatch batch_dimsmcombined_weightsmixraugdepthrrrrrrs r=rzAugMix.forward!sy"#"28"<"<&% h ' ' 0C$e -- 0d }x/!//$///%%h//C**4+>PPOO !s1sx<333i?@@jjmm_sej1n'==   " " L$*dj1%, G G G N NzZ[}^` a a    11 L$*(::5< P P P W WXbcdXegi j j  aaadGLL*Q-, - -.1gll:&&.t)** D DAC(,(81(<(r nnModuler r r r rKr?r=rs  00000000 ] ] ]M MM*/M@QMYabfglbmYnMMMM`tTtTtTtTtT%(/tTtTtTnZZZZZ%(/ZZZzSSSSSSSSlUUUUUUX_UUUUUr?