o )iSn @sddlZddlmZddlmZmZmZmZddlZddlm Z ddl m Z m Z gdZde d ed ed e d eeef d dZGdddeZGdddejjZGdddejjZGdddejjZGdddejjZdS)N)Enum)DictListOptionalTuple)Tensor) functionalInterpolationMode)AutoAugmentPolicy AutoAugment RandAugmentTrivialAugmentWideAugMiximgop_name magnitude interpolationfillc Cs|dkrtj|dddgdtt|dg||ddgd}|S|dkr>tj|dddgddtt|g||ddgd}|S|dkrVtj|dt|dgd|ddg|d}|S|d krntj|ddt|gd|ddg|d}|S|d kr}tj||||d }|S|d krt|d|}|S|d krt|d|}|S|dkrt |d|}|S|dkrt |d|}|S|dkrt |t|}|S|dkrt ||}|S|dkrt |}|S|dkrt|}|S|dkrt|}|S|dkr |Std|d)NShearXr?)angle translatescaleshearrrcenterShearY TranslateX)rrrrrr TranslateYRotaterr BrightnessColorContrast Sharpness PosterizeSolarize AutoContrastEqualizeInvertIdentityzThe provided operator  is not recognized.)FZaffinemathdegreesatanintrotateZadjust_brightnessZadjust_saturationZadjust_contrastZadjust_sharpnessZ posterizeZsolarizeZ autocontrastZequalizeinvert ValueError)rrrrrr5q/var/www/html/eduruby.in/lip-sync/lip-sync-env/lib/python3.10/site-packages/torchvision/transforms/autoaugment.py _apply_op sC6 + !       r7c@seZdZdZdZdZdZdS)r zoAutoAugment policies learned on different datasets. Available policies are IMAGENET, CIFAR10 and SVHN. ZimagenetZcifar10ZsvhnN)__name__ __module__ __qualname____doc__IMAGENETCIFAR10SVHNr5r5r5r6r ]s r c seZdZdZejejdfdededee e ddffdd Z dede e e e e eefe e e eefffd d Zd ed e eefdee e eefffd dZedede eeeffddZdedefddZde fddZZS)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. Npolicyrrreturncs,t||_||_||_|||_dSN)super__init__r?rr _get_policiespolicies)selfr?rr __class__r5r6rCys zAutoAugment.__init__cCsF|tjkr gdS|tjkrgdS|tjkrgdStd|d)N)))r&皙?)r 333333? )r'rKr(rKNr)皙?Nr)rKN))r&rK)r&rKr)rIN)r'皙?)rWr rRrJ))r'rKrS))r&rRrNr)rN))r rXr[)r'rKrJ)rS)r&rIrU)rZr#rIr))r rIrLrS))r)rNrQr*rKNr\)r#rKrY)r$rrJ)rZ)r#r))r#rRrJ)r'rRrT))r%rIrTr_))rrKrNr\)r]rSrVrMr^r`rP))r*皙?N)r$rXrU))r ffffff?ra)r333333?rL))r%rRr)r%?r[))r?rJrrdrL))r(rgNr)rfN))rrXrT)r&rerT))r#rIr[)r"rKrT))r%rerL)r"rdrL)rS)r)rgN))r$rKrT)r%rKrN))r#rdrT)rrgrJ))r)reN)r(rIN))rrIr[)r%rXrU))r"rfrU)r#rXrJ))r'rgra)r*rN)r)rXNrO)rjrS))r#rfrLrS)r(rRN)r'rXrJ))r"rcr[)r#rdr))r'rIrNr(rfN))rrfrLrh)rl)r'rRr[)rQrb)rhrl))rrfrY)r*rXN)rrfrJr*rdN)rS)r'rKrUr*rfNrSrS)r rfr[)rmrk)rn)r*rIN))rrfrN)r'rXrU)rqrkrr)rm)r'rer[))rrRrJro)ri)rrKrUrp))r$rer[r rRrY)r*rRN)rrra))rrdrU)r'rIrJ)r_rs))rrerT)rrfr[))rrcrUr_))r'rdra)rrKrT))rrRrYrt))rrdrL)rrRr[))rrRrN)r(rdN))rrdrarbzThe provided policy r,)r r<r=r>r4)rFr?r5r5r6rDs   zAutoAugment._get_policiesnum_bins image_sizecCstdd|dftdd|dftdd|d|dftdd|d|dftdd|dftdd|dftdd|dftdd|dftdd|dfd t||dd d ftd d|d ftdd ftdd ftdd fd S)NrreTt?rr>@rfrJrYFo@)rrrrr r"r#r$r%r&r'r(r)r*)torchlinspacearangeroundr1tensorrFrurvr5r5r6_augmentation_spaces$   zAutoAugment._augmentation_space transform_numcCs4tt|d}td}tdd}|||fS)zGet parameters for autoaugment transformation Returns: params required by the autoaugment transformation r)rara)r1rzrandintitemZrand)rZ policy_idprobssignsr5r5r6 get_paramss   zAutoAugment.get_paramsrcCs|j}t|\}}}t|tr*t|ttfrt|g|}n |dur*dd|D}|t|j \}}}| d||f} t |j |D]7\} \} } } || | kr{| | \}}| durct||  nd}|rq|| dkrq|d9}t || ||j|d}qD|S) z img (PIL Image or Tensor): Image to be transformed. Returns: PIL Image or Tensor: AutoAugmented image. NcSg|]}t|qSr5float.0fr5r5r6 z'AutoAugment.forward.. rrr!)rr-get_dimensions isinstancerr1rrlenrEr enumeraterr7r)rFrrchannelsheightwidthZ transform_idrrop_metairpZ magnitude_id magnitudessignedrr5r5r6forwards$   zAutoAugment.forwardcCs|jjd|jd|jdS)Nz(policy=, fill=))rHr8r?r)rFr5r5r6__repr__szAutoAugment.__repr__)r8r9r:r;r r<r NEARESTrrrrCrstrr1rDrrboolr staticmethodrrr __classcell__r5r5rGr6r hs0  * .Z r c seZdZdZdddejdfdededed ed eee d df fd d Z dede eefd e e e eefffddZded efddZd e fddZZS)r a~RandAugment data augmentation method based on `"RandAugment: Practical automated data augmentation with a reduced search space" `_. 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. rarLNnum_opsrnum_magnitude_binsrrr@cs,t||_||_||_||_||_dSrA)rBrCrrrrr)rFrrrrrrGr5r6rC2s  zRandAugment.__init__rurvcCstddftdd|dftdd|dftdd|d|dftdd|d|dftdd|dftdd |dftdd |dftdd |dftdd |dfd t||dd dftd d|dftddftddfd S)NrFreTrwrrrxrfrJrYryr+rrrrr r"r#r$r%r&r'r(r)rzr~r{r|r}r1rr5r5r6rAs $  zRandAugment._augmentation_spacerc Cs|j}t|\}}}t|tr*t|ttfrt|g|}n |dur*dd|D}||j||f}t |j D]B}tt t |d}t||} || \} } | jdkrbt| |jnd} | rpt ddrp| d9} t|| | |j|d }q8|S) img (PIL Image or Tensor): Image to be transformed. Returns: PIL Image or Tensor: Transformed image. NcSrr5rrr5r5r6rarz'RandAugment.forward..rrrrarr!)rr-rrrr1rrrrangerrzrrrlistkeysndimrr7r) rFrrrrrr_op_indexrrrrr5r5r6rTs"   zRandAugment.forwardc Cs:|jjd|jd|jd|jd|jd|jd }|S)Nz (num_ops=z , magnitude=z, num_magnitude_bins=, interpolation=rr)rHr8rrrrrrFsr5r5r6ros  zRandAugment.__repr__)r8r9r:r;r rr1rrrrCrrrrrrrrrr5r5rGr6r s. .r c seZdZdZdejdfdededeee ddffdd Z d ede e e eefffd d Zd edefddZde fddZZS)raDataset-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. rNrrrr@cs t||_||_||_dSrA)rBrCrrr)rFrrrrGr5r6rCs  zTrivialAugmentWide.__init__rucCstddftdd|dftdd|dftdd|dftdd|dftdd|dftdd|dftdd|dftdd|dftdd|dfdt||dd dftd d|dftddftddfd S) NrFgGz?Tg@@g`@rJrrUryrr)rFrur5r5r6rs $  z&TrivialAugmentWide._augmentation_spacerc Cs|j}t|\}}}t|tr*t|ttfrt|g|}n |dur*dd|D}||j}tt t |d }t ||}||\} } | jdkr`t| t j t | dt jd nd} | rnt ddrn| d 9} t||| |j|d S) rNcSrr5rrr5r5r6rrz.TrivialAugmentWide.forward..rrdtyperrarr!)rr-rrrr1rrrrzrrrrrrlongr7r) rFrrrrrrrrrrrr5r5r6rs$    "zTrivialAugmentWide.forwardcCs*|jjd|jd|jd|jd}|S)Nz(num_magnitude_bins=rrr)rHr8rrrrr5r5r6rs zTrivialAugmentWide.__repr__)r8r9r:r;r rr1rrrrCrrrrrrrrrr5r5rGr6r|s" " rcseZdZdZdddddejdfdeded ed ed ed ed e e eddffdd Z dede eefde ee eefffddZejjdefddZejjdefddZdedefddZdedefddZdefd d!ZZS)"raAugMix 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. r[rTNseverity mixture_width chain_depthalphaall_opsrrr@csntd|_d|kr|jks ntd|jd|d||_||_||_||_||_||_ ||_ dS)Nrrz!The severity must be between [1, z]. Got z instead.) rBrC_PARAMETER_MAXr4rrrrrrr)rFrrrrrrrrGr5r6rCs  zAugMix.__init__rurvc Cstdd|dftdd|dftd|dd|dftd|dd|dftdd|dfdt||ddd ftd d|d ftdd ftdd fd }|jr|tdd |dftdd |dftdd |dftdd |dfd |S)NrreTrg@rrxrYFry) rrrrr r&r'r(r)rf)r"r#r$r%)rzr{r|r}r1r~rupdate)rFrurvrr5r5r6rs&$   zAugMix._augmentation_spacecC t|SrA)r-Z pil_to_tensorrFrr5r5r6_pil_to_tensor zAugMix._pil_to_tensorrcCrrA)r-Z to_pil_imagerr5r5r6_tensor_to_pilrzAugMix._tensor_to_pilparamscCrrA)rz_sample_dirichlet)rFrr5r5r6rrzAugMix._sample_dirichletorig_imgc Cst|j}t|\}}}t|tr-|}t|ttfr!t|g|}n|dur,dd|D}n||}||j ||f}t |j }| dgt d|jd|} | dgdg| jd} |tj|j|jg| jd| dd} |tj|jg|j| jd| dd| dddf | ddg} | dddf | | } t|jD]x}| }|jdkr|jn ttjddd d }t|D]K}ttt|d }t ||}||\}}|jdkrt|tj|jd tjd nd }|rtd d r|d9}t||||j |d}q| !| dd|f | |q| |j"|j#d } t|ts8|$| S| S)rNcSrr5rrr5r5r6r/rz"AugMix.forward..rrYr)devicerr)lowhighsizerrrarr!)%rr-rrrr1rrrrrshapeviewmaxrrrrzr~rrexpandrrrrrrrrrr7rZadd_torr)rFrrrrrrrZ orig_dimsbatchZ batch_dimsmZcombined_weightsZmixraugdepthrrrrrrr5r5r6r!sT    "$(    "  zAugMix.forwardcCsJ|jjd|jd|jd|jd|jd|jd|jd|jd}|S) Nz (severity=z, mixture_width=z, chain_depth=z, alpha=z , all_ops=rrr) rHr8rrrrrrrrr5r5r6r[s"  zAugMix.__repr__)r8r9r:r;r ZBILINEARr1rrrrrCrrrrrrzZjitZunusedrrrrrrr5r5rGr6rsD  .:r)r.enumrtypingrrrrrzrr r-r __all__rrr7r nnModuler r rrr5r5r5r6s0    P 8]V