o &j8@sdZddlmZmZmZddlZddlmZ ddlm Z ddlm Z dd lm Z dd lmZdd lmZdd lmZGd dde jZdS)zxAugmenters that are collections of other augmenters. List of augmenters: * :class:`RandAugment` Added in 0.4.0. )print_functiondivisionabsolute_importN) parameters)random)meta) arithmetic)flip)pillike)sizecsLeZdZdZdZ   dfdd Zed d Zed d ZddZ Z S) RandAugmentaApply RandAugment to inputs as described in the corresponding paper. See paper:: Cubuk et al. RandAugment: Practical automated data augmentation with a reduced search space .. note:: The paper contains essentially no hyperparameters for the individual augmentation techniques. The hyperparameters used here come mostly from the official code repository, which however seems to only contain code for CIFAR10 and SVHN, not for ImageNet. So some guesswork was involved and a few of the hyperparameters were also taken from https://github.com/ildoonet/pytorch-randaugment/blob/master/RandAugment/augmentations.py . This implementation deviates from the code repository for all PIL enhance operations. In the repository these use a factor of ``0.1 + M*1.8/M_max``, which would lead to a factor of ``0.1`` for the weakest ``M`` of ``M=0``. For e.g. ``Brightness`` that would result in a basically black image. This definition is fine for AutoAugment (from where the code and hyperparameters are copied), which optimizes each transformation's ``M`` individually, but not for RandAugment, which uses a single fixed ``M``. We hence redefine these hyperparameters to ``1.0 + S * M * 0.9/M_max``, where ``S`` is randomly either ``1`` or ``-1``. We also note that it is not entirely clear which transformations were used in the ImageNet experiments. The paper lists some transformations in Figure 2, but names others in the text too (e.g. crops, flips, cutout). While Figure 2 lists the Identity function, this transformation seems to not appear in the repository (and in fact, the function ``randaugment(N, M)`` doesn't seem to exist in the repository either). So we also make a best guess here about what transformations might have been used. .. warning:: This augmenter only works with image data, not e.g. bounding boxes. The used PIL-based affine transformations are not yet able to process non-image data. (This augmenter uses PIL-based affine transformations to ensure that outputs are as similar as possible to the paper's implementation.) Added in 0.4.0. **Supported dtypes**: minimum of ( :class:`~imgaug.augmenters.flip.Fliplr`, :class:`~imgaug.augmenters.size.KeepSizeByResize`, :class:`~imgaug.augmenters.size.Crop`, :class:`~imgaug.augmenters.meta.Sequential`, :class:`~imgaug.augmenters.meta.SomeOf`, :class:`~imgaug.augmenters.meta.Identity`, :class:`~imgaug.augmenters.pillike.Autocontrast`, :class:`~imgaug.augmenters.pillike.Equalize`, :class:`~imgaug.augmenters.arithmetic.Invert`, :class:`~imgaug.augmenters.pillike.Affine`, :class:`~imgaug.augmenters.pillike.Posterize`, :class:`~imgaug.augmenters.pillike.Solarize`, :class:`~imgaug.augmenters.pillike.EnhanceColor`, :class:`~imgaug.augmenters.pillike.EnhanceContrast`, :class:`~imgaug.augmenters.pillike.EnhanceBrightness`, :class:`~imgaug.augmenters.pillike.EnhanceSharpness`, :class:`~imgaug.augmenters.arithmetic.Cutout`, :class:`~imgaug.augmenters.pillike.FilterBlur`, :class:`~imgaug.augmenters.pillike.FilterSmooth` ) Parameters ---------- n : int or tuple of int or list of int or imgaug.parameters.StochasticParameter or None, optional Parameter ``N`` in the paper, i.e. number of transformations to apply. The paper suggests ``N=2`` for ImageNet. See also parameter ``n`` in :class:`~imgaug.augmenters.meta.SomeOf` for more details. Note that horizontal flips (p=50%) and crops are always applied. This parameter only determines how many of the other transformations are applied per image. m : int or tuple of int or list of int or imgaug.parameters.StochasticParameter or None, optional Parameter ``M`` in the paper, i.e. magnitude/severity/strength of the applied transformations in interval ``[0 .. 30]`` with ``M=0`` being the weakest. The paper suggests for ImageNet ``M=9`` in case of ResNet-50 and ``M=28`` in case of EfficientNet-B7. This implementation uses a default value of ``(6, 12)``, i.e. the value is uniformly sampled per image from the interval ``[6 .. 12]``. This ensures greater diversity of transformations than using a single fixed value. * If ``int``: That value will always be used. * If ``tuple`` ``(a, b)``: A random value will be uniformly sampled per image from the discrete interval ``[a .. b]``. * If ``list``: A random value will be picked from the list per image. * If ``StochasticParameter``: For ``B`` images in a batch, ``B`` values will be sampled per augmenter (provided the augmenter is dependent on the magnitude). cval : number or tuple of number or list of number or imgaug.ALL or imgaug.parameters.StochasticParameter, optional The constant value to use when filling in newly created pixels. See parameter `fillcolor` in :class:`~imgaug.augmenters.pillike.Affine` for details. The paper's repository uses an RGB value of ``125, 122, 113``. This implementation uses a single intensity value of ``128``, which should work better for cases where input images don't have exactly ``3`` channels or come from a different dataset than used by the paper. seed : None or int or imgaug.random.RNG or numpy.random.Generator or numpy.random.BitGenerator or numpy.random.SeedSequence or numpy.random.RandomState, optional See :func:`~imgaug.augmenters.meta.Augmenter.__init__`. name : None or str, optional See :func:`~imgaug.augmenters.meta.Augmenter.__init__`. random_state : None or int or imgaug.random.RNG or numpy.random.Generator or numpy.random.BitGenerator or numpy.random.SeedSequence or numpy.random.RandomState, optional Old name for parameter `seed`. Its usage will not yet cause a deprecation warning, but it is still recommended to use `seed` now. Outdated since 0.4.0. deterministic : bool, optional Deprecated since 0.4.0. See method ``to_deterministic()`` for an alternative and for details about what the "deterministic mode" actually does. Examples -------- >>> import imgaug.augmenters as iaa >>> aug = iaa.RandAugment(n=2, m=9) Create a RandAugment augmenter similar to the suggested hyperparameters in the paper. >>> aug = iaa.RandAugment(m=30) Create a RandAugment augmenter with maximum magnitude/strength. >>> aug = iaa.RandAugment(m=(0, 9)) Create a RandAugment augmenter that applies its transformations with a random magnitude between ``0`` (very weak) and ``9`` (recommended for ImageNet and ResNet-50). ``m`` is sampled per transformation. >>> aug = iaa.RandAugment(n=(0, 3)) Create a RandAugment augmenter that applies ``0`` to ``3`` of its child transformations to images. Horizontal flips (p=50%) and crops are always applied. r N deprecatedc s|dkr|n|}t|}tj|dddddd}||_||_||} |||} | | fD] } | D]} || _q1q-t t |j t j | |dt j|| d|dg||||d dS) Nrm)rNTF)Z value_rangeZtuple_to_uniformZlist_to_choiceZ allow_floats)seed)Z random_orderr)rname random_state deterministic)iarandomZRNGiapZhandle_discrete_param_m_cval_create_initial_augmenters_list_create_main_augmenters_listrsuperr__init__r SequentialZ derive_rng_ZSomeOf) selfnrcvalrrrrrngZ initial_augsZ main_augslstZ augmenter __class__^/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/imgaug/augmenters/collections.pyr!s4       zRandAugment.__init__cCs8tdtjtjtjtd|dddddddd gS) N?rTZ elementwiseF)percentZsample_independentlyZ keep_sizeZlinear) interpolation)r ZFliplrsizelibZKeepSizeByResizeZCroprZDivideZUniform)clsrr*r*r+rs z+RandAugment._create_initial_augmenters_listc s~|jfddfdd}fdd}dd}fd d }tj}td }ttjd d t t j dd|||dddtj |dt ||dd ddtjdt |d||dd ddt||t||t||t|||d|||id|d|||id|d||did|d||didt jdt |dd ddd d!ttgS)"Ncs|}tj||ddSNTr.)rZMultiply)levelmaxvalZ maxval_norm)m_maxr*r+_float_parameterszBRandAugment._create_main_augmenters_list.._float_parametercstj||ddS)NF)round)rZ Discretize)r4r5r7r*r+_int_parameters z@RandAugment._create_main_augmenters_list.._int_parametercs*|d}ttjdt|ddddS)Ng??Tr.g?gffffff?)rClipAdd RandomSign)r4Zfparamr9r*r+_enhance_parameters zDRandAugment._create_main_augmenters_list.._enhance_parametercSstj||ddSr3)rZSubtract)abr*r*r+ _subtractsz;RandAugment._create_main_augmenters_list.._subtractcs(|d<d|vr d|d<tj|i|S)NZ fillcolorcenter)rD)r ZAffine)argskwargs)r%r*r+_affinesz9RandAugment._create_main_augmenters_list.._affineg333333?r)cutoffr;)pr)r,r,)rotaterCr)Znb_bits)rI thresholdx)ZshearygQ?)Ztranslate_percentrg?TZconstant)r ZsquaredZ fill_moder%)_M_MAXrr>npZrad2degr ZIdentityr Z AutocontrastZEqualizer InvertZ Posterizer<ZSolarizeZ EnhanceColorZEnhanceContrastZEnhanceBrightnessZEnhanceSharpnessZCutoutZ FilterBlurZ FilterSmooth) r2rr%r:r?rBrGZ_rnd_sZ shear_maxr*)r7r%r6r+rs^            z(RandAugment._create_main_augmenters_listcCs|d}|j|j|jgS)z=See :func:`~imgaug.augmenters.meta.Augmenter.get_parameters`.r)r$rr)r#Zsomeofr*r*r+get_parametersRszRandAugment.get_parameters)rrrNNrr) __name__ __module__ __qualname____doc__rPr! classmethodrrrS __classcell__r*r*r(r+rs*  Vr)rW __future__rrrnumpyrQrrrrr r r r r r1r"rr*r*r*r+s