3jTAXSrSSKrSSKJrJrJr SSKrSSKJr SSK J r J r J r SSK JrJrJr SSKJrJrJrJrJrJrJrJrJr SSKJrJrJr SS KJ r S S \ \ S S 4S\\!\\!\!44S\"S\\#S4S\\#S4S\$S\$4 Sjjr%S SSSSSSSS SSSS\ \ SSSSS S S S SSS S 4S\\!\\!\!44S\\\#\#4S\\\#\#4S \\"S!\#S"\#S#\\#\\#S44S$\\#S%\$S&\#S'\#S(\\"S\"S\\#S4S\\#S4S)\#S*\"S+\!S,\!S\$S\$S-\$S.\$S/\\!\\!\!44S0\!S1\$S2\$46S3jjr&S SSSS \ \ S S S SSS S 4S\\!\\!\!44S4\\#S5\\"S6\\!S\"S\\#S4S\\#S4S\$S\$S.\$S/\\!\\!\!44S0\!S1\$S2\$4S7jjr'S S S SSSSSSSSSSS \ \ SSSSSSSS S S S S SSS S 4 S8\\!\\!\!4\\!\!\!44S9\$S:\$S \\"S\\\#\#4S\\\#\#4S!\#S"\#S#\\#\\#S44S$\\#S&\#S'\#S(\\"S\"S\\#S4S\\#S4S)\#S*\"S+\!S,\!S4\\#S5\\"S6\\!S;\$S\$S\$S-\$S.\$S/\\!\\!\!44S0\!S1\$S2\$4@S<jjr(g)=zTransforms Factory Factory methods for building image transforms for use with TIMM (PyTorch Image Models) Hacked together by / Copyright 2019, Ross Wightman N)OptionalTupleUnion) transforms)IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDDEFAULT_CROP_PCT)rand_augment_transformaugment_and_mix_transformauto_augment_transform) str_to_interp_modestr_to_pil_interp!RandomResizedCropAndInterpolationResizeKeepRatioCenterCropOrPadRandomCropOrPad TrimBorder MaybeToTensorMaybePILToTensor)RandomResizedCropToSequenceResizeToSequencePatchify) RandomErasingbilinearFTimg_size interpolationmean.stduse_prefetcher normalizecUS:XaSn[R"U[U5S9[R"U5/nU(aU[ 5/- nO`U(dU[ 5/- nOJU[ 5[R "[R"U5[R"U5S9/- n[R"U5$)aNo-augmentation image transforms for training. Args: img_size: Target image size. interpolation: Image interpolation mode. mean: Image normalization mean. std: Image normalization standard deviation. use_prefetcher: Prefetcher enabled. Do not convert image to tensor or normalize. normalize: Normalization tensor output w/ provided mean/std (if prefetcher not used). Returns: randomrrrr) rResizer CenterCroprr NormalizetorchtensorCompose)rrrrr r!tfls V/home/wildlama/miniconda3/lib/python3.13/site-packages/timm/data/transforms_factory.pytransforms_noaug_trainr.s* " (2D]2STh' C  "##   "## O  \\$'LL%      c ""?g?r#consti@scaleratiotrain_crop_modehflipvflip color_jittercolor_jitter_probforce_color_jittergrayscale_probgaussian_blur_prob auto_augmentre_probre_modere_count re_num_splitsseparatenaflex patch_size max_seq_lenpatchifypatchify_channels_lastchU=(d SnUS;de/nU(a:[U=(d S5n[U=(d S5nU[UUUUU S9/- nOUS;aU[U=(d S5n[U=(d S5nU[UU S US S US 9US :Xa [US S9O [ US S9/- nO8[U=(d S5n[U=(d S5nU[ UUUU S9/- nUS:aU[ R"US9/- nUS:aU[ R"US9/- n/nSnU (Ga[U [5(deU=(d SU ;(+n[U[[45(a [U5nOUn[[US-5[U Vs/sHn[S[SU-55PM sn5S9n U (aU S:wa[!U 5U S'U R#S5(aU[%U U 5/- nO"U 5[<R>"U5S!9/- n!US:aU![AUUUUS"S#9/- n!U(aU![CUUS$9/- n!U(aA[ RD"U5[ RD"U5[ RD"U!54$[ RD"UU-U!-5$s snf)%a#ImageNet-oriented image transforms for training. Args: img_size: Target image size. train_crop_mode: Training random crop mode ('rrc', 'rkrc', 'rkrr'). scale: Random resize scale range (crop area, < 1.0 => zoom in). ratio: Random aspect ratio range (crop ratio for RRC, ratio adjustment factor for RKR). hflip: Horizontal flip probability. vflip: Vertical flip probability. color_jitter: Random color jitter component factors (brightness, contrast, saturation, hue). Scalar is applied as (scalar,) * 3 (no hue). color_jitter_prob: Apply color jitter with this probability if not None (for SimlCLR-like aug). force_color_jitter: Force color jitter where it is normally disabled (ie with RandAugment on). grayscale_prob: Probability of converting image to grayscale (for SimCLR-like aug). gaussian_blur_prob: Probability of applying gaussian blur (for SimCLR-like aug). auto_augment: Auto augment configuration string (see auto_augment.py). interpolation: Image interpolation mode. mean: Image normalization mean. std: Image normalization standard deviation. re_prob: Random erasing probability. re_mode: Random erasing fill mode. re_count: Number of random erasing regions. re_num_splits: Control split of random erasing across batch size. use_prefetcher: Prefetcher enabled. Do not convert image to tensor or normalize. normalize: Normalize tensor output w/ provided mean/std (if prefetcher not used). separate: Output transforms in 3-stage tuple. naflex: Enable NaFlex mode, sequence constrained patch output patch_size: Patch size for NaFlex mode. max_seq_len: Max sequence length for NaFlex mode. Returns: If separate==True, the transforms are returned as a tuple of 3 separate transforms for use in a mixing dataset that passes * all data through the first (primary) transform, called the 'clean' data * a portion of the data through the secondary transform * normalizes and converts the branches above with the third, final transform rrc>rKrkrcrkrr)g{Gz??)g?gUUUUUU?)rFrGr5r6r)rLrM)g?rN)g?grq?r0T)rrandom_scale_probrandom_scale_rangerandom_scale_arearandom_aspect_probrandom_aspect_rangerLreflect) padding_mode)r5r6rr1)pF3ag?)translate_constimg_meanr#rrandaugmixg333333? translate_pct)r^) kernel_sizer%cpu)mode max_count num_splitsdevicerF channels_last)#tuplerrrrrrRandomHorizontalFlipRandomVerticalFlip isinstancestrlistmindictintroundr startswithr r r lenfloat RandomApply ColorJitterRandomGrayscale GaussianBlurrrr(r)r*rrr+)"rr5r6r7r8r9r:r;r<r=r>r?rrrr@rArBrCr r!rDrErFrGrHrI primary_tfl secondary_tfldisable_color_jitter img_size_minx aa_params final_tfls" r-transforms_imagenet_trainrAsnD&.O 5 55 5K e*{+e1123!#'     . .%.;/E%.;/E "/&)',&*'*(-#f, yAyA  K%.;/E%5#56E 1"/  K rz 77%@AA  rz 55>?? M ,,,,,%7$N$,:NO h . .x=L#L t 34dCdCU37^4dCD  ]h6):=)IIo &  " "6 * * 4\9MN NM  $ $X . .),Io & 7 iPQ QM 4\9MN NM(< lT5M 2 2|$. ..",/1A5L  ( &&".. =(( M j44lCD DM*44~FGG   " "++;$%   I&()) &())  O  \\$'LL%    R<  &,  Ih*DZ[\\ !!+. 0B0B=0QS]SeSefoSppp!!+ "= "IJJYDs "P/crop_pct crop_modecrop_border_pixelsc pU=(d [n[U[[45(aD[ U5S:Xde[UVs/sHn[ R "X- 5PM sn5nO[ R "X- 5nX4n/nU(aU[U5/- nU (aU[U U US9/- nOUS:Xa8U[R"U[U5S9[R"U5/- nOUS:Xa6UVs/sHn[SU-5PM nnU[XSS9[UUS 9/- nO[US US :Xa&U[R"US [U5S9/- nOU[U5/- nU[R"U5/- nU(aU[!5/- nO`U(dU[!5/- nOJU[#5[R$"[&R("U5[&R("U5S 9/- nU (a U[+XS 9/- n[R,"U5$s snfs snf)aImageNet-oriented image transform for evaluation and inference. Args: img_size: Target image size. crop_pct: Crop percentage. Defaults to 0.875 when None. crop_mode: Crop mode. One of ['squash', 'border', 'center']. Defaults to 'center' when None. crop_border_pixels: Trim a border of specified # pixels around edge of original image. interpolation: Image interpolation mode. mean: Image normalization mean. std: Image normalization standard deviation. use_prefetcher: Prefetcher enabled. Do not convert image to tensor or normalize. normalize: Normalize tensor output w/ provided mean/std (if prefetcher not used). naflex: Enable NaFlex mode, sequence constrained patch output patch_size: Patch size for NaFlex mode. max_seq_len: Max sequence length for NaFlex mode. patchify: Patchify the output instead of relying on prefetcher Returns: Composed transform pipeline )rFrGrsquashr$borderrXrN)rlongest)fillrr3r%rg)r rlrirnrtmathfloorrrrr&r r'rrrrrrr(r)r*rr+)rrrrrrrr r!rErFrGrHrIr~ scale_sizer,vrs r-transforms_imagenet_evalrs7H++H(UDM**8}!!!hGhDJJq|4hGH ZZ 34  - C -.//   !#'      !!* zoom in). ratio: Random aspect ratio range (crop ratio for RRC, ratio adjustment factor for RKR). hflip: Horizontal flip probability. vflip: Vertical flip probability. color_jitter: Random color jitter component factors (brightness, contrast, saturation, hue). Scalar is applied as (scalar,) * 3 (no hue). color_jitter_prob: Apply color jitter with this probability if not None (for SimlCLR-like aug). grayscale_prob: Probability of converting image to grayscale (for SimCLR-like aug). gaussian_blur_prob: Probability of applying gaussian blur (for SimCLR-like aug). auto_augment: Auto augment configuration string (see auto_augment.py). interpolation: Image interpolation mode. mean: Image normalization mean. std: Image normalization standard deviation. re_prob: Random erasing probability. re_mode: Random erasing fill mode. re_count: Number of random erasing regions. re_num_splits: Control split of random erasing across batch size. crop_pct: Inference crop percentage (output size / resize size). crop_mode: Inference crop mode. One of ['squash', 'border', 'center']. Defaults to 'center' when None. crop_border_pixels: Inference crop border of specified # pixels around edge of original image. tf_preprocessing: Use TF 1.0 inference preprocessing for testing model ports use_prefetcher: Pre-fetcher enabled. Do not convert image to tensor or normalize. normalize: Normalization tensor output w/ provided mean/std (if prefetcher not used). separate: Output transforms in 3-stage tuple. Returns: Composed transforms or tuple thereof Nz6Separate transforms not supported for TF preprocessingr)TfPreprocessTransform)rsizerz-Cannot perform split augmentation with no_aug)rrrr r!r7r5r6r8r9r:r;r=r>r?rrrr@rArBrCr r!rDrErFrGrHrIz>Separate transforms not supported for validation preprocessing) rrrrrrr r!rErFrGrHrI)rlrirntimm.data.tf_preprocessingrr.rr)#rrrr7r5r6r8r9r:r;r=r>r?rrrr@rArBrCrrrrr r!rDrErFrGrHrIrr transforms# r-create_transformr{sJ*udm,,bc?NUUU|D)#' @ u 6 P!P P<.+-# Ip a1 /     *#4 .$6*,   !""#$,%& .'($)*"+,-.&/0(12"34(>5I^ % a!a a<0+!##5-#%'!'=I" r/))__doc__rtypingrrrr) torchvisionrtimm.data.constantsrrr timm.data.auto_augmentr r r timm.data.transformsr rrrrrrrrtimm.data.naflex_transformsrrrtimm.data.random_erasingrrqrmruboolr.rrrr/r-rs"  )) "]]llccc__214'"7!5$ *#U38_,-*#*#E3J*#5#:  *#  *#  *#\14/3/3)-8;-1#( "$&&*%"7!5$24'+7MKU38_,-MKeUl+,MKeUl+,MK"# MK  MK  MKE5#445MK$E?MK!MKMK"MKsmMKMKE3JMK5#: MK !MK"#MK$%MK&'MK()MK*+MK,-MK./MK0#uS#X./1MK23MK45MK6!%7MKb14$(#',0'"7!5$24'+g#U38_,-g#5/g#C=g#%SM g#  g# E3J g#5#: g#g#g#g##uS#X./g#g#g#!%g#VIL!)-/3/38;-1 "$&&*'"7!5$(#',0!&$24'+AM#uS#Xc3m0DDEMMM"# M eUl+, M eUl+, MMME5#445M$E?MM"MsmMME3JM 5#: !M"#M$%M&'M()M*5/+M,C=-M.%SM/M01M23M45M67M89M:#uS#X./;M<=M>?M@!%AMr/