Processing
AutoPadding
Bases: Processing
, ABC
Source code in src/super_gradients/training/processing/processing.py
114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 |
|
__init__(shape_multiple, pad_value)
Parameters:
Name | Type | Description | Default |
---|---|---|---|
shape_multiple |
Tuple[int, int]
|
Tuple of (H, W) indicating the height and width multiples to which the input image dimensions will be padded. For instance, with a value of (32, 40), an input image of size (45, 67) will be padded to (64, 80). |
required |
pad_value |
int
|
Value to pad the image with. |
required |
Source code in src/super_gradients/training/processing/processing.py
115 116 117 118 119 120 121 122 |
|
CenterCrop
Bases: ClassificationProcess
Parameters:
Name | Type | Description | Default |
---|---|---|---|
size |
int
|
Desired output size of the crop. |
224
|
Source code in src/super_gradients/training/processing/processing.py
646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 |
|
infer_image_input_shape()
Infer the output image shape from the processing.
Returns:
Type | Description |
---|---|
Optional[Tuple[int, int]]
|
(rows, cols) Returns the last known output shape for all the processings. |
Source code in src/super_gradients/training/processing/processing.py
676 677 678 679 680 681 682 |
|
preprocess_image(image)
Crops the given image at the center.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
image |
np.ndarray
|
Image, in (H, W, C) format. |
required |
Returns:
Type | Description |
---|---|
Tuple[np.ndarray, None]
|
The center cropped image. |
Source code in src/super_gradients/training/processing/processing.py
656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 |
|
ComposeProcessing
Bases: Processing
Compose a list of Processing objects into a single Processing object.
Source code in src/super_gradients/training/processing/processing.py
133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 |
|
__init__(processings)
Parameters:
Name | Type | Description | Default |
---|---|---|---|
processings |
List[Processing]
|
List of Processing objects to compose. |
required |
Source code in src/super_gradients/training/processing/processing.py
137 138 139 140 141 |
|
get_equivalent_compose_without_resizing(auto_padding)
Get a composed processing equivalent to this one, but without resizing the image.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
auto_padding |
AutoPadding
|
AutoPadding object to use for padding the image. This is required since models often expect input image to be a multiple of a specific shape (usually 32x32). This padding operation will be applied on the input image before any other processing. |
required |
Returns:
Type | Description |
---|---|
ComposeProcessing
|
A composed processing equivalent to this one, but without resizing the image. |
Source code in src/super_gradients/training/processing/processing.py
185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 |
|
infer_image_input_shape()
Infer the output image shape from the processing.
Returns:
Type | Description |
---|---|
Optional[Tuple[int, int]]
|
(rows, cols) Returns the last known output shape for all the processings. |
Source code in src/super_gradients/training/processing/processing.py
167 168 169 170 171 172 173 174 175 176 177 178 179 |
|
postprocess_predictions(predictions, metadata)
Postprocess the model output predictions.
Source code in src/super_gradients/training/processing/processing.py
151 152 153 154 155 156 |
|
preprocess_image(image)
Processing an image, before feeding it to the network.
Source code in src/super_gradients/training/processing/processing.py
143 144 145 146 147 148 149 |
|
ImagePermute
Bases: Processing
Permute the image dimensions.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
permutation |
Tuple[int, int, int]
|
Specify new order of dims. Default value (2, 0, 1) suitable for converting from HWC to CHW format. |
(2, 0, 1)
|
Source code in src/super_gradients/training/processing/processing.py
204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 |
|
NormalizeImage
Bases: Processing
Normalize an image based on means and standard deviation.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
mean |
List[float]
|
Mean values for each channel. |
required |
std |
List[float]
|
Standard deviation values for each channel. |
required |
Source code in src/super_gradients/training/processing/processing.py
297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 |
|
Processing
Bases: ABC
Interface for preprocessing and postprocessing methods that are used to prepare images for a model and process the model's output.
Subclasses should implement the preprocess_image
and postprocess_predictions
methods according to the specific requirements of the model and task.
Source code in src/super_gradients/training/processing/processing.py
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
|
resizes_image: bool
abstractmethod
property
Return True if the processing resizes the image, False otherwise.
get_equivalent_photometric_module()
abstractmethod
Get the equivalent photometric preprocessing module for this processing. A photometric preprocessing apply a transformation to the image pixels, without changing the image size. This includes RGB -> BGR, standardization, normalization etc. If a Processing subclass does not have change pixel values, it should return an nn.Identity module. If a Processing subclass does not have an equivalent photometric preprocessing, it should return None.
Returns:
Type | Description |
---|---|
Optional[nn.Module]
|
Source code in src/super_gradients/training/processing/processing.py
86 87 88 89 90 91 92 93 94 95 96 |
|
infer_image_input_shape()
Infer the shape (rows, cols) of the image after all the processing steps. This is the effective image size that is fed to model itself
Returns:
Type | Description |
---|---|
Optional[Tuple[int, int]]
|
Return the image shape (rows, cols), or None if the image shape cannot be inferred (When preprocessing contains no resize/padding operations). |
Source code in src/super_gradients/training/processing/processing.py
98 99 100 101 102 103 104 105 |
|
postprocess_predictions(predictions, metadata)
abstractmethod
Postprocess the model output predictions.
Source code in src/super_gradients/training/processing/processing.py
81 82 83 84 |
|
preprocess_image(image)
abstractmethod
Processing an image, before feeding it to the network. Expected to be in (H, W, C) or (H, W).
Source code in src/super_gradients/training/processing/processing.py
76 77 78 79 |
|
ProcessingMetadata
dataclass
Bases: ABC
Metadata including information to postprocess a prediction.
Source code in src/super_gradients/training/processing/processing.py
34 35 36 |
|
Resize
Bases: ClassificationProcess
Source code in src/super_gradients/training/processing/processing.py
613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 |
|
preprocess_image(image)
Resize an image.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
image |
np.ndarray
|
Image, in (H, W, C) format. |
required |
Returns:
Type | Description |
---|---|
Tuple[np.ndarray, None]
|
The resized image. |
Source code in src/super_gradients/training/processing/processing.py
619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 |
|
ReverseImageChannels
Bases: Processing
Reverse the order of the image channels (RGB -> BGR or BGR -> RGB).
Source code in src/super_gradients/training/processing/processing.py
229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
|
preprocess_image(image)
Reverse the channel order of an image.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
image |
np.ndarray
|
Image, in (H, W, C) format. |
required |
Returns:
Type | Description |
---|---|
Tuple[np.ndarray, None]
|
Image with reversed channel order. (RGB if input was BGR, BGR if input was RGB) |
Source code in src/super_gradients/training/processing/processing.py
233 234 235 236 237 238 239 240 241 242 243 244 |
|
SegmentationPadShortToCropSize
Bases: Processing
Pads image to 'crop_size'.
Should be called only after "SegRescale" or "SegRandomRescale" in augmentations pipeline.
:param crop_size: Tuple of (width, height) for the final crop size, if is scalar size is a square (crop_size, crop_size)
= :param fill_image: Grey value to fill image padded background.
Source code in src/super_gradients/training/processing/processing.py
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 |
|
infer_image_input_shape()
Infer the output image shape from the processing.
Returns:
Type | Description |
---|---|
Optional[Tuple[int, int]]
|
(rows, cols) Returns the last known output shape for all the processings. |
Source code in src/super_gradients/training/processing/processing.py
867 868 869 870 871 872 873 |
|
SegmentationPadToDivisible
Bases: Processing
Pads image to a size divisible by the defined parameter.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
divisible_value |
int
|
The divisible value, new image size is an int multiplication of this number |
required |
fill_image |
Union[int, Tuple, List]
|
The value to use for padding the image. |
required |
Source code in src/super_gradients/training/processing/processing.py
876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 |
|
SegmentationRescale
Bases: Processing
Rescale image by scaling factor while preserving aspect ratio. The rescaling can be done according to scale_factor, short_size or long_size. If more than one argument is given, the rescaling mode is determined by this order: scale_factor, then short_size, then long_size.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
scale_factor |
Optional[float]
|
Rescaling is done by multiplying input size by scale_factor: out_size = (scale_factor * w, scale_factor * h) |
None
|
short_size |
Optional[int]
|
Rescaling is done by determining the scale factor by the ratio short_size / min(h, w). |
None
|
long_size |
Optional[int]
|
Rescaling is done by determining the scale factor by the ratio long_size / max(h, w). |
None
|
Source code in src/super_gradients/training/processing/processing.py
743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 |
|
resizes_image: bool
property
Return True if the processing resizes the image, False otherwise.
SegmentationResize
Bases: Processing
Resize image to given image dimensions.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_shape |
Tuple[int, int]
|
output shape will be (output_h, output_w) |
required |
Source code in src/super_gradients/training/processing/processing.py
792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 |
|
infer_image_input_shape()
Infer the output image shape from the processing.
Returns:
Type | Description |
---|---|
Optional[Tuple[int, int]]
|
(rows, cols) Returns the last known output shape for all the processings. |
Source code in src/super_gradients/training/processing/processing.py
822 823 824 825 826 827 828 |
|
SegmentationResizeWithPadding
Bases: Processing
Resize image to given image dimensions while preserving aspect ratio (padding might be used).
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_shape |
Tuple[int, int]
|
(H, W) |
required |
pad_value |
int
|
padding value (will be used if padding needed) |
required |
Source code in src/super_gradients/training/processing/processing.py
689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 |
|
infer_image_input_shape()
Infer the output image shape from the processing.
Returns:
Type | Description |
---|---|
Optional[Tuple[int, int]]
|
(rows, cols) Returns the last known output shape for all the processings. |
Source code in src/super_gradients/training/processing/processing.py
734 735 736 737 738 739 740 |
|
StandardizeImage
Bases: Processing
Standardize image pixel values with img/max_val
Parameters:
Name | Type | Description | Default |
---|---|---|---|
max_value |
float
|
Current maximum value of the image pixels. (usually 255) |
255.0
|
Source code in src/super_gradients/training/processing/processing.py
259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 |
|
preprocess_image(image)
Reverse the channel order of an image.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
image |
np.ndarray
|
Image, in (H, W, C) format. |
required |
Returns:
Type | Description |
---|---|
Tuple[np.ndarray, None]
|
Image with reversed channel order. (RGB if input was BGR, BGR if input was RGB) |
Source code in src/super_gradients/training/processing/processing.py
270 271 272 273 274 275 276 277 |
|
default_cityscapes_processing_params(scale=1)
Processing parameters commonly used for training segmentation models on Cityscapes dataset.
Source code in src/super_gradients/training/processing/processing.py
1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 |
|
default_dekr_coco_processing_params()
Processing parameters commonly used for training DEKR on COCO dataset.
Source code in src/super_gradients/training/processing/processing.py
983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 |
|
default_imagenet_processing_params()
Processing parameters commonly used for training resnet on Imagenet dataset.
Source code in src/super_gradients/training/processing/processing.py
1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 |
|
default_ppyoloe_coco_processing_params()
Processing parameters commonly used for training PPYoloE on COCO dataset. TODO: remove once we load it from the checkpoint
Source code in src/super_gradients/training/processing/processing.py
937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 |
|
default_segformer_cityscapes_processing_params()
Processing parameters commonly used for training Segformer on Cityscapes dataset.
Source code in src/super_gradients/training/processing/processing.py
1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 |
|
default_vit_imagenet_processing_params()
Processing parameters used by ViT for training resnet on Imagenet dataset.
Source code in src/super_gradients/training/processing/processing.py
1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 |
|
default_yolo_nas_coco_processing_params()
Processing parameters commonly used for training YoloNAS on COCO dataset. TODO: remove once we load it from the checkpoint
Source code in src/super_gradients/training/processing/processing.py
960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 |
|
default_yolox_coco_processing_params()
Processing parameters commonly used for training YoloX on COCO dataset. TODO: remove once we load it from the checkpoint
Source code in src/super_gradients/training/processing/processing.py
914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 |
|
get_pretrained_processing_params(model_name, pretrained_weights)
Get the processing parameters for a pretrained model. TODO: remove once we load it from the checkpoint
Source code in src/super_gradients/training/processing/processing.py
1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 |
|