Skip to content
Permalink
Branch: master
Find file Copy path
Find file Copy path
3 contributors

Users who have contributed to this file

@pkulzc @tombstone @nealwu
535 lines (439 sloc) 19.3 KB
syntax = "proto2";
package object_detection.protos;
// Message for defining a preprocessing operation on input data.
// See: //third_party/tensorflow_models/object_detection/core/preprocessor.py
message PreprocessingStep {
oneof preprocessing_step {
NormalizeImage normalize_image = 1;
RandomHorizontalFlip random_horizontal_flip = 2;
RandomPixelValueScale random_pixel_value_scale = 3;
RandomImageScale random_image_scale = 4;
RandomRGBtoGray random_rgb_to_gray = 5;
RandomAdjustBrightness random_adjust_brightness = 6;
RandomAdjustContrast random_adjust_contrast = 7;
RandomAdjustHue random_adjust_hue = 8;
RandomAdjustSaturation random_adjust_saturation = 9;
RandomDistortColor random_distort_color = 10;
RandomJitterBoxes random_jitter_boxes = 11;
RandomCropImage random_crop_image = 12;
RandomPadImage random_pad_image = 13;
RandomCropPadImage random_crop_pad_image = 14;
RandomCropToAspectRatio random_crop_to_aspect_ratio = 15;
RandomBlackPatches random_black_patches = 16;
RandomResizeMethod random_resize_method = 17;
ScaleBoxesToPixelCoordinates scale_boxes_to_pixel_coordinates = 18;
ResizeImage resize_image = 19;
SubtractChannelMean subtract_channel_mean = 20;
SSDRandomCrop ssd_random_crop = 21;
SSDRandomCropPad ssd_random_crop_pad = 22;
SSDRandomCropFixedAspectRatio ssd_random_crop_fixed_aspect_ratio = 23;
SSDRandomCropPadFixedAspectRatio ssd_random_crop_pad_fixed_aspect_ratio = 24;
RandomVerticalFlip random_vertical_flip = 25;
RandomRotation90 random_rotation90 = 26;
RGBtoGray rgb_to_gray = 27;
ConvertClassLogitsToSoftmax convert_class_logits_to_softmax = 28;
RandomAbsolutePadImage random_absolute_pad_image = 29;
RandomSelfConcatImage random_self_concat_image = 30;
AutoAugmentImage autoaugment_image = 31;
DropLabelProbabilistically drop_label_probabilistically = 32;
RemapLabels remap_labels = 33;
RandomJpegQuality random_jpeg_quality = 34;
RandomDownscaleToTargetPixels random_downscale_to_target_pixels = 35;
RandomPatchGaussian random_patch_gaussian = 36;
}
}
// Normalizes pixel values in an image.
// For every channel in the image, moves the pixel values from the range
// [original_minval, original_maxval] to [target_minval, target_maxval].
message NormalizeImage {
optional float original_minval = 1;
optional float original_maxval = 2;
optional float target_minval = 3 [default=0];
optional float target_maxval = 4 [default=1];
}
// Randomly horizontally flips the image and detections 50% of the time.
message RandomHorizontalFlip {
// Specifies a mapping from the original keypoint indices to horizontally
// flipped indices. This is used in the event that keypoints are specified,
// in which case when the image is horizontally flipped the keypoints will
// need to be permuted. E.g. for keypoints representing left_eye, right_eye,
// nose_tip, mouth, left_ear, right_ear (in that order), one might specify
// the keypoint_flip_permutation below:
// keypoint_flip_permutation: 1
// keypoint_flip_permutation: 0
// keypoint_flip_permutation: 2
// keypoint_flip_permutation: 3
// keypoint_flip_permutation: 5
// keypoint_flip_permutation: 4
repeated int32 keypoint_flip_permutation = 1;
}
// Randomly vertically flips the image and detections 50% of the time.
message RandomVerticalFlip {
// Specifies a mapping from the original keypoint indices to vertically
// flipped indices. This is used in the event that keypoints are specified,
// in which case when the image is vertically flipped the keypoints will
// need to be permuted. E.g. for keypoints representing left_eye, right_eye,
// nose_tip, mouth, left_ear, right_ear (in that order), one might specify
// the keypoint_flip_permutation below:
// keypoint_flip_permutation: 1
// keypoint_flip_permutation: 0
// keypoint_flip_permutation: 2
// keypoint_flip_permutation: 3
// keypoint_flip_permutation: 5
// keypoint_flip_permutation: 4
repeated int32 keypoint_flip_permutation = 1;
}
// Randomly rotates the image and detections by 90 degrees counter-clockwise
// 50% of the time.
message RandomRotation90 {}
// Randomly scales the values of all pixels in the image by some constant value
// between [minval, maxval], then clip the value to a range between [0, 1.0].
message RandomPixelValueScale {
optional float minval = 1 [default=0.9];
optional float maxval = 2 [default=1.1];
}
// Randomly enlarges or shrinks image (keeping aspect ratio).
message RandomImageScale {
optional float min_scale_ratio = 1 [default=0.5];
optional float max_scale_ratio = 2 [default=2.0];
}
// Randomly convert entire image to grey scale.
message RandomRGBtoGray {
optional float probability = 1 [default=0.1];
}
// Randomly changes image brightness by up to max_delta. Image outputs will be
// saturated between 0 and 1.
message RandomAdjustBrightness {
optional float max_delta=1 [default=0.2];
}
// Randomly scales contract by a value between [min_delta, max_delta].
message RandomAdjustContrast {
optional float min_delta = 1 [default=0.8];
optional float max_delta = 2 [default=1.25];
}
// Randomly alters hue by a value of up to max_delta.
message RandomAdjustHue {
optional float max_delta = 1 [default=0.02];
}
// Randomly changes saturation by a value between [min_delta, max_delta].
message RandomAdjustSaturation {
optional float min_delta = 1 [default=0.8];
optional float max_delta = 2 [default=1.25];
}
// Performs a random color distortion. color_orderings should either be 0 or 1.
message RandomDistortColor {
optional int32 color_ordering = 1;
}
// Randomly jitters corners of boxes in the image determined by ratio.
// ie. If a box is [100, 200] and ratio is 0.02, the corners can move by [1, 4].
message RandomJitterBoxes {
optional float ratio = 1 [default=0.05];
}
// Randomly crops the image and bounding boxes.
message RandomCropImage {
// Cropped image must cover at least one box by this fraction.
optional float min_object_covered = 1 [default=1.0];
// Aspect ratio bounds of cropped image.
optional float min_aspect_ratio = 2 [default=0.75];
optional float max_aspect_ratio = 3 [default=1.33];
// Allowed area ratio of cropped image to original image.
optional float min_area = 4 [default=0.1];
optional float max_area = 5 [default=1.0];
// Minimum overlap threshold of cropped boxes to keep in new image. If the
// ratio between a cropped bounding box and the original is less than this
// value, it is removed from the new image.
optional float overlap_thresh = 6 [default=0.3];
// Whether to clip the boxes to the cropped image.
optional bool clip_boxes = 8 [default=true];
// Probability of keeping the original image.
optional float random_coef = 7 [default=0.0];
}
// Randomly adds padding to the image.
message RandomPadImage {
// Minimum dimensions for padded image. If unset, will use original image
// dimension as a lower bound.
optional int32 min_image_height = 1;
optional int32 min_image_width = 2;
// Maximum dimensions for padded image. If unset, will use double the original
// image dimension as a lower bound.
optional int32 max_image_height = 3;
optional int32 max_image_width = 4;
// Color of the padding. If unset, will pad using average color of the input
// image.
repeated float pad_color = 5;
}
// Randomly adds a padding of size [0, max_height_padding), [0, max_width_padding).
message RandomAbsolutePadImage {
// Height will be padded uniformly at random from [0, max_height_padding).
optional int32 max_height_padding = 1;
// Width will be padded uniformly at random from [0, max_width_padding).
optional int32 max_width_padding = 2;
// Color of the padding. If unset, will pad using average color of the input
// image.
repeated float pad_color = 3;
}
// Randomly crops an image followed by a random pad.
message RandomCropPadImage {
// Cropping operation must cover at least one box by this fraction.
optional float min_object_covered = 1 [default=1.0];
// Aspect ratio bounds of image after cropping operation.
optional float min_aspect_ratio = 2 [default=0.75];
optional float max_aspect_ratio = 3 [default=1.33];
// Allowed area ratio of image after cropping operation.
optional float min_area = 4 [default=0.1];
optional float max_area = 5 [default=1.0];
// Minimum overlap threshold of cropped boxes to keep in new image. If the
// ratio between a cropped bounding box and the original is less than this
// value, it is removed from the new image.
optional float overlap_thresh = 6 [default=0.3];
// Whether to clip the boxes to the cropped image.
optional bool clip_boxes = 11 [default=true];
// Probability of keeping the original image during the crop operation.
optional float random_coef = 7 [default=0.0];
// Maximum dimensions for padded image. If unset, will use double the original
// image dimension as a lower bound. Both of the following fields should be
// length 2.
repeated float min_padded_size_ratio = 8;
repeated float max_padded_size_ratio = 9;
// Color of the padding. If unset, will pad using average color of the input
// image. This field should be of length 3.
repeated float pad_color = 10;
}
// Randomly crops an iamge to a given aspect ratio.
message RandomCropToAspectRatio {
// Aspect ratio.
optional float aspect_ratio = 1 [default=1.0];
// Minimum overlap threshold of cropped boxes to keep in new image. If the
// ratio between a cropped bounding box and the original is less than this
// value, it is removed from the new image.
optional float overlap_thresh = 2 [default=0.3];
// Whether to clip the boxes to the cropped image.
optional bool clip_boxes = 3 [default=true];
}
// Randomly adds black square patches to an image.
message RandomBlackPatches {
// The maximum number of black patches to add.
optional int32 max_black_patches = 1 [default=10];
// The probability of a black patch being added to an image.
optional float probability = 2 [default=0.5];
// Ratio between the dimension of the black patch to the minimum dimension of
// the image (patch_width = patch_height = min(image_height, image_width)).
optional float size_to_image_ratio = 3 [default=0.1];
}
// Randomly resizes the image up to [target_height, target_width].
message RandomResizeMethod {
optional int32 target_height = 1;
optional int32 target_width = 2;
}
// Converts the RGB image to a grayscale image. This also converts the image
// depth from 3 to 1, unlike RandomRGBtoGray which does not change the image
// depth.
message RGBtoGray {}
// Scales boxes from normalized coordinates to pixel coordinates.
message ScaleBoxesToPixelCoordinates {
}
// Resizes images to [new_height, new_width].
message ResizeImage {
optional int32 new_height = 1;
optional int32 new_width = 2;
enum Method {
AREA=1;
BICUBIC=2;
BILINEAR=3;
NEAREST_NEIGHBOR=4;
}
optional Method method = 3 [default=BILINEAR];
}
// Normalizes an image by subtracting a mean from each channel.
message SubtractChannelMean {
// The mean to subtract from each channel. Should be of same dimension of
// channels in the input image.
repeated float means = 1;
}
message SSDRandomCropOperation {
// Cropped image must cover at least this fraction of one original bounding
// box.
optional float min_object_covered = 1;
// The aspect ratio of the cropped image must be within the range of
// [min_aspect_ratio, max_aspect_ratio].
optional float min_aspect_ratio = 2;
optional float max_aspect_ratio = 3;
// The area of the cropped image must be within the range of
// [min_area, max_area].
optional float min_area = 4;
optional float max_area = 5;
// Cropped box area ratio must be above this threhold to be kept.
optional float overlap_thresh = 6;
// Whether to clip the boxes to the cropped image.
optional bool clip_boxes = 8 [default=true];
// Probability a crop operation is skipped.
optional float random_coef = 7;
}
// Randomly crops a image according to:
// Liu et al., SSD: Single shot multibox detector.
// This preprocessing step defines multiple SSDRandomCropOperations. Only one
// operation (chosen at random) is actually performed on an image.
message SSDRandomCrop {
repeated SSDRandomCropOperation operations = 1;
}
message SSDRandomCropPadOperation {
// Cropped image must cover at least this fraction of one original bounding
// box.
optional float min_object_covered = 1;
// The aspect ratio of the cropped image must be within the range of
// [min_aspect_ratio, max_aspect_ratio].
optional float min_aspect_ratio = 2;
optional float max_aspect_ratio = 3;
// The area of the cropped image must be within the range of
// [min_area, max_area].
optional float min_area = 4;
optional float max_area = 5;
// Cropped box area ratio must be above this threhold to be kept.
optional float overlap_thresh = 6;
// Whether to clip the boxes to the cropped image.
optional bool clip_boxes = 13 [default=true];
// Probability a crop operation is skipped.
optional float random_coef = 7;
// Min ratio of padded image height and width to the input image's height and
// width. Two entries per operation.
repeated float min_padded_size_ratio = 8;
// Max ratio of padded image height and width to the input image's height and
// width. Two entries per operation.
repeated float max_padded_size_ratio = 9;
// Padding color.
optional float pad_color_r = 10;
optional float pad_color_g = 11;
optional float pad_color_b = 12;
}
// Randomly crops and pads an image according to:
// Liu et al., SSD: Single shot multibox detector.
// This preprocessing step defines multiple SSDRandomCropPadOperations. Only one
// operation (chosen at random) is actually performed on an image.
message SSDRandomCropPad {
repeated SSDRandomCropPadOperation operations = 1;
}
message SSDRandomCropFixedAspectRatioOperation {
// Cropped image must cover at least this fraction of one original bounding
// box.
optional float min_object_covered = 1;
// The area of the cropped image must be within the range of
// [min_area, max_area].
optional float min_area = 4;
optional float max_area = 5;
// Cropped box area ratio must be above this threhold to be kept.
optional float overlap_thresh = 6;
// Whether to clip the boxes to the cropped image.
optional bool clip_boxes = 8 [default=true];
// Probability a crop operation is skipped.
optional float random_coef = 7;
}
// Randomly crops a image to a fixed aspect ratio according to:
// Liu et al., SSD: Single shot multibox detector.
// Multiple SSDRandomCropFixedAspectRatioOperations are defined by this
// preprocessing step. Only one operation (chosen at random) is actually
// performed on an image.
message SSDRandomCropFixedAspectRatio {
repeated SSDRandomCropFixedAspectRatioOperation operations = 1;
// Aspect ratio to crop to. This value is used for all crop operations.
optional float aspect_ratio = 2 [default=1.0];
}
message SSDRandomCropPadFixedAspectRatioOperation {
// Cropped image must cover at least this fraction of one original bounding
// box.
optional float min_object_covered = 1;
// The aspect ratio of the cropped image must be within the range of
// [min_aspect_ratio, max_aspect_ratio].
optional float min_aspect_ratio = 2;
optional float max_aspect_ratio = 3;
// The area of the cropped image must be within the range of
// [min_area, max_area].
optional float min_area = 4;
optional float max_area = 5;
// Cropped box area ratio must be above this threhold to be kept.
optional float overlap_thresh = 6;
// Whether to clip the boxes to the cropped image.
optional bool clip_boxes = 8 [default=true];
// Probability a crop operation is skipped.
optional float random_coef = 7;
}
// Randomly crops and pads an image to a fixed aspect ratio according to:
// Liu et al., SSD: Single shot multibox detector.
// Multiple SSDRandomCropPadFixedAspectRatioOperations are defined by this
// preprocessing step. Only one operation (chosen at random) is actually
// performed on an image.
message SSDRandomCropPadFixedAspectRatio {
repeated SSDRandomCropPadFixedAspectRatioOperation operations = 1;
// Aspect ratio to pad to. This value is used for all crop and pad operations.
optional float aspect_ratio = 2 [default=1.0];
// Min ratio of padded image height and width to the input image's height and
// width. Two entries per operation.
repeated float min_padded_size_ratio = 3;
// Max ratio of padded image height and width to the input image's height and
// width. Two entries per operation.
repeated float max_padded_size_ratio = 4;
}
// Converts class logits to softmax optionally scaling the values by temperature
// first.
message ConvertClassLogitsToSoftmax {
// Scale to use on logits before applying softmax.
optional float temperature = 1 [default=1.0];
}
// Randomly concatenates the image with itself horizontally and/or vertically.
message RandomSelfConcatImage {
// Probability of concatenating the image vertically.
optional float concat_vertical_probability = 1 [default = 0.1];
// Probability of concatenating the image horizontally.
optional float concat_horizontal_probability = 2 [default = 0.1];
}
// Apply an Autoaugment policy to the image and bounding boxes.
message AutoAugmentImage {
// What AutoAugment policy to apply to the Image
optional string policy_name = 1 [default="v0"];
}
// Randomly drops ground truth boxes for a label with some probability.
message DropLabelProbabilistically {
// The label that should be dropped. This corresponds to one of the entries
// in the label map.
optional int32 label = 1;
// Probability of dropping the label.
optional float drop_probability = 2 [default = 1.0];
}
//Remap a set of labels to a new label.
message RemapLabels {
// Labels to be remapped.
repeated int32 original_labels = 1;
// Label to map to.
optional int32 new_label = 2;
}
// Applies a jpeg encoding with a random quality factor.
message RandomJpegQuality {
// Probability of keeping the original image.
optional float random_coef = 1 [default = 0.0];
// Minimum jpeg quality to use.
optional int32 min_jpeg_quality = 2 [default = 0];
// Maximum jpeg quality to use.
optional int32 max_jpeg_quality = 3 [default = 100];
}
// Randomly shrinks image (keeping aspect ratio) to a target number of pixels.
// If the image contains less than the chosen target number of pixels, it will
// not be changed.
message RandomDownscaleToTargetPixels {
// Probability of keeping the original image.
optional float random_coef = 1 [default = 0.0];
// The target number of pixels will be chosen to be in the range
// [min_target_pixels, max_target_pixels]
optional int32 min_target_pixels = 2 [default = 300000];
optional int32 max_target_pixels = 3 [default = 500000];
}
message RandomPatchGaussian {
// Probability of keeping the original image.
optional float random_coef = 1 [default = 0.0];
// The patch size will be chosen to be in the range
// [min_patch_size, max_patch_size).
optional int32 min_patch_size = 2 [default = 1];
optional int32 max_patch_size = 3 [default = 250];
// The standard deviation of the gaussian noise applied within the patch will
// be chosen to be in the range [min_gaussian_stddev, max_gaussian_stddev).
optional float min_gaussian_stddev = 4 [default = 0.0];
optional float max_gaussian_stddev = 5 [default = 1.0];
}
You can’t perform that action at this time.