TensorFlow 对象检测管道配置中 data_augmentation_options 的可能值是什么？答案

【问题标题】：What are possible values for data_augmentation_options in the TensorFlow Object Detection pipeline configuration?TensorFlow 对象检测管道配置中 data_augmentation_options 的可能值是什么？
【发布时间】：2017-12-07 22:43:45
【问题描述】：

我已经使用 TensorFlow 成功训练了一个对象检测模型，并使用此处给出的示例配置：https://github.com/tensorflow/models/tree/master/object_detection/samples/configs

现在我想微调我的配置以获得更好的结果。我在那里看到的有希望的选项之一是“train_config”下的“data_augmentation_options”。目前，它看起来像这样：

train_config: {
  batch_size: 1
  ...
  data_augmentation_options {
    random_horizontal_flip {
    }
  }
}

是否有其他选项可以进行随机缩放、裁剪或调整亮度？

【问题讨论】：

标签： tensorflow configuration object-detection

【解决方案1】：

preprocessor.proto中提供了选项列表：

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;

您可以在preprocessor.py 中查看有关每个选项的详细信息。参数可以作为键值对提供。

  data_augmentation_options {
    ssd_random_crop {
    }
  }
  data_augmentation_options {
    random_pixel_value_scale {
      minval: 0.6
    }
  }

【讨论】：

所有这些数据增强操作都是按顺序完成的吗？我们可以指定它们是随机完成的吗？
你能告诉我们如何使用ssd_random_crop_pad操作的参数吗？
github.com/tensorflow/models/blob/master/research/…，此文件可以帮助需要详细配置的人
确保查看 preprocessor.proto 链接。现在有更多选择。
对象检测 API 在内部处理。您不必担心标签。当您应用数据增强时，它们也会自动转换。 @SaurabhChauhan

【解决方案2】：

添加到解决方案，这里是里面添加的整个列表

data_augmentation_options {
 ...
  }

增强选项 (found here)：

normalize_image {
  original_minval: 0.0
  original_maxval: 255.0
  target_minval: -1.0
  target_maxval: 1.0
}


random_horizontal_flip {
  keypoint_flip_permutation: 1
  keypoint_flip_permutation: 0
  keypoint_flip_permutation: 2
  keypoint_flip_permutation: 3
  keypoint_flip_permutation: 5
  keypoint_flip_permutation: 4
  probability: 0.5
}


random_vertical_flip {
  keypoint_flip_permutation: 1
  keypoint_flip_permutation: 0
  keypoint_flip_permutation: 2
  keypoint_flip_permutation: 3
  keypoint_flip_permutation: 5
  keypoint_flip_permutation: 4
  probability: 0.5
}


random_rotation90 {
  keypoint_rot_permutation: 3
  keypoint_rot_permutation: 0
  keypoint_rot_permutation: 1
  keypoint_rot_permutation: 2
  probability: 0.5
}


random_pixel_value_scale {
  minval: 0.8
  maxval: 1.2
}


random_image_scale {
  min_scale_ratio: 0.8
  max_scale_ratio: 2.2
}


random_rgb_to_gray {
  probability: 0.8
}


random_adjust_brightness {
  max_delta: 0.2
}


random_adjust_contrast {
  min_delta: 0.7
  max_delta: 1.1
}


random_adjust_hue {
  max_delta: 0.01
}


random_adjust_saturation {
  min_delta: 0.75
  max_delta: 1.15
}


random_distort_color {
  color_ordering: 1
}


random_jitter_boxes {
  ratio: 0.1
  jitter_mode: SHRINK
}


random_crop_image {
  min_object_covered: 0.75
  min_aspect_ratio: 0.75
  max_aspect_ratio: 1.5
  min_area: 0.25
  max_area: 0.875
  overlap_thresh: 0.5
  clip_boxes: False
  random_coef: 0.125
}


random_pad_image {
}


random_absolute_pad_image {
  max_height_padding: 50
  max_width_padding: 100
}


random_crop_pad_image {
  min_object_covered: 0.75
  min_aspect_ratio: 0.75
  max_aspect_ratio: 1.5
  min_area: 0.25
  max_area: 0.875
  overlap_thresh: 0.5
  clip_boxes: False
  random_coef: 0.125
}


random_crop_pad_image {
  min_object_covered: 0.75
  min_aspect_ratio: 0.75
  max_aspect_ratio: 1.5
  min_area: 0.25
  max_area: 0.875
  overlap_thresh: 0.5
  clip_boxes: False
  random_coef: 0.125
  min_padded_size_ratio: 0.5
  min_padded_size_ratio: 0.75
  max_padded_size_ratio: 0.5
  max_padded_size_ratio: 0.75
}


random_crop_to_aspect_ratio {
  aspect_ratio: 0.85
  overlap_thresh: 0.35
  clip_boxes: False
}


random_black_patches {
  max_black_patches: 20
  probability: 0.95
  size_to_image_ratio: 0.12
}


random_jpeg_quality {
  random_coef: 0.5
  min_jpeg_quality: 40
  max_jpeg_quality: 90
}


random_downscale_to_target_pixels {
  random_coef: 0.5
  min_target_pixels: 200
  max_target_pixels: 900
}


random_patch_gaussian {
  random_coef: 0.5
  min_patch_size: 10
  max_patch_size: 300
  min_gaussian_stddev: 0.2
  max_gaussian_stddev: 1.5
}


autoaugment_image {
  policy_name: 'v0'
}


drop_label_probabilistically{
  label: 2
  drop_probability: 0.5
}


remap_labels{
  original_labels: 1
  original_labels: 2
  new_label: 3
}


random_resize_method {
  target_height: 75
  target_width: 100
}


resize_image {
  new_height: 75
  new_width: 100
  method: BICUBIC
}



random_self_concat_image {
  concat_vertical_probability: 0.5
  concat_horizontal_probability: 0.25
}


ssd_random_crop {
  operations {
    min_object_covered: 0.0
    min_aspect_ratio: 0.875
    max_aspect_ratio: 1.125
    min_area: 0.5
    max_area: 1.0
    overlap_thresh: 0.0
    clip_boxes: False
    random_coef: 0.375
  }
  operations {
    min_object_covered: 0.25
    min_aspect_ratio: 0.75
    max_aspect_ratio: 1.5
    min_area: 0.5
    max_area: 1.0
    overlap_thresh: 0.25
    clip_boxes: True
    random_coef: 0.375
  }
}


ssd_random_crop {
}


ssd_random_crop_pad {
  operations {
    min_object_covered: 0.0
    min_aspect_ratio: 0.875
    max_aspect_ratio: 1.125
    min_area: 0.5
    max_area: 1.0
    overlap_thresh: 0.0
    clip_boxes: False
    random_coef: 0.375
    min_padded_size_ratio: [1.0, 1.0]
    max_padded_size_ratio: [2.0, 2.0]
    pad_color_r: 0.5
    pad_color_g: 0.5
    pad_color_b: 0.5
  }
  operations {
    min_object_covered: 0.25
    min_aspect_ratio: 0.75
    max_aspect_ratio: 1.5
    min_area: 0.5
    max_area: 1.0
    overlap_thresh: 0.25
    clip_boxes: True
    random_coef: 0.375
    min_padded_size_ratio: [1.0, 1.0]
    max_padded_size_ratio: [2.0, 2.0]
    pad_color_r: 0.5
    pad_color_g: 0.5
    pad_color_b: 0.5
  }
}


ssd_random_crop_fixed_aspect_ratio {
  operations {
    min_object_covered: 0.0
    min_area: 0.5
    max_area: 1.0
    overlap_thresh: 0.0
    clip_boxes: False
    random_coef: 0.375
  }
  operations {
    min_object_covered: 0.25
    min_area: 0.5
    max_area: 1.0
    overlap_thresh: 0.25
    clip_boxes: True
    random_coef: 0.375
  }
  aspect_ratio: 0.875
}


ssd_random_crop_pad_fixed_aspect_ratio {
  operations {
    min_object_covered: 0.0
    min_aspect_ratio: 0.875
    max_aspect_ratio: 1.125
    min_area: 0.5
    max_area: 1.0
    overlap_thresh: 0.0
    clip_boxes: False
    random_coef: 0.375
  }
  operations {
    min_object_covered: 0.25
    min_aspect_ratio: 0.75
    max_aspect_ratio: 1.5
    min_area: 0.5
    max_area: 1.0
    overlap_thresh: 0.25
    clip_boxes: True
    random_coef: 0.375
  }
  aspect_ratio: 0.875
  min_padded_size_ratio: [1.0, 1.0]
  max_padded_size_ratio: [2.0, 2.0]
}


convert_class_logits_to_softmax {
    temperature: 2
}


random_square_crop_by_scale {
  scale_min: 0.25
  scale_max: 2.0
  num_scales: 8
}


adjust_gamma {
  gamma: 2.2
  gain: 2.0
}

【讨论】：

添加所有这些选项是否会增加处理时间..是否也会增加准确性？
是的，添加增强会增加训练时间，还有助于模型泛化到不同的变化。
如何找出适合特定选项的值？有好的参考吗？谢谢