TensorFlow 对象检测管道配置中 data_augmentation_options 的可能值是什么? [英] What are possible values for data_augmentation_options in the TensorFlow Object Detection pipeline configuration?

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

I have successfully trained an object detection model with TensorFlow with the sample configurations given here: 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:

Now I want to fine tune my configuration to get better results. One of the promising options I see in there is "data_augmentation_options" under "train_config". Currently, it looks like this:

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

是否有其他选项可以随机缩放、裁剪或调整亮度?

Are there other options to do random scaling, cropping or tweaking of brightness?

推荐答案

选项列表在 preprocessor.proto:

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 中查看每个选项的详细信息.py.参数可以作为键值对提供.

You can see the details about each option in preprocessor.py. Arguments can be provided as key-value pairs.

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

这篇关于TensorFlow 对象检测管道配置中 data_augmentation_options 的可能值是什么?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！