Save tensorflow object detection augmented images

Question

Is there a way to view the images that tensorflow object detection api trains on after all preprocessing/augmentation.

I'd like to verify that things look correctly. I was able to verify the resizing my looking at the graph post resize in inference but I obviously can't do that for augmentation options.

In the past with Keras I've been able to do that and I've found that I was to aggressive.

which Kind of Augmentation Options are you talking about? Could you provide some Code example? — mrk, Dec 21 '18 at 21:58
Generally, you could see love this by adding the augmented images to tensorboard if you use it. If not you could save them in numpy arrays and plot them. You should provide a code example. — Lau, Dec 22 '18 at 09:19
Any model run using the object detection api with a config file with any of these options listed https://github.com/tensorflow/models/blob/master/research/object_detection/protos/preprocessor.proto — user27108, Dec 22 '18 at 13:20
Does this answer your question? [Visualizing augmented train images \[tensorflow object detection api\]](https://stackoverflow.com/questions/55020315/visualizing-augmented-train-images-tensorflow-object-detection-api) — user2672299, Mar 12 '21 at 10:48

Danny Fang · Accepted Answer · 2019-04-06T09:03:37.530

The API provides test code for augmentation options. In input_test.py file, the function test_apply_image_and_box_augmentation is for that. You can rewrite this function by passing your own images to the tensor_dict and then save the augmented_tensor_dict_out for verification or you can directly visualize it.

EDIT: Since this answer was long ago answered and still not accepted, I decided to provide a more specific answer with examples. I wrote a little test script called augmentation_test.py.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import functools
import os
from absl.testing import parameterized

import numpy as np
import tensorflow as tf
from scipy.misc import imsave, imread

from object_detection import inputs
from object_detection.core import preprocessor
from object_detection.core import standard_fields as fields
from object_detection.utils import config_util
from object_detection.utils import test_case

FLAGS = tf.flags.FLAGS

class DataAugmentationFnTest(test_case.TestCase):

  def test_apply_image_and_box_augmentation(self):
    data_augmentation_options = [
        (preprocessor.random_horizontal_flip, {
        })
    ]
    data_augmentation_fn = functools.partial(
        inputs.augment_input_data,
        data_augmentation_options=data_augmentation_options)
    tensor_dict = {
        fields.InputDataFields.image:
            tf.constant(imread('lena.jpeg').astype(np.float32)),
        fields.InputDataFields.groundtruth_boxes:
            tf.constant(np.array([[.5, .5, 1., 1.]], np.float32))
    }
    augmented_tensor_dict = 
        data_augmentation_fn(tensor_dict=tensor_dict)
    with self.test_session() as sess:
      augmented_tensor_dict_out = sess.run(augmented_tensor_dict)
    imsave('lena_out.jpeg',augmented_tensor_dict_out[fields.InputDataFields.image])


if __name__ == '__main__':
  tf.test.main()

You can put this script under models/research/object_detection/ and simply run it with python augmentation_test.py. To successfully run it you should provide any image name 'lena.jpeg' and the output image after augmentation would be saved as 'lena_out.jpeg'.

I ran it with the 'lena' image and here is the result before augmentation and after augmentation.

.

Note that I used preprocessor.random_horizontal_flip in the script. And the result showed exactly what the input image looks like after random_horizontal_flip. To test it with other augmentation options, you can replace the random_horizontal_flip with other methods (which are all defined in preprocessor.py and also in the config proto file), all you can append other options to the data_augmentation_options list, for example:

data_augmentation_options = [(preprocessor.resize_image, {
        'new_height': 20,
        'new_width': 20,
        'method': tf.image.ResizeMethod.NEAREST_NEIGHBOR
    }),(preprocessor.random_horizontal_flip, {
    })]

score 0 · Answer 2 · answered Mar 12 '21 at 10:50

Here is the code to achieve what has been asked in the question https://github.com/majrie/visualize_augmentation/blob/master/visualize_augmentation.ipynb .

It is based on the answer of @danyfang in following question Visualizing augmented train images [tensorflow object detection api].

Save tensorflow object detection augmented images

2 Answers2

Linked