Problem when there are several boxes in a same image

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• [Yes, I am ] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
• [Yes ] I am reporting the issue to the correct repository. (Model Garden official or research directory)
• [Yes, I checked ] I checked to make sure that this issue has not already been filed.

1. The entire URL of the file you are using

https://github.com/tensorflow/models/blob/master/research/object_detection/colab_tutorials/eager_few_shot_od_training_tflite.ipynb
https://github.com/tensorflow/models/tree/master/research/...

2. Describe the bug

I am attempting to create several boxes in a same image but I got an error. Following this colab https://colab.research.google.com/github/tensorflow/models/blob/master/research/object_detection/colab_tutorials/eager_few_shot_od_training_tf2_colab.ipynb#scrollTo=YBD6l-E4N71y
When I try to create two boxes, in the first image I got this values.

[array([[0.425 , 0.57678781, 0.63833333, 0.72919109],
[0.47 , 0.1137163 , 0.685 , 0.26377491]]),
array([[0.53333333, 0.56037515, 0.75666667, 0.71512309]]),
array([[0.44666667, 0.39273154, 0.66 , 0.56154748]]),
array([[0.29666667, 0.29660023, 0.67166667, 0.53575615]]),
array([[0.235 , 0.43141852, 0.49 , 0.63774912]])]

But in the step of

Let's just visualize the rubber duckies as a sanity check

I got an error.

IndexError: index 1 is out of bounds for axis 0 with size 1

3. Steps to reproduce

You can run this colab
https://colab.research.google.com/github/tensorflow/models/blob/master/research/object_detection/colab_tutorials/eager_few_shot_od_training_tf2_colab.ipynb#scrollTo=YBD6l-E4N71y
and replace gt_boxes whith this values.

[array([[0.425 , 0.57678781, 0.63833333, 0.72919109],
[0.47 , 0.1137163 , 0.685 , 0.26377491]]),
array([[0.53333333, 0.56037515, 0.75666667, 0.71512309]]),
array([[0.44666667, 0.39273154, 0.66 , 0.56154748]]),
array([[0.29666667, 0.29660023, 0.67166667, 0.53575615]]),
array([[0.235 , 0.43141852, 0.49 , 0.63774912]])]

Also, you can create the boxes with the
colab_utils.annotate(train_images_np, box_storage_pointer=gt_boxes)
it is found in the same colab.

4. Expected behavior

I really need the capability of several boxes in a same image for my dataset but the sample don't support it.

A clear and concise description of what you expected to happen.

5. Additional context

None. Thanks in advance

6. System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
• Mobile device name if the issue happens on a mobile device:
• TensorFlow installed from (source or binary):
• TensorFlow version (use command below):
• Python version:
• Bazel version (if compiling from source):
• GCC/Compiler version (if compiling from source):
• CUDA/cuDNN version:
• GPU model and memory: