Add an end-to-end Colab for few-shot object detection with TFLite inference

PiperOrigin-RevId: 335521712

research/object_detection/g3doc/running_on_mobile_tf2.md

@@ -16,6 +16,10 @@ This document shows how elgible models from the
 [TF2 Detection zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md)
 can be converted for inference with TFLite.
 
+For an end-to-end Python guide on how to fine-tune an SSD model for mobile
+inference, look at
+[this Colab](../colab_tutorials/eager_few_shot_od_training_tflite.ipynb).
+
 **NOTE:** TFLite currently only supports **SSD Architectures** (excluding
 EfficientDet) for boxes-based detection. Support for EfficientDet is coming
 soon.

research/object_detection/g3doc/tf2.md

@@ -55,6 +55,9 @@ python object_detection/builders/model_builder_tf2_test.py
 *   Inference -
     [Run inference with models from the zoo](../colab_tutorials/inference_tf2_colab.ipynb)
 
+*   Few Shot Learning for Mobile Inference -
+    [Fine-tune a pre-trained detector for use with TensorFlow Lite](../colab_tutorials/eager_few_shot_od_training_tflite.ipynb)
+
 <!-- mdlint on -->
 
 ## Training and Evaluation