ValueError: Only fixed_shape_resizeris supported with tflite. Found keep_aspect_ratio_resize

[Dibyajyoti227]

Prerequisites

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

• I am using the latest TensorFlow Model Garden release and TensorFlow 2.
• I am reporting the issue to the correct repository. (Model Garden research directory)
• 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/tree/master/research/object_detection/configs/tf2/ssd_efficientdet_d0_512x512_coco17_tpu-8.config

2. Describe the bug

While trying to create tflite graph using
python3 object_detection/export_tflite_graph_tf2.py --pipeline_config_path ssd_efficientdet_d0_512x512_coco17_tpu-8.config --trained_checkpoint_dir /checkpoints --output_directory /ssd_tfexport

I am getting error,
File ".local/lib/python3.8/site-packages/object_detection/export_tflite_graph_lib_tf2.py", line 100, in _process_config raise ValueError( ValueError: Only fixed_shape_resizeris supported with tflite. Found keep_aspect_ratio_resizer

I checked the .config file and looks like the keep_aspect_ratio_resizer is mentioned there. How do I get rid of this error and successfully create tflite graph for tflite conversion?

6. System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 20.04
• TensorFlow installed from (source or binary):pip install
• TensorFlow version (use command below):2.13.1
• Python version:3.8

[Dibyajyoti227]

@laxmareddyp , any update on this issue?

[laxmareddyp]

Hi @Dibyajyoti227 ,

Could you please try to open a issue in this repo to get faster response.The error not related to models repo as it is tflite issue.

Thanks