Pre-trained Object Detection models don't have any variables to export in the variables folder for TF2.x usage

[mankeyboy]

System information

• Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04
• Mobile device (e.g., Pixel 4, Samsung Galaxy 10) if the issue happens on mobile device:
• TensorFlow installed from (source or binary): binary
• TensorFlow version (use command below): 2.1
• Python version: 3.7
• Bazel version (if compiling from source):
• GCC/Compiler version (if compiling from source):
• CUDA/cuDNN version: 7.6.5
• GPU model and memory: Tesla T4

Please provide the entire URL of the model you are using?

https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md Describe the current behavior Related issue: https://github.com/tensorflow/tensorrt/issues/178 TF2.x looks for variables from the variables folder to restore the model but this folder is empty in the pretrained models available for download. I have tried converting from the checkpoint given but it just creates an empty frozen graph. Describe the expected behavior A saved_model file + a variables folder should be created when using this. Code to reproduce the issue

Look at related issue Other info / logs

[saberkun]

https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md does not support TF 2.1 (?) Would you mind to use TF 1.15?

[mankeyboy]

@saberkun I know that but I'm trying to utilize the saved_model given in the tar file or get a saved_model from the training checkpoint and frozen graph given and none of those are able to provide me with a trained saved_model. Could you help me outline the steps I'd have to take to get to a trained saved_model?

[saberkun]

Object detection probject owners are: /research/object_detection/ @jch1 @tombstone @derekjchow @jesu9 @dreamdragon @pkulzc

[Akashtyagi]

Any updates on this ?