Converting tensorflow model and checkpoint to onnx

[RobertB]

I am trying to convert a pretrained model (Efficientnet) which I have trained on some custom images and new labels. But when using tf2onnx to convert it to onnx format it requires a checkpoint.meta file? But I can’t see this file anywhere? I only see a .index and .data file from the model when I have trained it.
How can I convert a custom model which is using transfer learning? I have downloaded the model from Tensorflow Model Zoo.

[AastaLLL]

Hi,

We download the efficientdet_d0_coco17_tpu-32.tar.gz from here.
And we can convert it into ONNX via tf2onnx with below command:

$ python3 -m tf2onnx.convert --saved-model efficientdet_d0_coco17_tpu-32/saved_model --output model.onnx

Here is our folder details for your reference:

$ ll efficientdet_d0_coco17_tpu-32/*
... efficientdet_d0_coco17_tpu-32/pipeline.config

efficientdet_d0_coco17_tpu-32/checkpoint:
total 22152
...  ./
...  ../
...  checkpoint
...  ckpt-0.data-00000-of-00001
...  ckpt-0.index

efficientdet_d0_coco17_tpu-32/saved_model:
total 20864
...  ./
...  ../
...  assets/
...  saved_model.pb
...  variables/

Thanks.