openvino_efficientdet's Introduction

EfficientDet with Intel OpenVINO

This repository demonstrates how to convert AutoML EfficientDet to OpenVINO IR.

Follow the steps from .github/workflows/main.yml to convert your model. For public models, download IRs from GitHub Actions

How to convert model

Freeze graph

cd automl/efficientdet
python3 model_inspect.py --runmode=saved_model --model_name=efficientdet-d4 --ckpt_path=efficientdet-d4 --saved_model_dir=savedmodeldir

Create IR

git clone https://github.com/openvinotoolkit/openvino --depth 1

python3 openvino/model-optimizer/mo.py \
  --input_model efficientdet-d4.pb \
  --transformations_config openvino/model-optimizer/extensions/front/tf/automl_efficientdet.json \
  --input_shape "[1, 1024, 1024, 3]"

find resolution of your model at https://github.com/google/automl/blob/master/efficientdet/hparams_config.py

automl_efficientdet.json contains topology hyper-parameters

Validate model comparing accuracy with an original frozen TensorFlow graph
```
python3 scripts/validate.py --version d4 --width 1024 --height 1024
```

openvino_efficientdet's People

Contributors

Stargazers

Watchers

openvino_efficientdet's Issues

Fix failed conversion

https://github.com/dkurt/openvino_efficientdet/actions/runs/1798710019

License

Would you mind adding license information to the repo?

Error Model Optimizer

Hi, i have an issue when i launch mo.py, this is the error

mo.utils.error.Error: Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.middle.PartialInfer.PartialInfer'>): Stopped shape/value propagation at "TensorArrayV2" node.
For more information please refer to Model Optimizer FAQ (https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html), question #38.

This is the run code.

python mo.py --input_model /Users/antoniosambataro/Desktop/frozen/d4/efficientdet-d4_frozen.pb --transformations_config /Users/antoniosambataro/Desktop/automl_efficientdet.json --input_shape "[1, 1024, 1024, 3]" -o /Users/antoniosambataro/Desktop/ --log_level=DEBUG

Im using ubuntu 18.04 and python3.7 and i try 3.6 too.
Can you help me plz? Also i tested the d6 version but same error

Thanks

Wrong classifications and additional bounding boxes on EfficientDet D0 Optimized

First of all i would like to thanks about this Repository which is being really helpful to be able run the EfficientDet optimized with Openvino. Following the CI file of the repo made possible the easy conversion to MO format. But when testing with custom dataset i got a really lower results comparing to the other models like the one from Yet-Another-EfficientDet-Pytorch even using the same confidence threshold as 0.2.
I thought i was using the wrong label map but realized that is the coco minus 1:
labels = {0:"person",2:"car",3:"motorcycle",5:"bus",7:"truck"}
Also the detections are really great just with a few additional bounding boxes, but the classification shows really wrong results , see the images below generated with EfficientDet D0:

Yet-Another-EfficientDet-Pytorch