search

PINTO0309 / openvino2tensorflow

This script converts the ONNX/OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and pb. PyTorch (NCHW) -> ONNX (NCHW) -> OpenVINO (NCHW) -> openvino2tensorflow -> Tensorflow/Keras (NHWC/NCHW) -> TFLite (NHWC/NCHW). And the conversion from .pb to saved_model and from saved_model to .pb and from .pb to .tflite and saved_model to .tflite and saved_model to onnx. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support.
MIT License
338 stars 39 forks source link

[Question] Resizeable models #27

Closed xandox closed 3 years ago

xandox commented 3 years ago

Hi. The openvino support resizable models. You can change input shape and outputs shape will change too. Is it possible convert such models?

PINTO0309 commented 3 years ago

The tool is designed to optimize the model to the limit for low-spec edge devices, so there are no plans to support variable resolution or variable batches at this time. This may be implemented in the future.

a-storm commented 2 years ago

Hi! Is it still impossible to convert model with variable batch size from OV to TF?

PINTO0309 commented 2 years ago

/usr/local/lib/python3.8/dist-packages/tensorflow_addons/utils/ensure_tf_install.py:53: UserWarning: Tensorflow Addons supports using Python ops for all Tensorflow versions above or equal to 2.3.0 and strictly below 2.5.0 (nightly versions are not supported). The versions of TensorFlow you are currently using is 2.9.0 and is not supported. Some things might work, some things might not. If you were to encounter a bug, do not file an issue. If you want to make sure you're using a tested and supported configuration, either change the TensorFlow version or the TensorFlow Addons's version. You can find the compatibility matrix in TensorFlow Addon's readme: https://github.com/tensorflow/addons warnings.warn( 2022-07-29 20:04:51,012 - onnx-tf - INFO - Start converting onnx pb to tf saved model WARNING:absl:Found untraced functions such as gen_tensor_dict while saving (showing 1 of 1). These functions will not be directly callable after loading. 2022-07-29 20:05:07,449 - onnx-tf - INFO - Converting completes successfully. INFO:onnx-tf:Converting completes successfully.

$ saved_model_cli show --dir saved_model/ --all

MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:

signature_def['__saved_model_init_op']: The given SavedModel SignatureDef contains the following input(s): The given SavedModel SignatureDef contains the following output(s): outputs['__saved_model_init_op'] tensor_info: dtype: DT_INVALID shape: unknown_rank name: NoOp Method name is:

signature_def['serving_default']: The given SavedModel SignatureDef contains the following input(s): inputs['input'] tensor_info: dtype: DT_FLOAT shape: (-1, 3, -1, -1) name: serving_default_input:0 The given SavedModel SignatureDef contains the following output(s): outputs['184'] tensor_info: dtype: DT_FLOAT shape: (-1, 1000) name: StatefulPartitionedCall:0 Method name is: tensorflow/serving/predict

Concrete Functions: Function Name: 'call' Named Argument #1 input

Function Name: 'gen_tensor_dict'