Closed wwdok closed 3 years ago
If I try to explain it properly, it will take a long time. Please wait a moment while I prepare it.
Oh, sorry for this will take you a long time, let me narrow down the scope of the the question, the model_float32.pb
comes from format convertion or transfer retraining ? You can just explain the key points, i will spend time to dive into it, thanks !
PyTorch -> ONNX -> OpenVINO IR -> openvino2tensorflow -> TFLite
$ python3 ${INTEL_OPENVINO_DIR}/deployment_tools/model_optimizer/mo.py \
--input_model nanodet_320x320.onnx \
--input i \
--input_shape [1,3,320,320] \
--output_dir openvino/nanodet_320x320/FP32 \
--data_type FP32
Three types of files will be generated: .xml, .bin, and .mapping.
https://github.com/PINTO0309/openvino2tensorflow.git
$ openvino2tensorflow \
--model_path onnx/openvino/nanodet_320x320/FP32/nanodet_320x320.xml \
--output_saved_model True \
--output_h5 True \
--output_pb True \
--output_no_quant_float32_tflite True \
--output_weight_quant_tflite True \
--output_float16_quant_tflite True
@wwdok
the model_float32.pb comes from format convertion or transfer retraining ?
format convertion
--output_pb True
Wow, the convertion process is longer than i thought, i am really thankful for this helpful guide !
Hi, @PINTO0309 , thank you for providing these great samples, now i am interested in using nanodet tflite model, you have provided the convertion python scripts, but i have a question, what is the file used to export tflite in
saved_model_320x320
? is itmodel_float32.pb
? if so, how to generate it? Could you please give me some instructions ? Many thanks !