its about running this

[Rimsha7777]

[Required] Your device (RaspberryPi3, LaptopPC, or other device name):

[Required] Your device's CPU architecture (armv7l, x86_64, or other architecture name):

[Required] Your OS (Raspbian, Ubuntu1604, or other os name):

[Required] Overview of problems and questions:

can you help me how i can generate .bin and .xml files. I am just new to using NCS2. I wanted to run using PRI3+. If you help me what I have to do with model optimizer exactly with command-line-arguments, I am not getting that I just visited other issues find some with this but did not get how to do.

[PINTO0309]

@Rimsha7777
Just execute the commands listed in the following file in order from the top.
https://github.com/PINTO0309/OpenVINO-YoloV3/blob/master/script.txt

python3 convert_weights_pb.py \
--class_names coco.names \
--weights_file weights/yolov3-tiny.weights \
--data_format NHWC \
--tiny \
--output_graph pbmodels/frozen_tiny_yolo_v3.pb

sudo python3 /opt/intel/openvino/deployment_tools/model_optimizer/mo_tf.py \
--input_model pbmodels/frozen_tiny_yolo_v3.pb \
--output_dir lrmodels/tiny-YoloV3/FP16 \
--data_type FP16 \
--batch 1 \
--tensorflow_use_custom_operations_config yolo_v3_tiny_changed.json

python3 openvino_yolov3_test.py -d MYRIAD

[Rimsha7777]

Thank you so much for your reply...this is indeed sounds helpful...I will update you right after implementing .

…

On Saturday, October 5, 2019, Katsuya Hyodo ***@***.***> wrote: @Rimsha7777 <https://github.com/Rimsha7777> Just execute the commands listed in the following file in order from the top. *https://github.com/PINTO0309/OpenVINO-YoloV3/blob/master/script.txt <https://github.com/PINTO0309/OpenVINO-YoloV3/blob/master/script.txt>* python3 convert_weights_pb.py \ --class_names coco.names \ --weights_file weights/yolov3-tiny.weights \ --data_format NHWC \ --tiny \ --output_graph pbmodels/frozen_tiny_yolo_v3.pb sudo python3 /opt/intel/openvino/deployment_tools/model_optimizer/mo_tf.py \ --input_model pbmodels/frozen_tiny_yolo_v3.pb \ --output_dir lrmodels/tiny-YoloV3/FP16 \ --data_type FP16 \ --batch 1 \ --tensorflow_use_custom_operations_config yolo_v3_tiny_changed.json python3 openvino_yolov3_test.py -d MYRIAD — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#56?email_source=notifications&email_token=ALWLRUTVX3KVWJFZ5A5QE3LQNBP75A5CNFSM4I5XAFGKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEANOZOQ#issuecomment-538635450>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ALWLRUWGXMZFQRHVU6O2X5DQNBP75ANCNFSM4I5XAFGA> .

[Rimsha7777]

Hi,
I can't find model_optimzer directory in development_tool in openvino(release is 2019). Do I need to download it externally?

[PINTO0309]

The OpenVINO installer for RaspberryPi does not include a model optimizer. So if you want to convert the model, you need a HostPC with the full version of OpenVINO installed.

HostPC ex) Ubuntu
First, download the latest OpenVINO from the following. And, install.
https://github.com/PINTO0309/OpenVINO-bin.git

Next, execute the following command on HostPC.

python3 convert_weights_pb.py \
--class_names coco.names \
--weights_file weights/yolov3-tiny.weights \
--data_format NHWC \
--tiny \
--output_graph pbmodels/frozen_tiny_yolo_v3.pb

sudo python3 /opt/intel/openvino/deployment_tools/model_optimizer/mo_tf.py \
--input_model pbmodels/frozen_tiny_yolo_v3.pb \
--output_dir lrmodels/tiny-YoloV3/FP16 \
--data_type FP16 \
--batch 1 \
--tensorflow_use_custom_operations_config yolo_v3_tiny_changed.json

Next, copy the .bin and .xml generated on HostPC to RaspberryPi.

[Rimsha7777]

Ok, thanks you so very much for helping.

…

On Sunday, October 6, 2019, Katsuya Hyodo ***@***.***> wrote: The OpenVINO installer for RaspberryPi does not include a model optimizer. So if you want to convert the model, you need a HostPC with the full version of OpenVINO installed. *HostPC ex) Ubuntu* First, download the latest OpenVINO from the following. And, install. *https://github.com/PINTO0309/OpenVINO-bin.git <https://github.com/PINTO0309/OpenVINO-bin.git>* Next, execute the following command on HostPC. python3 convert_weights_pb.py \ --class_names coco.names \ --weights_file weights/yolov3-tiny.weights \ --data_format NHWC \ --tiny \ --output_graph pbmodels/frozen_tiny_yolo_v3.pb sudo python3 /opt/intel/openvino/deployment_tools/model_optimizer/mo_tf.py \ --input_model pbmodels/frozen_tiny_yolo_v3.pb \ --output_dir lrmodels/tiny-YoloV3/FP16 \ --data_type FP16 \ --batch 1 \ --tensorflow_use_custom_operations_config yolo_v3_tiny_changed.json Next, copy the .bin and .xml generated on HostPC to RaspberryPi. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#56?email_source=notifications&email_token=ALWLRUXIB4IFZS4NYRGJEXDQNGRZZA5CNFSM4I5XAFGKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEAOEX7A#issuecomment-538725372>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ALWLRUUXTYQJV5UGR5EKGLTQNGRZZANCNFSM4I5XAFGA> .