Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6480 Discussions

mo_tf.py killed during model optimization

resh
Beginner
1,153 Views

Command used-

reshu@reshu-GL63-8RC:/opt/intel/openvino_2021.3.394/deployment_tools/model_optimizer$ sudo python3 mo_tf.py --saved_model_dir  <saved_model_TF2_dir> --data_type FP16 --log_level=DEBUG

 

Error-

2021-06-15 15:27:31.922828: I tensorflow/core/platform/profile_utils/cpu_utils.cc:114] CPU Frequency: 2299965000 Hz
2021-06-15 15:27:32.564944: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:1144] Optimization results for grappler item: graph_to_optimize
function_optimizer: Graph size after: 2329 nodes (1835), 3371 edges (2877), time = 408.197ms.
function_optimizer: function_optimizer did nothing. time = 1.001ms.

Killed

0 Kudos
4 Replies
Syamimi_Intel
Moderator
1,132 Views

Hi Reshu Singh,

Thank you for reaching out. I need more information about your environment, what model you want to convert, and are you using TensorFlow 2?

 

Meanwhile, If you are using TensorFlow 2, could you please have a try to convert the model by adding more arguments to the conversion command.

 

For example, if you downloaded the SSD MobileNet V1 FPN 640x640 from TensorFlow 2 Detection Model Zoo , the sample command line to convert the model looks as follows:

 

python mo_tf.py --saved_model_dir "<Install_Dir>\openvino_2021.3.394\ssd_mobilenet_v1\saved_model" --transformations_config="<Install_Dir>\openvino_2021.3.394\deployment_tools\model_optimizer\extensions\front\tf\ssd_support_api_v2.0.json" --tensorflow_object_detection_api_pipeline_config="<Install_Dir>\openvino_2021.3.394\ssd_mobilenet_v1\pipeline.config"

 

For more information refer to Converting TensorFlow* Object Detection API Models.

 

 

Regards,

Syamimi

 

0 Kudos
Syamimi_Intel
Moderator
1,114 Views

Hi Reshu Singh,

This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.



Regards,

Syamimi


0 Kudos
Wenjing
Employee
1,090 Views

This is probably due to out of memory.

0 Kudos
resh
Beginner
1,077 Views

Thanks, The issue is resolved

0 Kudos
Reply