- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I am opening this thread for a user question that landed on Intel FPGA forums. Question is related to Model Optimizer
Here is the direct link to customer questions.
Hi All,
Trying to generate .xml & .bin file by using model optimizer, with command
"python3 /home/datadrive1/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_optimizer/mo_tf.py --input_model 0818_pspnet_1.0_713_resnet_v1/frozen_inference_graph_opt.pb"
but it always fail with below log;
Model Optimizer version: 1.4.292.6ef7232d
[ ERROR ] Cannot infer shapes or values for node "pad_to_bounding_box/Pad".
[ ERROR ] Input tensor shape [ 1 1 256 256 3] and pads values (4, 2) do not match for Pad node pad_to_bounding_box/Pad
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function <function Pad.infer at 0x7f0994516f28>.
[ ERROR ] Or because the node inputs have incorrect values/shapes.
[ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
[ ERROR ] Run Model Optimizer with --log_level=DEBUG for more information.
[ ERROR ] Stopped shape/value propagation at "pad_to_bounding_box/Pad" node.
For more information please refer to Model Optimizer FAQ (<INSTALL_DIR>/deployment_tools/documentation/docs/MO_FAQ.html), question #38.
trying with some other model, but got same error log;
cmd:python3 /home/datadrive1/intel/computer_vision_sdk_2018.4.420/deployment_tools/model_optimizer/mo_tf.py --input_model
ICNet-model.pb
[ ERROR ] Shape is not defined for output 0 of "split".
[ ERROR ] Shape is not defined for output 1 of "split".
[ ERROR ] Shape is not defined for output 2 of "split".
[ ERROR ] Cannot infer shapes or values for node "split".
[ ERROR ] Not all output shapes were inferred or fully defined for node "split".
For more information please refer to Model Optimizer FAQ (<INSTALL_DIR>/deployment_tools/documentation/docs/MO_FAQ.html), question #40.
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function <function tf_split_infer at 0x7f0cae157d08>.
[ ERROR ] Or because the node inputs have incorrect values/shapes.
[ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
[ ERROR ] Run Model Optimizer with --log_level=DEBUG for more information.
[ ERROR ] Stopped shape/value propagation at "split" node.
I will link this post to Intel FPGA forum as well.
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
did you solve the problem?
![](/skins/images/C4F7392A5C68ACA60290C9576F107044/responsive_peak/images/icon_anonymous_message.png)
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page