-
Notifications
You must be signed in to change notification settings - Fork 2.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Problem converting onnx model using inference engine #94
Comments
erez can you kindly attach your model and also the exact MO command you used so that we may assist you ? Also which version of ONNX are you using ? |
Certainly, thank you the the prompt response. The model class is attached below. In addition there are the custom functions i.e. i know it is a lot. basically this custom model is supposed to receive as an input a [1,1,960,1280] tensor and output [1,113,960,1280] tensor. It initially pads the input tensor and then follows the layers.
|
Hi erez. I meant your ONNX model (not your Pytorch model). Can you kindly attach your exported onnx model ? Also add --log_level DEBUG to your MO command so that I can see the debug logs. |
exported model is:
and the mo output with debug
|
erez what you attached is not an ONNX model, rather it seems to be a print of an ONNX model. I want to try mo_onnx.py myself - which is why I'm requesting a genuine onnx model. Anyway, let's try and debug just based on the print alone. The error seems to be directly related to the warning prior to the exception
Looking at the ONNX printout I see several examples of -1 in Tensor values. -1 is not an acceptable dimension value to Model Optimizer if it refers to incoming shape. Could this be the issue ? Numpy can infer dimensions based on -1 but Model Optimizer cannot. The builder of the model must be very specific about shape dimensions, starting with batch size. Additionally Line 67 is a 1x3 tensor while 61 and 64 are 1x6 tensors. The WARNING says the shape should be 4D. I would start though by getting rid of the -1 and see what happens next. %67 : Tensor = onnx::Constantvalue= -1 960 1280 [ CPULongType{3} ], scope: SlimNet |
sorry about that, my model is attached within the zip file here: i'll try getting rid of any -1 and update. |
@erezposner is this issue still actual? I can convert the model now with the following command line |
Yes it is still relevant. Thanks for taking the time to address this issue. |
It seems that the issues is not actual anymore as no response. Closing it. Feel free to reopen it or create a new one. |
* Small refactoring * Fix type * Fix python codestyle
* WIP * update input validation * upsample_nearest2d and upsample_bilinear2d support * support leaky_relu add test for inplace relu * update tests, add handler for ListConstruct * Do not create extra outputs in main body * add positive case with non-default value * update testing * update test, handle non constant size and scale * remove ie_device * add aten::group_norm support * refactoring * Enable aten::reshape_as operator and add layer test * more tests * Fix typo in test * Resolve conflicts * fix code style * expand init version * expand_as and tests * add transposed convolutions support * add tests * initial support pad * add circular * update for differenced in rang * cleanup * refactor * more tests * apply review comments * Add split+listunpack transformation * Add split+getitem transformation * Add test cases * fix typo * Minor fixes * Apply suggestions from code review Co-authored-by: Maxim Vafin <[email protected]> * Apply suggestions from code review * Small fix * Support converting models without freezing * support BoolTensor and masked_fill * add support aten::rsqrt and test for sqrt * add cumsum and type_as * support clamp * support more matrix operations * add tests * Add aten::adaptive_avg_pool3d and layer test * Change to rank * fix code style in utils.hpp * Update src/frontends/pytorch/src/op_table.cpp Co-authored-by: Sergey Lyalin <[email protected]> * fix code style * add tests * add xfail * remove unnecessary broadcast * Changes required by style formater * aten::_convolution_mode * Changes requested by a reviewer * remove code duplication * add aten::unbind transformation * full, zeros and ones * Support getattr list and unrolling nested ifs * Remove line change * Enable back freezing in layer tests * Add aten::norm operator and layer test * Small fix in layer test * add aten::roll * add empty line * Typo fix * fix style * fix style v2 * add pytorch frontend to wheel * Support all types of numeric norms * add check for dynamic shapes * remove random change * merge statements * add min and max ops support * aten::max and aten::min * move axes range creation to utils * add transformation for tuple results, update tests * fix copyright * aten::var * add test and translation for numel * ignore aten::clone * Add layer test for aten::add operator * Fix typo * Remove redundant import * Add parameter name in forward method * fix code style * apply review comments * Add size+slice+listunpack transform * Add append listunpack transformation * Register transformation * aten::where * update realization * Fix issue with getitem * Fix getitem * Add layer test for aten::view operator * Add tests for listunpack * add test for aten::div * fix style * update aten::adaptive_max_pool2d * fix style * add aten::floor_divide * aten::addmm support alpha and beta with different dtype * nonzero * Change test name * update test cases to include other dtypes * aten::arange * prim::max transformation for ListConstruct * rename op * generalize conv2d implementation for conv1d and conv3d * aten::unsqueeze_ and tests for aten::unsqueeze (#70) * add aten::le, aten::ge and tests for other tensor comparision ops (#74) * add support trigonometry ops (#73) * support aten::upsample_bicubic2d, aten::ceil, aten::floor (#72) Co-authored-by: Maxim Vafin <[email protected]> * extend and add tests for avg_pool and max_pool * extend tests and constant filling ops * fix as_tensor and full ops * aten::repeat * fix code style * aten::im2col (#61) * aten::im2col * remove debug prints, add number of elements check * fix failed tests * move helper function * use split * Update src/frontends/pytorch/src/op/im2col.cpp Co-authored-by: Maxim Vafin <[email protected]> * fix code style Co-authored-by: Maxim Vafin <[email protected]> * Update src/frontends/pytorch/src/utils.cpp Co-authored-by: Maxim Vafin <[email protected]> * fix code style * revert removeinf floordiv, add floor_divide file * Fix merge issue * reduce code duplication * refactor * Add len operator with layer test * update clamp to support mixed precision and add support torch.long for constants * aten::selu * add trunc mode to div * add else statement * Add test case to layer test * Fix submodules (#88) * update test file * fix namings * execute in fp64 and convert back to initial precision * Revert set_output_size to master. Small fix in If validate * Fix build and code style * fix failed tests * Add torchvision::nms operator and layer test * Change requested by a reviewer * Remove div test * convert constants to input type * Mark some cases in div tests as xfail (#93) * Small refactoring (#94) * Small refactoring * Fix type * Fix python codestyle * Incremental fix code style (#95) * Fix style (#96) * Fix copyright * Fix code style * Branch clean up (#97) * Optimize includes and force opset10 (#98) * Optimize includes * Force opset10 in pt fe * Fix codestyle (#99) * Fix style * Fix clang codestyle * Fix cerr with debug log * Update src/bindings/python/src/pyopenvino/frontend/pytorch/decoder.cpp * Add pytorch dependency only if pytorch frontend is enabled * Update src/bindings/python/src/pyopenvino/CMakeLists.txt * Add layer tests to precommit (#100) * Add layer tests to precommit * Remove accidentally added files * Apply code style on layer tests * batch norm tests and fixes * move default weight and bias to else block * reduce code duplication * Changes requested by a reviewer * Changes requested by a reviewer * Remove dependency from pytorch in pyopenvino (#102) * Remove dependency from pytorch when fe is disabled * Change docstring * Remove pytorch FE dependency from pyopenvino * Apply codestyle (#107) * Apply codestyle * Remove commented line * Apply suggestions from code review Co-authored-by: Roman Kazantsev <[email protected]> * Fix mock FE test (#108) * Fix mock PE test (#111) * Revert changes in StridedSlice (#114) * Small refactoring (#116) * Small refactoring * Fix codestyle * Apply suggestions from code review Co-authored-by: Roman Kazantsev <[email protected]> * Apply suggestions from code review * Update src/frontends/pytorch/src/op/group_norm.cpp * Fix cmake copyright define (#117) * Update src/frontends/pytorch/src/op/arange.cpp * Apply suggestions from code review * Update build configs (#120) * FIx build configs * Update type cast in full.cpp * Apply review feedback (#121) * Apply suggestions from code review * Apply suggestions from code review Co-authored-by: Roman Kazantsev <[email protected]> * Fix issue after master merge (#122) * Fix issue after master merge * Fix build Co-authored-by: eaidova <[email protected]> Co-authored-by: bszmelcz <[email protected]> Co-authored-by: Sergey Lyalin <[email protected]> Co-authored-by: sikorsl1 <[email protected]> Co-authored-by: Leonard Sikorski <[email protected]> Co-authored-by: Mateusz <[email protected]> Co-authored-by: Roman Kazantsev <[email protected]>
* WIP * update input validation * upsample_nearest2d and upsample_bilinear2d support * support leaky_relu add test for inplace relu * update tests, add handler for ListConstruct * Do not create extra outputs in main body * add positive case with non-default value * update testing * update test, handle non constant size and scale * remove ie_device * add aten::group_norm support * refactoring * Enable aten::reshape_as operator and add layer test * more tests * Fix typo in test * Resolve conflicts * fix code style * expand init version * expand_as and tests * add transposed convolutions support * add tests * initial support pad * add circular * update for differenced in rang * cleanup * refactor * more tests * apply review comments * Add split+listunpack transformation * Add split+getitem transformation * Add test cases * fix typo * Minor fixes * Apply suggestions from code review Co-authored-by: Maxim Vafin <[email protected]> * Apply suggestions from code review * Small fix * Support converting models without freezing * support BoolTensor and masked_fill * add support aten::rsqrt and test for sqrt * add cumsum and type_as * support clamp * support more matrix operations * add tests * Add aten::adaptive_avg_pool3d and layer test * Change to rank * fix code style in utils.hpp * Update src/frontends/pytorch/src/op_table.cpp Co-authored-by: Sergey Lyalin <[email protected]> * fix code style * add tests * add xfail * remove unnecessary broadcast * Changes required by style formater * aten::_convolution_mode * Changes requested by a reviewer * remove code duplication * add aten::unbind transformation * full, zeros and ones * Support getattr list and unrolling nested ifs * Remove line change * Enable back freezing in layer tests * Add aten::norm operator and layer test * Small fix in layer test * add aten::roll * add empty line * Typo fix * fix style * fix style v2 * add pytorch frontend to wheel * Support all types of numeric norms * add check for dynamic shapes * remove random change * merge statements * add min and max ops support * aten::max and aten::min * move axes range creation to utils * add transformation for tuple results, update tests * fix copyright * aten::var * add test and translation for numel * ignore aten::clone * Add layer test for aten::add operator * Fix typo * Remove redundant import * Add parameter name in forward method * fix code style * apply review comments * Add size+slice+listunpack transform * Add append listunpack transformation * Register transformation * aten::where * update realization * Fix issue with getitem * Fix getitem * Add layer test for aten::view operator * Add tests for listunpack * add test for aten::div * fix style * update aten::adaptive_max_pool2d * fix style * add aten::floor_divide * aten::addmm support alpha and beta with different dtype * nonzero * Change test name * update test cases to include other dtypes * aten::arange * prim::max transformation for ListConstruct * rename op * generalize conv2d implementation for conv1d and conv3d * aten::unsqueeze_ and tests for aten::unsqueeze (#70) * add aten::le, aten::ge and tests for other tensor comparision ops (#74) * add support trigonometry ops (#73) * support aten::upsample_bicubic2d, aten::ceil, aten::floor (#72) Co-authored-by: Maxim Vafin <[email protected]> * extend and add tests for avg_pool and max_pool * extend tests and constant filling ops * fix as_tensor and full ops * aten::repeat * fix code style * aten::im2col (#61) * aten::im2col * remove debug prints, add number of elements check * fix failed tests * move helper function * use split * Update src/frontends/pytorch/src/op/im2col.cpp Co-authored-by: Maxim Vafin <[email protected]> * fix code style Co-authored-by: Maxim Vafin <[email protected]> * Update src/frontends/pytorch/src/utils.cpp Co-authored-by: Maxim Vafin <[email protected]> * fix code style * revert removeinf floordiv, add floor_divide file * Fix merge issue * reduce code duplication * refactor * Add len operator with layer test * update clamp to support mixed precision and add support torch.long for constants * aten::selu * add trunc mode to div * add else statement * Add test case to layer test * Fix submodules (#88) * update test file * fix namings * execute in fp64 and convert back to initial precision * Revert set_output_size to master. Small fix in If validate * Fix build and code style * fix failed tests * Add torchvision::nms operator and layer test * Change requested by a reviewer * Remove div test * convert constants to input type * Mark some cases in div tests as xfail (#93) * Small refactoring (#94) * Small refactoring * Fix type * Fix python codestyle * Incremental fix code style (#95) * Fix style (#96) * Fix copyright * Fix code style * Branch clean up (#97) * Optimize includes and force opset10 (#98) * Optimize includes * Force opset10 in pt fe * Fix codestyle (#99) * Fix style * Fix clang codestyle * Fix cerr with debug log * Update src/bindings/python/src/pyopenvino/frontend/pytorch/decoder.cpp * Add pytorch dependency only if pytorch frontend is enabled * Update src/bindings/python/src/pyopenvino/CMakeLists.txt * Add layer tests to precommit (#100) * Add layer tests to precommit * Remove accidentally added files * Apply code style on layer tests * batch norm tests and fixes * move default weight and bias to else block * reduce code duplication * Changes requested by a reviewer * Changes requested by a reviewer * Remove dependency from pytorch in pyopenvino (#102) * Remove dependency from pytorch when fe is disabled * Change docstring * Remove pytorch FE dependency from pyopenvino * Apply codestyle (#107) * Apply codestyle * Remove commented line * Apply suggestions from code review Co-authored-by: Roman Kazantsev <[email protected]> * Fix mock FE test (#108) * Fix mock PE test (#111) * Revert changes in StridedSlice (#114) * Small refactoring (#116) * Small refactoring * Fix codestyle * Apply suggestions from code review Co-authored-by: Roman Kazantsev <[email protected]> * Apply suggestions from code review * Update src/frontends/pytorch/src/op/group_norm.cpp * Fix cmake copyright define (#117) * Update src/frontends/pytorch/src/op/arange.cpp * Apply suggestions from code review * Update build configs (#120) * FIx build configs * Update type cast in full.cpp * Apply review feedback (#121) * Apply suggestions from code review * Apply suggestions from code review Co-authored-by: Roman Kazantsev <[email protected]> * Fix issue after master merge (#122) * Fix issue after master merge * Fix build Co-authored-by: eaidova <[email protected]> Co-authored-by: bszmelcz <[email protected]> Co-authored-by: Sergey Lyalin <[email protected]> Co-authored-by: sikorsl1 <[email protected]> Co-authored-by: Leonard Sikorski <[email protected]> Co-authored-by: Mateusz <[email protected]> Co-authored-by: Roman Kazantsev <[email protected]>
Hi,
I'm trying to optimize a custom network using the model optimizer using the following command
python mo_onnx.py --input_model "C:\Users\erez.posner\Desktop\FDFE.onnx"
and get the following error (below):
[4,1,H/2,H/2] .
i suspect an issue with batch dimension change during run. could this be the case? thank you
The text was updated successfully, but these errors were encountered: