Fix input and output shape/data type in roberta-sequence-classificati… #405
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…on-9 model Model expects input to have data type int64 and shape (batch_size, sequence_length) - while current input tensor has float64 and (1, 1, 6) shape. Regarding the output - model expects float32 data type and (batch_size, 2) shape - while current output tensor has float64 and (1, 1, 1, 2) shape. Signed-off-by: Mateusz Tabaka <mateusz.tabaka@intel.com>
wenbingl
approved these changes
Dec 16, 2020
KsenijaS
pushed a commit
to KsenijaS/models
that referenced
this pull request
Dec 17, 2020
…on-9 model (onnx#405) Model expects input to have data type int64 and shape (batch_size, sequence_length) - while current input tensor has float64 and (1, 1, 6) shape. Regarding the output - model expects float32 data type and (batch_size, 2) shape - while current output tensor has float64 and (1, 1, 1, 2) shape. Signed-off-by: Mateusz Tabaka <mateusz.tabaka@intel.com> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com> Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com>
wenbingl
added a commit
that referenced
this pull request
Jan 4, 2021
* enable export with dynamic axes Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * Fix output tensor in Yolo v4 model (#407) Seems like the outputs were the copies of the inputs. New outputs are generated with onnxruntime and grouped in test_data_set_* directories. Signed-off-by: Mateusz Tabaka <mateusz.tabaka@intel.com> Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * Fix input and output shape/data type in roberta-sequence-classification-9 model (#405) Model expects input to have data type int64 and shape (batch_size, sequence_length) - while current input tensor has float64 and (1, 1, 6) shape. Regarding the output - model expects float32 data type and (batch_size, 2) shape - while current output tensor has float64 and (1, 1, 1, 2) shape. Signed-off-by: Mateusz Tabaka <mateusz.tabaka@intel.com> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com> Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * Ultra-lightweight face detection model (#401) * ultraface Signed-off-by: asiryan <dmc5mod@yandex.ru> * dependencies Signed-off-by: asiryan <dmc5mod@yandex.ru> * contributors Signed-off-by: asiryan <dmc5mod@yandex.ru> * remove .pyc Signed-off-by: asiryan <dmc5mod@yandex.ru> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com> Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * add mobilenetv2 onnx model Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * add tar file Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> Co-authored-by: Mateusz Tabaka <mateusz.tabaka@intel.com> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com> Co-authored-by: Valery Asiryan <dmc5mod@yandex.ru>
jcwchen
pushed a commit
to jcwchen/models
that referenced
this pull request
Apr 26, 2022
…on-9 model (onnx#405) Model expects input to have data type int64 and shape (batch_size, sequence_length) - while current input tensor has float64 and (1, 1, 6) shape. Regarding the output - model expects float32 data type and (batch_size, 2) shape - while current output tensor has float64 and (1, 1, 1, 2) shape. Signed-off-by: Mateusz Tabaka <mateusz.tabaka@intel.com> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com>
jcwchen
pushed a commit
to jcwchen/models
that referenced
this pull request
Apr 26, 2022
* enable export with dynamic axes Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * Fix output tensor in Yolo v4 model (onnx#407) Seems like the outputs were the copies of the inputs. New outputs are generated with onnxruntime and grouped in test_data_set_* directories. Signed-off-by: Mateusz Tabaka <mateusz.tabaka@intel.com> Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * Fix input and output shape/data type in roberta-sequence-classification-9 model (onnx#405) Model expects input to have data type int64 and shape (batch_size, sequence_length) - while current input tensor has float64 and (1, 1, 6) shape. Regarding the output - model expects float32 data type and (batch_size, 2) shape - while current output tensor has float64 and (1, 1, 1, 2) shape. Signed-off-by: Mateusz Tabaka <mateusz.tabaka@intel.com> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com> Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * Ultra-lightweight face detection model (onnx#401) * ultraface Signed-off-by: asiryan <dmc5mod@yandex.ru> * dependencies Signed-off-by: asiryan <dmc5mod@yandex.ru> * contributors Signed-off-by: asiryan <dmc5mod@yandex.ru> * remove .pyc Signed-off-by: asiryan <dmc5mod@yandex.ru> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com> Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * add mobilenetv2 onnx model Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> * add tar file Signed-off-by: Ksenija Stanojevic <ksenija.stanojevic@gmail.com> Co-authored-by: Mateusz Tabaka <mateusz.tabaka@intel.com> Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com> Co-authored-by: Valery Asiryan <dmc5mod@yandex.ru>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
…on-9 model
Model expects input to have data type int64 and shape (batch_size, sequence_length) -
while current input tensor has float64 and (1, 1, 6) shape.
Regarding the output - model expects float32 data type and (batch_size, 2) shape -
while current output tensor has float64 and (1, 1, 1, 2) shape.
Signed-off-by: Mateusz Tabaka mateusz.tabaka@intel.com