Commit Graph

6 Commits

Author SHA1 Message Date
Mikhail Nosov
ce9a229313 [OV20] NV12toRGB and NV12toBGR operations specification (#7595)
* [OV20] NV12toRGB and NV12toBGR operations specification

* Changed supported type to "`uint8` or any supported floating-point type"

* Apply suggestions from code review

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2021-09-24 13:02:15 +03:00
Anastasia Popova
c776ea90d8 Added specification for RandomUniform operation. (#6196)
* Added RandomUniform specification.

* Extended description of obtaining float numbers.

* Added description of obtainin float16 and double values.

* Added description of xor symbol.

* Small correction.

* Small corrections.

* Added initial type attribute.

* Corrected IR example, removed unnecessary default values.

* Small correction.

* Added information about type cast between initial and output types.

* Removed initial type attribute.

* Corrected output_type description.

* Corrected minval, maxval description. Corrected IR example.

* Apply suggestions from code review

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>

* Removed unnecessary paper link.

Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
2021-07-23 14:22:53 +03:00
Eugeny Volosenkov
37b46de164 If spec (#6296)
* Add If specification

* Fix spec

* Fix doc

* Fix doc

* Fix Description

* Add detaile description

* Fix IR

* Fix IR

* Fix IR

* Fix IR

* fix doc

* fix doc

* Change internal network to subgraph

* move to condition dir

* Change opset in IR

* Fix comments

* Fix comments

* Fix comments

* Update to master

* fix comments

* fix ci
2021-07-21 15:52:37 +03:00
Pavel Esir
b2d25da04d [spec] add Gather-8 with negative indices (#6172)
* add Gather-8 with negative indices

* incremented version

* updated opset8.md
2021-06-21 15:33:13 +03:00
Ivan Tikhonov
8543b42ac0 DeformableConvolution v8 specification (#5684)
* ModulatedDeformableConvolution spec

* add bilinear_interpolation_mode attribute

* updated formulas for DeformableConv v1 and v8, applied review remarks

* fix doxygen formulas

* Update Deformable conv v8 spec, update docs
2021-06-18 09:50:29 +03:00
Maxim Vafin
c3ad7dc2a4 Specify AdaptiveAvgPool-8 and AdaptiveMaxPool-8 (#5773)
* Specify AdaptiveAvgPool-8 and AdaptiveMaxPool-8

* Apply review feedback

* Describe indices output

* Apply review feedback

* Apply review feedback

* Update AdaptiveMaxPool_8.md

* Apply suggestions from code review

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>

* Apply review feedback

Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com>
2021-06-10 18:09:35 +03:00