ASL demo internal PR by mpashchenkov · Pull Request #4 · mpashchenkov/open_model_zoo

mpashchenkov · 2021-07-29T07:05:26Z

No description provided.

Merge OpenVINO toolkit 2021.2 content into master

Merge OpenVINO toolkit 2021.3 content into master

Merge OpenVINO toolkit 2021.4 content into master

…O-version ci: bump OpenVINO version

mpashchenkov · 2021-08-02T07:33:16Z

@dmatveev

@aDanPin, if interest is exist.

dmatveev · 2021-08-03T17:25:11Z

@@ -0,0 +1,12 @@
+# Copyright (C) 2018-2019 Intel Corporation


dmatveev · 2021-08-03T17:30:08Z

+private:
+    double smoothingFactor;
+    double value;
+};


Is it taken from the original demo and is this the way it is called in the original demo?

I get this from Gaze estimation. This will be removed, because OMZ get unified FPS counter soon.

Unified metrics have appeared. Will be removed.

dmatveev · 2021-08-03T17:30:41Z

+    }
+};
+
+} // namespace custom


I believe every sample have it now, is it worth putting it to some common place?

All demos use this stream_source (IFD soon). It is good point put this to common cpp_gapi folder.

openvinotoolkit#2778

dmatveev · 2021-08-03T17:38:18Z

+struct TrackedObject {
+    cv::Rect rect;
+    float confidence;
+
+    int object_id;
+
+    size_t frame_idx;


Can this structure be just plain? E.g. default field initializers and no constructor?

dmatveev · 2021-08-03T17:41:15Z

+            if      (key == 27) break;  //esc
+            if      (key == 48) id = 0; // person id
+            else if (key == 49) id = 1;
+            else if (key == 50) id = 2;
+            else if (key == 51) id = 3;
+            else if (key == 52) id = 4;
+            else if (key == 53) id = 5;
+            else if (key == 54) id = 6;
+            else if (key == 55) id = 7;
+            else if (key == 56) id = 8;
+            else if (key == 57) id = 9;
+            else if (key == 13) out_label_number = -1; // reset last gesture


magik numbers here?

Key codes for 0...9 buttons

Added comments.

dmatveev · 2021-08-03T18:08:59Z

+                std::copy_n(matR.begin<float>(), height * width,
+                            prepared_mat[0].begin<float>() + 0 * batch * height * width
+                                + step * height * width);
+                std::copy_n(matG.begin<float>(), height * width,
+                            prepared_mat[0].begin<float>() + 1 * batch * height * width
+                                + step * height * width);
+                std::copy_n(matB.begin<float>(), height * width,
+                            prepared_mat[0].begin<float>() + 2 * batch * height * width
+                                + step * height * width);


What I'd expect here is

The preprocessing part (crop, resize, covertTo, split) - happening only once per a new frame - if it is possble.

Only copy_n happenning for all (past+new) preprocessed frames to form the resulting blob.

dmatveev · 2021-08-03T18:09:46Z

+// Copyright (C) 2021 Intel Corporation
+// SPDX-License-Identifier: Apache-2.0
+//
+
+#include "exponential_averager.hpp"
+
+ExponentialAverager::ExponentialAverager(double smoothingFactor, double initValue):
+                     smoothingFactor(smoothingFactor), value(initValue) {
+}
+
+double ExponentialAverager::getAveragedValue() const {
+    return value;
+}
+
+void ExponentialAverager::updateValue(double newValue) {
+    value = smoothingFactor * newValue + (1. - smoothingFactor) * value;
+}


This thing looks quite tiny, it is used everywhere or just in a single place? If the latter, I'd drop a separate file here and put it right to the place where it is used.

Will be removed.

dmatveev · 2021-08-03T18:10:19Z

+        throw std::logic_error("Gesture file doesn't open.");
+    }
+    return labels;
+}


no newline here

dmatveev · 2021-08-03T18:10:47Z

+                cv::destroyWindow(storage_window_name_);
+            }
+        }
+    }


no newline here either, also the alignment "hangs"

dmatveev · 2021-08-03T18:11:10Z

        int id = 0;
        for (const auto& item : fn) {
            std::string label = item.name();
+            std::cout << label << std::endl;


is it required? Seems like an unstructured random output

No. Removed.

Co-authored-by: Anzhella Pankratova <anzhella.pankratova@intel.com>

Merge OpenVINO toolkit 2021.4.1 content into master

…drop in v1.0 (openvinotoolkit#2744)

* AC: port important bugfixes to release * set metric profiler for coco_orig_precision

…otoolkit#2771)

Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>

…tests_pedestrian_tracker Update tests for pedestrian_tracker_demo

* Fixed pylint(2.10.2) errors in AC files * Fix comment

* update pot import * preserve old import

…inotoolkit/open_model_zoo into feature/vl/support_tr_0016

Merge release into master

…vl/support_tr_0016 Text Recognition 0016

The file was deleted in open-edge-platform/geti#660

…rieval-update-link-to-gallery.txt demos/image_retrieval: update link to gallery.txt

…lkit#2903)

* Add inference adapter * Do not refer directly to model_executor attributes * Move Openvino interface from the demo and AsyncPipeline to Adapter, implement RemoteAdapter, add documentation to ModelAdapter Abstract class * Add the __call__ method to ModelBase class * Refactoring * Update get_input_layers(), get_output_layers(), add Metadata structure, separate the model reading from the loading * Update model wrappers for object_detection_demo, except YOLO wrappers * Update Deblurring, Monodepth demos * Update bert_named_entity_recognition, bert_question_answering demos * Move logging to OpenvinoAdapter, add class Core * Ngraph removed from YOLO * Fix * Update human_pose_estimation_demo + Openpose wrapper * Update hpe_associative_embedding wrapper, bert_question_answering_embedding demo * Fix in object_detection_demo * Delete extra EOF * Update yolo.py * Remove int2float(), add list of openvino precisions * Small fixes * Suggestions * Add ability to read network from byte buffer. * Update demos/common/python/openvino/model_zoo/model_api/adapters/openvino_adapter.py * Update demos/common/python/openvino/model_zoo/model_api/adapters/openvino_adapter.py * Remove trailing whitespaces Co-authored-by: eizamaliev <eduard.zamaliev@intel.com>

…g-strategy Change branching strategy Align the strategy with https://github.com/openvinotoolkit/openvino/wiki/Branches: master - development branch releases/202?/? - release branches

…-develop-master CONTRIBUTING.md: develop->master

…t#2908)

* update install section * update openvino-dev installation * add note about pip version

…ry usage

dmatveev · 2023-06-01T10:15:54Z

@mpashchenkov can you please close this PR? I believe its no longer relevant?

Roman Donchenko and others added 5 commits December 16, 2020 18:02

Merge pull request openvinotoolkit#1924 from openvinotoolkit/release

3386309

Merge OpenVINO toolkit 2021.2 content into master

Merge pull request openvinotoolkit#2238 from openvinotoolkit/release

9ca5dbe

Merge OpenVINO toolkit 2021.3 content into master

Merge pull request openvinotoolkit#2557 from openvinotoolkit/release

e37a163

Merge OpenVINO toolkit 2021.4 content into master

ci: bump OpenVINO version

a9b8216

Merge pull request openvinotoolkit#2570 from Wovchena/ci-bump-OpenVIN…

b1ff98b

…O-version ci: bump OpenVINO version

mpashchenkov force-pushed the mp/asl-demo branch from 461746f to 7e10d5b Compare August 2, 2021 07:24

dmatveev reviewed Aug 3, 2021

View reviewed changes

eizamaliev and others added 7 commits September 9, 2021 12:23

Add monodepth_demo

cfbbbb1

Fix

3355195

Update tests

b4e55fd

Add suggestions

cdd8793

Apply suggestions from code review

5b14fd2

Co-authored-by: Anzhella Pankratova <anzhella.pankratova@intel.com>

Merge pull request openvinotoolkit#2749 from openvinotoolkit/release

f97e6e2

Merge OpenVINO toolkit 2021.4.1 content into master

Use strict major version v0.24 for scikit-learn due to py3.6 support …

9e3a481

…drop in v1.0 (openvinotoolkit#2744)

mpashchenkov force-pushed the mp/asl-demo branch from 0d73094 to d66d8c5 Compare September 17, 2021 08:23

mpashchenkov changed the base branch from develop to master September 20, 2021 07:25

mpashchenkov changed the base branch from master to develop September 20, 2021 07:25

eaidova and others added 12 commits September 20, 2021 19:17

AC: port important bugfixes to release (openvinotoolkit#2763)

4fa7a19

* AC: port important bugfixes to release * set metric profiler for coco_orig_precision

Update demos/common/python/models/monodepth.py

c9a6bad

update documentation for retinanet-tf (openvinotoolkit#2769) (openvin…

793c191

…otoolkit#2771)

Merge remote-tracking branch 'b/develop' into HEAD

4369e2c

Move monodepth.py to openvino/model_zoo/model_api/

d65dbc1

Update tests for pedestrian_tracker_demo

2b88fa7

Update demos/tests/cases.py

3449c18

Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>

Fix: str -> ModelArg

59f3dc1

Merge pull request openvinotoolkit#2788 from anzhella-pankratova/fix_…

f462f63

…tests_pedestrian_tracker Update tests for pedestrian_tracker_demo

Fixed pylint(2.10.2) errors in AC files (openvinotoolkit#2789)

dd751c9

* Fixed pylint(2.10.2) errors in AC files * Fix comment

Raw comparison for reference (openvinotoolkit#2785)

e73d0fa

Model Quantizer: update pot import (openvinotoolkit#2790)

444c362

* update pot import * preserve old import

Vladimir and others added 19 commits November 17, 2021 15:30

Merge branch 'feature/vl/support_tr_0016' of https://github.com/openv…

bffc0dd

…inotoolkit/open_model_zoo into feature/vl/support_tr_0016

add details about decoder output

6b2f68e

Merge pull request openvinotoolkit#2897 from openvinotoolkit/release

0d7aeac

Merge release into master

Merge pull request openvinotoolkit#2891 from openvinotoolkit/feature/…

f22498f

…vl/support_tr_0016 Text Recognition 0016

demos/image_retrieval: update link to gallery.txt

a17cb30

The file was deleted in open-edge-platform/geti#660

Merge pull request openvinotoolkit#2901 from Wovchena/demos/image_ret…

ef53fec

…rieval-update-link-to-gallery.txt demos/image_retrieval: update link to gallery.txt

AC: fix initial reshape for dynamic inputs case (openvinotoolkit#2902)

091b79a

face-detection-adas-0001 interactive_face_detection_demo (openvinotoo…

9d508f1

…lkit#2903)

AC: support label map from datumaro (openvinotoolkit#2904)

60e560a

Merge branch 'develop' into change-branching-strategy

082858a

Merge pull request openvinotoolkit#2905 from Wovchena/change-branchin…

324b4cc

…g-strategy Change branching strategy Align the strategy with https://github.com/openvinotoolkit/openvino/wiki/Branches: master - development branch releases/202?/? - release branches

CONTRIBUTING.md: develop->master

298a1a6

Merge pull request openvinotoolkit#2906 from Wovchena/CONTRIBUTING.md…

0283008

…-develop-master CONTRIBUTING.md: develop->master

Fixed max_ind_range configuration in criteo converter (openvinotoolki…

4d3fc84

…t#2908)

model_tools: update installation section (openvinotoolkit#2863)

e14d01e

* update install section * update openvino-dev installation * add note about pip version

correct output format for classification models (openvinotoolkit#2910)

146a73b

AC: support openvino 2.0 launcher (openvinotoolkit#2898)

8441861

Gesture recognition demo

1aefc46

mpashchenkov force-pushed the mp/asl-demo branch from a492e88 to 1aefc46 Compare November 22, 2021 09:51

Pashchenkov Maxim added 9 commits November 26, 2021 11:29

Added lost move

92ee330

Changed rights

e1f4c5a

Applying comments

ee08b01

Applying comments + added check for negative value of source

b74d285

Removed extra cast

6926cf6

Wrapped time_step

bb5407a

Applying comments, added dropping batch info, fixed bug, reduced memo…

fe7fc7c

…ry usage

Warnings

b7fd126

Removed mistake

c290e15

Conversation

mpashchenkov commented Jul 29, 2021

Uh oh!

mpashchenkov commented Aug 2, 2021

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

dmatveev commented Jun 1, 2023

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

14 participants