Skip to content

[GSoC] Added TF and PyTorch detection model conversion cases#18237

Merged
alalek merged 3 commits intoopencv:masterfrom
LupusSanctus:am/pytorch_tf_det_tutorial
Apr 2, 2021
Merged

[GSoC] Added TF and PyTorch detection model conversion cases#18237
alalek merged 3 commits intoopencv:masterfrom
LupusSanctus:am/pytorch_tf_det_tutorial

Conversation

@LupusSanctus
Copy link
Copy Markdown

@LupusSanctus LupusSanctus commented Aug 31, 2020

GSoC project: "Write a tutorial about training a network in TF or PyTorch and then running it in OpenCV"

Part 1.Classification case.
Part 2. Segmentation case.
Part 3. Detection case.

Provided dnn_model_runner module part for the object detection model retrieval and processing for further reading and inference with OpenCV API.
Provided tutorial series.

Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

  • I agree to contribute to the project under Apache 2 License.
  • To the best of my knowledge, the proposed patch is not based on a code under GPL or other license that is incompatible with OpenCV
  • The PR is proposed to proper branch
  • There is reference to original bug report and related work
  • There is accuracy test, performance test and test data in opencv_extra repository, if applicable
    Patch to opencv_extra has the same branch name.
  • The feature is well documented and sample code can be built with the project CMake

@asmorkalov asmorkalov added category: dnn category: documentation Documentation fix or update labels Aug 31, 2020
@GArik GArik added the GSoC label Aug 31, 2020
@alalek
Copy link
Copy Markdown
Member

alalek commented Aug 31, 2020

Please ask your mentor to check licensing terms of added images. Add readme.md files with this information.

input_img = cv2.resize(input_img, (256, 256))

# define preprocess parameters
mean = np.array([0.485, 0.456, 0.406]) * 255.0
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It'll be great, if you point the origin of this values and where should users get it for other models.

@ichisadashioko
Copy link
Copy Markdown
Contributor

Is this feature abandoned at the moment?

@LupusSanctus LupusSanctus force-pushed the am/pytorch_tf_det_tutorial branch from d5e6d7c to f7a0920 Compare November 24, 2020 07:10
@alalek
Copy link
Copy Markdown
Member

alalek commented Nov 25, 2020

wants to merge 8 commits

Please squash commits into one, so we can see real size of this patch without history of intermediate changes.

@alalek
Copy link
Copy Markdown
Member

alalek commented Feb 6, 2021

Please squash commits into one (to trim git history) and rebase on the latest master?

@LupusSanctus LupusSanctus force-pushed the am/pytorch_tf_det_tutorial branch from f7a0920 to cdb496a Compare April 1, 2021 07:01
@LupusSanctus LupusSanctus changed the title WIP: [GSoC] Added TF and PyTorch detection model conversion cases [GSoC] Added TF and PyTorch detection model conversion cases Apr 1, 2021
@alalek alalek merged commit 1263949 into opencv:master Apr 2, 2021
@alalek alalek mentioned this pull request Apr 9, 2021
a-sajjad72 pushed a commit to a-sajjad72/opencv that referenced this pull request Mar 30, 2023
…utorial

[GSoC] Added TF and PyTorch detection model conversion cases

* Added object detection convertion pipeline and tutorials

* Added tutorial corrections
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants