# Project: Machine Learning models for image classification, object detection and segmentation in Virtual Reality **URL:** \ **Category:** Radiology\ **Tags:** gsoc2022-project, radiology, 350-hour-project, gsoc2022\ **Created:** [May 20, 2022, 6:00pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506 "2022-05-20T18:00:03Z")\ **Posts on this page:** 20\ **Page:** 2
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [June 25, 2022, 9:06am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/21 "2022-06-25T09:06:01Z")
I was running experiments is Kaggle, but can create a GitHub repo to store them. Is it ok? UPD: here is my preliminary repo: [GitHub - DaniilOr/cv\_in\_vr: My GSoC 2022 project](https://github.com/DaniilOr/cv_in_vr) I will add more details to README soon (project/company info, the purpose of this project, repository structure etc) ---
**Author:** ![sunbiz](https://forums.librehealth.io/user_avatar/forums.librehealth.io/sunbiz/32/395_2.png) [@sunbiz](https://forums.librehealth.io/u/sunbiz)\ **Post date:** [June 25, 2022, 8:48pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/22 "2022-06-25T20:48:01Z")
Please use Gitlab under the LibreHealth organization. @pri2si17 or @r0bby can create one for you under the Radiology project. ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [June 25, 2022, 8:54pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/23 "2022-06-25T20:54:52Z")
Got it, I will migrate to gitlab. Thanks! ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [June 25, 2022, 8:55pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/24 "2022-06-25T20:55:12Z")
@DaniilOr Please use following repository to commit your codes: > **[LibreHealth / LibreHealth Radiology / lh-radiology-vr-models · GitLab](https://gitlab.com/librehealth/radiology/lh-radiology-vr-models/)** > > Machine learning models for VR. @sunbiz@judywawira Please open gitlab issues in this repository. ---
**Author:** ![r0bby](https://forums.librehealth.io/user_avatar/forums.librehealth.io/r0bby/32/1781_2.png) [@r0bby](https://forums.librehealth.io/u/r0bby)\ **Post date:** [June 25, 2022, 8:59pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/26 "2022-06-25T20:59:50Z")
I updated the naming but otherwise, this is fine – usually, I do: `lh-PROJECTNAME-REPONAME` which is sane IMHO and not too burdensome. `PROJECTNAME` is `radiology` in this case. `REPONAME` is entirely up to you. ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [June 25, 2022, 9:14pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/27 "2022-06-25T21:14:31Z")
My tasks: 1. Move notebooks with output to gitlab 2. Do one more multi class segmentation task Main blockers: 1. When downloading models from Kaggle, output can be vanished My expectations / what help I expect to receive: 1. Probably, I will need some feedback on my notebooks: approach, code style, information etc ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [June 28, 2022, 11:33pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/28 "2022-06-28T23:33:13Z")
Hi @sunbiz can @DaniilOr get GPU server to train the model? Please let us know. ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [July 3, 2022, 2:10am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/29 "2022-07-03T02:10:21Z")
@pri2si17 Hi, are you joining the meeting tonight? ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [July 3, 2022, 2:19am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/30 "2022-07-03T02:19:50Z")
My work for the past week: - Improved the multi class segmentation model (now IoU and dice scores even for the distorted model are close to 0.7 in the best case) - Created a MR to commit my experiments to gitlab (I have no access to LibreHealth repo, so just left the MR) [Segmentation (!1) · Merge requests · LibreHealth / LibreHealth Radiology / lh-radiology-vr-models · GitLab](https://gitlab.com/librehealth/radiology/lh-radiology-vr-models/-/merge_requests/1) - Start working towards the inference Tasks for next week: 0. Add something to experiments if needed 1. Commit codes for model inference (probably we have to discuss here the inference of the model) 2. Implement method for distorting bboxes for object detection Main blockers: 1. distorted bounding-boxes may not work well (in this case other options such as the change of bboxes shape could help) 2. It is not 100% clear how the inference should be implemented My expectations / what help I expect to receive: 1. Guidances regarding the inference ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [July 3, 2022, 9:59am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/31 "2022-07-03T09:59:40Z")
Hi @DaniilOr , sorry I got busy so I couldn’t join the meeting. I will have a look at the code and let you know. ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [July 3, 2022, 10:03am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/32 "2022-07-03T10:03:45Z")
That is fine. Waiting for any kind of feedback ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [July 9, 2022, 8:08pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/33 "2022-07-09T20:08:36Z")
My work for the past week: - Created an inference pipeline ([link](https://gitlab.com/DaniilOr/lh-radiology-vr-models/-/tree/segmentation/inference)) Tasks for next week: 1. Add something to inference if needed 2. Show findings on bbox transformation My expectations / what help I expect to receive: 1. Feedback on the inference ---
**Author:** ![r0bby](https://forums.librehealth.io/user_avatar/forums.librehealth.io/r0bby/32/1781_2.png) [@r0bby](https://forums.librehealth.io/u/r0bby)\ **Post date:** [July 10, 2022, 10:33pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/34 "2022-07-10T22:33:24Z")
Have you been blogging? ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [July 11, 2022, 4:10am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/35 "2022-07-11T04:10:22Z")
Sure, I was. Probably, some changes in the post were not saved, I will check it out ---
**Author:** ![r0bby](https://forums.librehealth.io/user_avatar/forums.librehealth.io/r0bby/32/1781_2.png) [@r0bby](https://forums.librehealth.io/u/r0bby)\ **Post date:** [July 12, 2022, 3:04am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/36 "2022-07-12T03:04:42Z")
Just share it here weekly – it’s a simple post and should not take too much extra time 🙂 ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [July 12, 2022, 1:15pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/37 "2022-07-12T13:15:37Z")
I was blogging here [https://daniilor.blogspot.com](https://daniilor.blogspot.com), so will just share links to new posts ---
**Author:** ![r0bby](https://forums.librehealth.io/user_avatar/forums.librehealth.io/r0bby/32/1781_2.png) [@r0bby](https://forums.librehealth.io/u/r0bby)\ **Post date:** [July 14, 2022, 2:50pm UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/38 "2022-07-14T14:50:27Z")
Yeah, that’s exactly what I want. It’s an easy way for those reading this thread to follow what you’re doing ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [July 17, 2022, 1:50am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/39 "2022-07-17T01:50:33Z")
Hi @DaniilOr this link is not working. Also, can you please provide work updates on forum for this week. I will meet you next week. ---
**Author:** ![DaniilOr](https://forums.librehealth.io/user_avatar/forums.librehealth.io/daniilor/32/1965_2.png) [@DaniilOr](https://forums.librehealth.io/u/DaniilOr)\ **Post date:** [July 17, 2022, 2:04am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/40 "2022-07-17T02:04:13Z")
Sure. It is possible that the platform I am using requires VPN in some countries (idk why). Here is the link to RSS feed of my blog: feed:[Daniil Orel GSoC 2022 blog](https://daniilor.blogspot.com/feeds/posts/default) My work for the past week: - Experimented with representation of bounding boxes for object detection in VR environment. - Found out that when an object is centred, we may just leave an original bounding box. For peripheral objects small corrections are needed (right now, using ellipses used to tackle this issue, but I am planning to use point-distortion algorithm) Tasks for next week: - Transfer Segmentation models to TensorRT / update their inference - Come up with the final algorithm for bounding boxes in VR My expectations / what help I expect to receive: 1. Feedback on MRs PS good luck with your conference ---
**Author:** ![pri2si17](https://forums.librehealth.io/user_avatar/forums.librehealth.io/pri2si17/32/1320_2.png) [@pri2si17](https://forums.librehealth.io/u/pri2si17)\ **Post date:** [July 17, 2022, 2:50am UTC](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506/41 "2022-07-17T02:50:06Z")
Hi @DaniilOr Thanks for the update. I am talking about the gitlab link. [Not Found (gitlab.com)](https://gitlab.com/DaniilOr/lh-radiology-vr-models/-/tree/segmentation) Your fork is not available to review the code. Please fix the url. [Previous page](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506.md?page=1) [Next page](https://forums.librehealth.io/t/project-machine-learning-models-for-image-classification-object-detection-and-segmentation-in-virtual-reality/4506.md?page=3)