Hi, I have got micrsoft form recognizer api which gives bounding box of 8 coordinates for a given class, how to draw bounding box using that. for eg: bounding_regions=[BoundingRegion(page_number=1, polygon=[Point(x=33.0, y=496.0), Point(x=169.0, y=496.0), Point(x=168.0, y=532.0), Point(x=33.0, y=532.0)])] they haven't provided in the documentation as well, if you could help, I would appreciate it. I have converted it into list like this [33.0, 496.0, 169.0, 496.0, 168.0, 532.0, 33.0, 532.0] but don't how to plot.
You can use torchvision API to convert bounding boxes - pytorch.org/vision/main/generated/torchvision.ops.box_convert.html or, if you look into many open source object detection projects you would find the functions to convert from one format to another If you are interested in changing the entire dataset in in one go then if you manage you dataset using fiftyone (github.com/voxel51/fiftyone) then they provide to export the dataset in different formats (pascal_voc, yolo etc)
there is a notebook for that tutorial. See in the description. What exactly are you looking for? If you are familiar with the concept then now there are many libraries that can abstract things for you. Check these out - filterpy.readthedocs.io/en/latest/ github.com/probml/dynamax
@@KapilSachdeva This is precisely what I was looking for; thank you. While watching your tutorial on KF, you mentioned that you would do a tutorial on particle filtering. Do you have any plans on releasing it soon?
Thanks a lot for your tutorials, they are very helpful
🙏
Hi, I have got micrsoft form recognizer api which gives bounding box of 8 coordinates for a given class, how to draw bounding box using that.
for eg:
bounding_regions=[BoundingRegion(page_number=1, polygon=[Point(x=33.0, y=496.0), Point(x=169.0, y=496.0), Point(x=168.0, y=532.0), Point(x=33.0, y=532.0)])]
they haven't provided in the documentation as well, if you could help, I would appreciate it. I have converted it into list like this
[33.0, 496.0, 169.0, 496.0, 168.0, 532.0, 33.0, 532.0] but don't how to plot.
Thanks, are there any websites/softwares to change formats between each other? (without uploading dataset itself)
You can use torchvision API to convert bounding boxes - pytorch.org/vision/main/generated/torchvision.ops.box_convert.html
or, if you look into many open source object detection projects you would find the functions to convert from one format to another
If you are interested in changing the entire dataset in in one go then if you manage you dataset using fiftyone (github.com/voxel51/fiftyone) then they provide to export the dataset in different formats (pascal_voc, yolo etc)
Can you do something related to the Kalman filter besides the video you already have, like an application in Python?
there is a notebook for that tutorial. See in the description.
What exactly are you looking for?
If you are familiar with the concept then now there are many libraries that can abstract things for you.
Check these out -
filterpy.readthedocs.io/en/latest/
github.com/probml/dynamax
@@KapilSachdeva This is precisely what I was looking for; thank you.
While watching your tutorial on KF, you mentioned that you would do a tutorial on particle filtering. Do you have any plans on releasing it soon?
Yes. Next year.
Thanks! But how do you get the coordinate of Giraffe ?
Initially you label it i.e. a human being draws a box around the objects of interest and assign it a class
Thanks
🙏
THANK TYOY SO MUCH