riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 33 Packages Projects Releases Wiki Activity

Fixing visualization code for object detection to support both types of bounding box. (#27842)

Browse Source 
* fix: minor enhancement and fix in bounding box visualization example

The example that was trying to visualize the bounding box was not considering an edge case,
where the bounding box can be un-normalized. So using the same set of code, we can not get
results with a different dataset with un-normalized bounding box. This commit fixes that.

* run make clean

* add an additional note on the scenarios where the box viz code works

---------

Co-authored-by: Anindyadeep <anindya@pop-os.localdomain>
This commit is contained in:
Anindyadeep 2023-12-22 18:54:40 +05:30 committed by GitHub
parent 5da3db3fd5
commit 74d9d0cebb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
docs/source/en/tasks/object_detection.md
View File

@ -139,6 +139,17 @@ To get an even better understanding of the data, visualize an example in the dat
... box = annotations["bbox"][i]
... class_idx = annotations["category"][i]
... x, y, w, h = tuple(box)
... # Check if coordinates are normalized or not
... if max(box) > 1.0:
... # Coordinates are un-normalized, no need to re-scale them
... x1, y1 = int(x), int(y)
... x2, y2 = int(x + w), int(y + h)
... else:
... # Coordinates are normalized, re-scale them
... x1 = int(x * width)
... y1 = int(y * height)
... x2 = int((x + w) * width)
... y2 = int((y + h) * height)
... draw.rectangle((x, y, x + w, y + h), outline="red", width=1)
... draw.text((x, y), id2label[class_idx], fill="white")
@ -153,7 +164,7 @@ To visualize the bounding boxes with associated labels, you can get the labels f
the `category` field.
You'll also want to create dictionaries that map a label id to a label class (`id2label`) and the other way around (`label2id`).
You can use them later when setting up the model. Including these maps will make your model reusable by others if you share
it on the Hugging Face Hub.
it on the Hugging Face Hub. Please note that, the part of above code that draws the bounding boxes assume that it is in `XYWH` (x,y co-ordinates and width and height of the box) format. It might not work for other formats like `(x1, y1, x2, y2)`.
As a final step of getting familiar with the data, explore it for potential issues. One common problem with datasets for
object detection is bounding boxes that "stretch" beyond the edge of the image. Such "runaway" bounding boxes can raise