Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

important information about bbox format and image_size as input. #677

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

important information about bbox format and image_size as input. #677

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions validated/vision/object_detection_segmentation/tiny-yolov3/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,16 @@ def preprocess(img):
image = Image.open(img_path)
# input
image_data = preprocess(image)

# if you give the image size from here, than you will need to take care of resizing the bounding boxes back to the input image.
image_size = np.array([image.size[1], image.size[0]], dtype=np.float32).reshape(1, 2)

# OR
# leave it like this so that model predicts the bounding box on the image directly.
# COSTED me hours to realise it
image_size = np.array([416, 416], dtype=np.float32).reshape(1, 2)


```

### Output of model
Expand All @@ -65,6 +74,8 @@ boxes: `(1x'n_candidates'x4)`, the coordinates of all anchor boxes,
scores: `(1x80x'n_candidates')`, the scores of all anchor boxes per class,
indices: `('nbox'x3)`, selected indices from the boxes tensor. The selected index format is (batch_index, class_index, box_index). The class list is [here](https://github.com/qqwweee/keras-yolo3/blob/master/model_data/coco_classes.txt)

**Format of the bounding boxes is : [y_min, x_min, y_max, x_max]**

### Postprocessing steps
Post processing and meaning of output
```python
Expand Down