Update README.md
Browse files
README.md
CHANGED
|
@@ -96,23 +96,6 @@ for box, score in zip(output["boxes"], output["scores"]):
|
|
| 96 |
img[y1:y2, x1:x2] = cv2.GaussianBlur(img[y1:y2, x1:x2], (51, 51), 0)
|
| 97 |
cv2.imwrite("anonymized.jpg", img)
|
| 98 |
```
|
| 99 |
-
|
| 100 |
-
## Repository structure
|
| 101 |
-
|
| 102 |
-
```text
|
| 103 |
-
Faster-RCNN-Vision-ANN18/
|
| 104 |
-
βββ README.md # this model card
|
| 105 |
-
βββ best_model.pth # trained checkpoint
|
| 106 |
-
βββ models/ # model definition (Faster R-CNN + ResNet-50 FPN backbone)
|
| 107 |
-
β βββ __init__.py
|
| 108 |
-
β βββ backbone.py
|
| 109 |
-
β βββ faster_rcnn.py
|
| 110 |
-
βββ examples/
|
| 111 |
-
β βββ inputs/ # original test images
|
| 112 |
-
β βββ outputs/ # anonymized results
|
| 113 |
-
βββ assets/ # banner and illustration images
|
| 114 |
-
```
|
| 115 |
-
|
| 116 |
## Intended use
|
| 117 |
|
| 118 |
Research and privacy-oriented computer vision experiments: anonymizing license plates and house numbers in street-level imagery before storage or publication. Not intended for surveillance or for identifying individuals.
|
|
|
|
| 96 |
img[y1:y2, x1:x2] = cv2.GaussianBlur(img[y1:y2, x1:x2], (51, 51), 0)
|
| 97 |
cv2.imwrite("anonymized.jpg", img)
|
| 98 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
## Intended use
|
| 100 |
|
| 101 |
Research and privacy-oriented computer vision experiments: anonymizing license plates and house numbers in street-level imagery before storage or publication. Not intended for surveillance or for identifying individuals.
|