compute the iou, slice picture etc.
Project description
ai_tool
ai tool
slice picture
from ai_tool.img_slide import yield_sub_img
# yield the sub image from the jpg
for bbox, sub_img in yield_sub_img("test.jpg", 0, 0, 180, 60):
clip = "-".join([str(x) for x in bbox])
print("sub img:{}".format(clip))
cv2.imshow(clip, sub_img)
cv2.waitKey(0)
IoU
compute the iou for tow boxes,
example box1 1, 2, 101, 102. location(1,2) is left-up, location(101,102) is right-down.
from ai_tool.bbox import BBox
bbox1 = BBox([1, 2, 101, 102])
bbox2 = BBox([11, 12, 121, 122])
iou = bbox1 / bbox2
print("iou", iou)
assert iou > 0.5
print('box1 S is', bbox1.S)
print('box1 & box2', bbox1 & bbox2)
print('box1 == box2', bbox1 == bbox2)
print('merge box1 + box2', bbox1 + bbox2)
print('merge box1 | box2', bbox1 | bbox2)
result is :
iou 0.5785714285714286
box1 S is 10000
box1 & box2 [11, 12, 101, 102]
box1 == box2 True
merge box1 + box2 [1, 2, 121, 122]
merge box1 | box2 [1, 2, 121, 122]
multi bbox operation
from ai_tool.bbox import BBoxes, BBox
bb1 = BBoxes(iou_thresh=0.6)
bb2 = BBoxes()
bb1.append([1,2, 101, 102])
bb1.append([1000, 2, 1101, 102])
bb2.append([11, 12, 111, 112])
bb2.append([1, 1002, 101, 1102])
# judge the bbox in bb1
print("[5, 5, 100, 100] in bb1", BBox([5, 5, 100, 100]) in bb1)
print("[100, 5, 200, 100] in bb1", BBox([100, 5, 200, 100]) in bb1)
# bb1 & bb2
print("bb1 & bb2", bb1 & bb2)
print("bb1 - bb2", bb1 - bb2)
print("bb2 - bb1", bb2 - bb1)
result is
[5, 5, 100, 100] in bb1 True
[100, 5, 200, 100] in bb1 False
bb1 & bb2 [[1, 2, 101, 102]]
bb1 - bb2 [[1000, 2, 1101, 102]]
bb2 - bb1 [[1, 1002, 101, 1102]]
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ai_tool-1.4.tar.gz
(6.6 kB
view details)
Built Distribution
ai_tool-1.4-py3-none-any.whl
(8.9 kB
view details)
File details
Details for the file ai_tool-1.4.tar.gz
.
File metadata
- Download URL: ai_tool-1.4.tar.gz
- Upload date:
- Size: 6.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/40.8.0 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 652e6be827a3cecec038c30f4cb0158b66536719530e97e47c287e56d5e4caf4 |
|
MD5 | 871d20dc4e2d5051eeea18b3789a7942 |
|
BLAKE2b-256 | f1f84ce50ea6212f293c3f409c5b5487f59669cd3d8271e467d09f7ab5dd8669 |
File details
Details for the file ai_tool-1.4-py3-none-any.whl
.
File metadata
- Download URL: ai_tool-1.4-py3-none-any.whl
- Upload date:
- Size: 8.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/40.8.0 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7441c6858c3f322abc73259a00585e50f6a2878fc8d9f7f901e6f1559199d623 |
|
MD5 | a032cc8534aa306b7b79be9bd78f719f |
|
BLAKE2b-256 | 496edb37c16dfb6cc45111fb23139d0e581481a5cd3c6a0ce4f667ec8b04f0f0 |