Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ This metric can be used to calculate object detection metrics. It has an option
|
|
20 |
|
21 |
## How to Use
|
22 |
```
|
23 |
-
>>> module = evaluate.load("
|
24 |
# shape: (n_images, m_predicted_bboxes, xywh)
|
25 |
>>> predictions = [
|
26 |
[
|
@@ -80,7 +80,7 @@ Each sub-dictionary holds performance metrics at the specific area range level:
|
|
80 |
#### Example 1
|
81 |
Basic usage example. Add predictions and references via `module.add_batch(predictions, references)` function. Finally, compute the metrics accross predictions and ground truths over different images via `module.compute()`.
|
82 |
```
|
83 |
-
>>> module = evaluate.load("
|
84 |
>>> predictions = [
|
85 |
[
|
86 |
[10, 15, 20, 25],
|
@@ -123,7 +123,7 @@ We can specify different area range levels, at which we would like to compute th
|
|
123 |
("medium", [6 ** 2, 12 ** 2]),
|
124 |
("large", [12 ** 2, 1e5 ** 2])
|
125 |
]
|
126 |
-
>>> module = evaluate.load("
|
127 |
>>> predictions = [
|
128 |
[
|
129 |
[10, 15, 5, 5],
|
|
|
20 |
|
21 |
## How to Use
|
22 |
```
|
23 |
+
>>> module = evaluate.load("SEA-AI/det-metrics")
|
24 |
# shape: (n_images, m_predicted_bboxes, xywh)
|
25 |
>>> predictions = [
|
26 |
[
|
|
|
80 |
#### Example 1
|
81 |
Basic usage example. Add predictions and references via `module.add_batch(predictions, references)` function. Finally, compute the metrics accross predictions and ground truths over different images via `module.compute()`.
|
82 |
```
|
83 |
+
>>> module = evaluate.load("SEA-AI/det-metrics", iou_thresholds=0.9)
|
84 |
>>> predictions = [
|
85 |
[
|
86 |
[10, 15, 20, 25],
|
|
|
123 |
("medium", [6 ** 2, 12 ** 2]),
|
124 |
("large", [12 ** 2, 1e5 ** 2])
|
125 |
]
|
126 |
+
>>> module = evaluate.load("SEA-AI/det-metrics", area_ranges_tuples=area_ranges_tuples)
|
127 |
>>> predictions = [
|
128 |
[
|
129 |
[10, 15, 5, 5],
|