|
@ -17,9 +17,16 @@ This operator can compare two ordered sequences, then detect the range which fea |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
```python |
|
|
```python |
|
|
placeholder |
|
|
|
|
|
|
|
|
# simulate a video feature by 10 frames of 512d vectors. |
|
|
|
|
|
videos_embeddings = np.random.randn(10,512) |
|
|
|
|
|
videos_embeddings = videos_embeddings / np.linalg.norm(videos_embeddings,axis=1).reshape(10,-1) |
|
|
|
|
|
|
|
|
|
|
|
towhee.dc['src','dest']([[videos_embeddings,videos_embeddings]]) \ |
|
|
|
|
|
.video_copy_detection.temporal_network[('src','dest'), ('range', 'range_score')]() \ |
|
|
|
|
|
.show() |
|
|
``` |
|
|
``` |
|
|
|
|
|
|
|
|
|
|
|
<img src="./tabular.png" alt="result" style="height:60px;"/> |
|
|
|
|
|
|
|
|
<br /> |
|
|
<br /> |
|
|
|
|
|
|
|
@ -70,7 +77,7 @@ A Temporal Network operator takes two numpy.ndarray(shape(N,D) N: number of feat |
|
|
|
|
|
|
|
|
**Parameters:** |
|
|
**Parameters:** |
|
|
|
|
|
|
|
|
***src_video_vec data:*** *numpy.ndarray* |
|
|
|
|
|
|
|
|
***src_video_vec*** *numpy.ndarray* |
|
|
|
|
|
|
|
|
Source video feature vectors. |
|
|
Source video feature vectors. |
|
|
|
|
|
|
|
@ -79,10 +86,13 @@ A Temporal Network operator takes two numpy.ndarray(shape(N,D) N: number of feat |
|
|
Destination video feature vectors. |
|
|
Destination video feature vectors. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
**Returns:** *List[List[Int]], List[float] * |
|
|
|
|
|
|
|
|
**Returns:** |
|
|
|
|
|
|
|
|
The returned aligned range and similarity score. |
|
|
|
|
|
|
|
|
***aligned_ranges:*** *List[List[Int]]* |
|
|
|
|
|
|
|
|
|
|
|
The returned aligned range. |
|
|
|
|
|
|
|
|
|
|
|
***aligned_scores:*** *List[float]* |
|
|
|
|
|
|
|
|
|
|
|
The returned similarity scores(length same as aligned_ranges). |
|
|
|
|
|
|
|
|