The weights the Distant Viewing Toolkit loads
Browse files- README.md +37 -0
- detect_shots.pt +3 -0
- laughter/laughter_classifier.json +0 -0
- laughter/laughter_net.pt +3 -0
- yolo26l_heads.pt +3 -0
README.md
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: mixed
|
| 4 |
+
tags:
|
| 5 |
+
- distant-viewing
|
| 6 |
+
- video
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Distant Viewing Toolkit models
|
| 10 |
+
|
| 11 |
+
The model weights that the [Distant Viewing Toolkit](https://github.com/distant-viewing/dvt)
|
| 12 |
+
loads and that are not published anywhere else. The toolkit fetches them from
|
| 13 |
+
here; the other models it uses come from their own repositories.
|
| 14 |
+
|
| 15 |
+
| File | Used by | What it is |
|
| 16 |
+
|-------------------------------------|------------|---------------------------------------------------------|
|
| 17 |
+
| `detect_shots.pt` | `frames` | TransNetV2 shot boundary weights, as a PyTorch state |
|
| 18 |
+
| `yolo26l_heads.pt` | `yolo` | a YOLO26-large detector trained to find heads |
|
| 19 |
+
| `laughter/laughter_net.pt` | `laughter` | the network of the laughter annotator |
|
| 20 |
+
| `laughter/laughter_classifier.json` | `laughter` | its classifier, 200 trees written out as json |
|
| 21 |
+
|
| 22 |
+
## Terms
|
| 23 |
+
|
| 24 |
+
The files do not share one license.
|
| 25 |
+
|
| 26 |
+
- `detect_shots.pt` holds the weights of TransNetV2 (Souček and Lokoč), which
|
| 27 |
+
its authors released under the MIT license.
|
| 28 |
+
- `yolo26l_heads.pt` was trained with the ultralytics library, which is
|
| 29 |
+
distributed under the AGPL-3.0 license. Read its terms before using these
|
| 30 |
+
weights in anything that is not open source.
|
| 31 |
+
- The two laughter files were trained by the Distant Viewing Lab and are
|
| 32 |
+
released under the MIT license.
|
| 33 |
+
|
| 34 |
+
## Citation
|
| 35 |
+
|
| 36 |
+
Arnold, Taylor and Lauren Tilton. "Distant Viewing: Analyzing Large Visual
|
| 37 |
+
Corpora." *Digital Scholarship in the Humanities*, 2019.
|
detect_shots.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9ad400f42624acfc799b19150304ff0570b8d7749467f75763f83b13fd6e96
|
| 3 |
+
size 30508715
|
laughter/laughter_classifier.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
laughter/laughter_net.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f663f0fc8c65459996a3d3d68780c3210269bb013d91447d921ab0c9b51117d
|
| 3 |
+
size 1105619
|
yolo26l_heads.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfe975e4d2853e71393fd8a30ad74b1c299997ae208d093b76cbf97e267464d7
|
| 3 |
+
size 52950821
|