Add TransNetV2 ONNX model, license and model card

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 Tomáš Souček
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,38 @@
+---
+license: mit
+library_name: onnx
+pipeline_tag: video-classification
+tags:
+  - transnetv2
+  - shot-boundary-detection
+  - scene-detection
+  - video
+  - onnx
+---
+
+# TransNetV2 (ONNX)
+
+`transnetv2.onnx` — an ONNX export of **TransNetV2** for shot boundary
+detection (finding the hard cuts and gradual transitions between the shots of
+a video). Runs client-side with onnxruntime-web.
+
+## Inputs / outputs
+
+- **Input:** `input` float32 `[1, 100, 27, 48, 3]` — a window of 100 frames,
+  each resized to 48x27, RGB, values 0..255 (the graph divides by 255 itself).
+- **Outputs:** two float32 `[1, 100, 1]` per-frame **probabilities** (the
+  sigmoid is already applied):
+  - single-frame — the frame a cut lands on (the last frame of the outgoing shot);
+  - many-hot — every frame inside a transition (dissolve, fade, …).
+- Upstream inference slides the window by 50 frames with 25 frames of context
+  either side and keeps the middle 50 predictions of each window.
+
+## Provenance & license
+
+- **Model:** TransNetV2 — *TransNet V2: An effective deep network architecture
+  for fast shot transition detection* (Souček & Lokoč, 2020),
+  [soCzech/TransNetV2](https://github.com/soCzech/TransNetV2). Code and model
+  weights are released under the **MIT license**
+  (`Copyright (c) 2020 Tomáš Souček`), included here as `LICENSE`.
+- **ONNX export:** [elya5/transnetv2](https://huggingface.co/elya5/transnetv2)
+  (MIT), mirrored verbatim.

transnetv2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d54a682bace32f25136ef83ca2c9d403e8f8193775efeb995172a0d95a8e0c
+size 31250929