Push model using huggingface_hub.
Browse files- README.md +12 -0
- config.json +64 -0
- model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- TDLP
|
| 5 |
+
- model_hub_mixin
|
| 6 |
+
- pytorch_model_hub_mixin
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
| 10 |
+
- Code: https://github.com/Robotmurlock/TDLP
|
| 11 |
+
- Paper: https://www.arxiv.org/abs/2512.22105
|
| 12 |
+
- Docs: https://github.com/Robotmurlock/TDLP
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"aggregator_params": {},
|
| 3 |
+
"aggregator_type": "sum",
|
| 4 |
+
"common_params": {
|
| 5 |
+
"dropout": 0.1,
|
| 6 |
+
"hidden_dim": 512,
|
| 7 |
+
"interaction_encoder_enable": true,
|
| 8 |
+
"interaction_encoder_ffn_dim": 1024,
|
| 9 |
+
"interaction_encoder_n_heads": 8,
|
| 10 |
+
"interaction_encoder_n_layers": 4,
|
| 11 |
+
"projector_intermediate_dim": 512,
|
| 12 |
+
"track_encoder_ffn_dim": 1024,
|
| 13 |
+
"track_encoder_n_heads": 8,
|
| 14 |
+
"track_encoder_n_layers": 4
|
| 15 |
+
},
|
| 16 |
+
"mm_dim": 1024,
|
| 17 |
+
"object_interaction_encoder_enable": true,
|
| 18 |
+
"object_interaction_encoder_params": {
|
| 19 |
+
"dropout": 0.1,
|
| 20 |
+
"hidden_dim": 1024,
|
| 21 |
+
"n_heads": 8,
|
| 22 |
+
"n_layers": 2
|
| 23 |
+
},
|
| 24 |
+
"per_feature_params": {
|
| 25 |
+
"appearance": {
|
| 26 |
+
"feature_encoder_params": {
|
| 27 |
+
"emb_size": 128,
|
| 28 |
+
"hidden_dim": 512
|
| 29 |
+
},
|
| 30 |
+
"feature_encoder_type": "parts_appearance",
|
| 31 |
+
"hidden_dim": 512,
|
| 32 |
+
"interaction_encoder_ffn_dim": 1024,
|
| 33 |
+
"track_encoder_enable_motion_encoder": false,
|
| 34 |
+
"track_encoder_ffn_dim": 1024
|
| 35 |
+
},
|
| 36 |
+
"bbox": {
|
| 37 |
+
"feature_encoder_params": {
|
| 38 |
+
"input_dim": 5
|
| 39 |
+
},
|
| 40 |
+
"feature_encoder_type": "motion"
|
| 41 |
+
},
|
| 42 |
+
"keypoints": {
|
| 43 |
+
"feature_encoder_params": {
|
| 44 |
+
"input_dim": 35
|
| 45 |
+
},
|
| 46 |
+
"feature_encoder_type": "motion"
|
| 47 |
+
}
|
| 48 |
+
},
|
| 49 |
+
"similarity_prediction_head_hidden_dim": 1024,
|
| 50 |
+
"sph_common_params": {
|
| 51 |
+
"hidden_dim": 512
|
| 52 |
+
},
|
| 53 |
+
"sph_per_feature_params": {
|
| 54 |
+
"appearance": {
|
| 55 |
+
"hidden_dim": 512
|
| 56 |
+
},
|
| 57 |
+
"bbox": {
|
| 58 |
+
"hidden_dim": 512
|
| 59 |
+
},
|
| 60 |
+
"keypoints": {
|
| 61 |
+
"hidden_dim": 512
|
| 62 |
+
}
|
| 63 |
+
}
|
| 64 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad61be077bc926fb89a7adb3a4a117e5d1ff7a27f51805195e78cb5e7cc3d794
|
| 3 |
+
size 309826976
|