Upload folder using huggingface_hub
Browse files- README.md +12 -13
- config.json +5 -3
- model.pth +3 -0
README.md
CHANGED
|
@@ -1,15 +1,14 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
---
|
| 4 |
-
# Kinesis motion imitation model (MoE with 3 experts)
|
| 5 |
|
| 6 |
-
## Model Description
|
| 7 |
-
- This model was trained on the KIT-Locomotion dataset and performs motion imitation using a musculoskeletal model (MyoLeg).
|
| 8 |
-
- For more details, please refer to the [paper](doi.org/10.48550/arXiv.2503.14637) and the [code repository](https://github.com/amathislab/Kinesis).
|
| 9 |
|
| 10 |
-
## Model Details
|
| 11 |
-
- **Framework**: PyTorch
|
| 12 |
-
- **Model Type**: MoE (Mixture of Experts) with 3 experts (MLP)
|
| 13 |
-
- **Training Data**: KIT-Locomotion dataset
|
| 14 |
-
- **Input**: Proprioceptive state and target motion frame
|
| 15 |
-
- **Output**: Target muscle lengths
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# Kinesis motion imitation model (MoE with 3 experts)
|
|
|
|
|
|
|
| 3 |
|
| 4 |
+
## Model Description
|
| 5 |
+
- This model was trained on the KIT-Locomotion dataset and performs motion imitation using a musculoskeletal model (MyoLeg).
|
| 6 |
+
- For more details, please refer to the [paper](doi.org/10.48550/arXiv.2503.14637) and the [code repository](https://github.com/amathislab/Kinesis).
|
| 7 |
|
| 8 |
+
## Model Details
|
| 9 |
+
- **Framework**: PyTorch
|
| 10 |
+
- **Model Type**: MoE (Mixture of Experts) with 3 experts (MLP)
|
| 11 |
+
- **Training Data**: KIT-Locomotion dataset
|
| 12 |
+
- **Input**: Proprioceptive state and target motion frame
|
| 13 |
+
- **Output**: Target muscle lengths
|
| 14 |
+
|
config.json
CHANGED
|
@@ -1,3 +1,5 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
{
|
| 3 |
+
"model_name": "kinesis_moe_imitation",
|
| 4 |
+
}
|
| 5 |
+
|
model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b35e082e2bf4f951222ba58706cdef8e3ad19ad579a512dc3663187003ebb6a1
|
| 3 |
+
size 184956157
|