Commit
•
49dda6b
1
Parent(s):
37628ec
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
@@ -1,3 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Model Card for Diffusion Policy / PushT
|
2 |
|
3 |
Diffusion Policy (as per [Diffusion Policy: Visuomotor Policy
|
@@ -11,10 +16,6 @@ See the [LeRobot library](https://github.com/huggingface/lerobot) (particularly
|
|
11 |
|
12 |
## Training Details
|
13 |
|
14 |
-
TODO commit hash.
|
15 |
-
|
16 |
-
Trained with [LeRobot@d747195](https://github.com/huggingface/lerobot/tree/d747195c5733c4f68d4bfbe62632d6fc1b605712).
|
17 |
-
|
18 |
The model was trained using [LeRobot's training script](https://github.com/huggingface/lerobot/blob/d747195c5733c4f68d4bfbe62632d6fc1b605712/lerobot/scripts/train.py) and with the [pusht](https://huggingface.co/datasets/lerobot/pusht/tree/v1.3) dataset.
|
19 |
|
20 |
Here are the [loss](./train_loss.csv), [evaluation score](./eval_avg_max_reward.csv), [evaluation success rate](./eval_pc_success.csv) (with 50 rollouts) during training.
|
@@ -23,6 +24,8 @@ Here are the [loss](./train_loss.csv), [evaluation score](./eval_avg_max_reward.
|
|
23 |
|
24 |
This took about 7 hours to train on an Nvida RTX 3090.
|
25 |
|
|
|
|
|
26 |
## Evaluation
|
27 |
|
28 |
The model was evaluated on the `PushT` environment from [gym-pusht](https://github.com/huggingface/gym-pusht) and compared to a similar model trained with the original [Diffusion Policy code](https://github.com/real-stanford/diffusion_policy). There are two evaluation metrics on a per-episode basis:
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- lerobot/pusht
|
5 |
+
---
|
6 |
# Model Card for Diffusion Policy / PushT
|
7 |
|
8 |
Diffusion Policy (as per [Diffusion Policy: Visuomotor Policy
|
|
|
16 |
|
17 |
## Training Details
|
18 |
|
|
|
|
|
|
|
|
|
19 |
The model was trained using [LeRobot's training script](https://github.com/huggingface/lerobot/blob/d747195c5733c4f68d4bfbe62632d6fc1b605712/lerobot/scripts/train.py) and with the [pusht](https://huggingface.co/datasets/lerobot/pusht/tree/v1.3) dataset.
|
20 |
|
21 |
Here are the [loss](./train_loss.csv), [evaluation score](./eval_avg_max_reward.csv), [evaluation success rate](./eval_pc_success.csv) (with 50 rollouts) during training.
|
|
|
24 |
|
25 |
This took about 7 hours to train on an Nvida RTX 3090.
|
26 |
|
27 |
+
_Note: At the time of training, [this PR](https://github.com/huggingface/lerobot/pull/129) was also incorporated._
|
28 |
+
|
29 |
## Evaluation
|
30 |
|
31 |
The model was evaluated on the `PushT` environment from [gym-pusht](https://github.com/huggingface/gym-pusht) and compared to a similar model trained with the original [Diffusion Policy code](https://github.com/real-stanford/diffusion_policy). There are two evaluation metrics on a per-episode basis:
|