Add A20 batch-512 trim-v2 step-4000 checkpoint
Browse files- README.md +41 -0
- a20-basket-transfer/b512-trimv2/step-004000/SHA256SUMS +9 -0
- a20-basket-transfer/b512-trimv2/step-004000/config.json +884 -0
- a20-basket-transfer/b512-trimv2/step-004000/model.pt +3 -0
- a20-basket-transfer/b512-trimv2/step-004000/protocol.json +11 -0
- code/hb_baselines_v1/baselines/__init__.py +8 -0
- code/hb_baselines_v1/baselines/act_nets.py +615 -0
- code/hb_baselines_v1/baselines/nets.py +207 -0
- code/hb_baselines_v1/baselines/policies.py +281 -0
- code/hb_baselines_v1/baselines/requirements.txt +12 -0
- code/hb_baselines_v1/baselines/runtime.py +123 -0
README.md
CHANGED
|
@@ -42,3 +42,44 @@ Training uses the Humanoid Benchmark online data augmentation spec v2 (15 photom
|
|
| 42 |
effects, one of them boosted to 1.5x per sample) with the model's own image augmentation turned off, plus joint-angle
|
| 43 |
bias and noise on the proprioception (column "Proprio augmentation"; the earlier recipe also delayed the
|
| 44 |
proprioception and dropped action-history rows).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
effects, one of them boosted to 1.5x per sample) with the model's own image augmentation turned off, plus joint-angle
|
| 43 |
bias and noise on the proprioception (column "Proprio augmentation"; the earlier recipe also delayed the
|
| 44 |
proprioception and dropped action-history rows).
|
| 45 |
+
|
| 46 |
+
## A20 pre-reach trim v2, batch 512, step 4000 (2026-11-17)
|
| 47 |
+
|
| 48 |
+
Checkpoint: [`a20-basket-transfer/b512-trimv2/step-004000/`](a20-basket-transfer/b512-trimv2/step-004000).
|
| 49 |
+
|
| 50 |
+
Trained on 100 demonstrations (54,433 frames) from
|
| 51 |
+
`humanoid-benchmark/a20-basket-transfer-pre-reach-trim-expert-v2`, with batch size 512,
|
| 52 |
+
4,000 optimizer steps, seed 0, EMA weights (decay 0.9999), and Humanoid Benchmark
|
| 53 |
+
augmentation v2. These weights use the `hb_baselines/1` format.
|
| 54 |
+
|
| 55 |
+
Inputs: Unitree G1 state44 and separate `ego_view` and `chest` RGB images, resized
|
| 56 |
+
to 168 x 224. Output: 16 actions of dimension 76 (64 SONIC motion-token values and
|
| 57 |
+
6 measured values for each INSPIRE hand). Normalization is stored in the weights.
|
| 58 |
+
The ResNet18 visual backbone was initialized with ImageNet weights and fine-tuned.
|
| 59 |
+
|
| 60 |
+
The checkpoint contains `model.pt`, `config.json` and `protocol.json` (weight size
|
| 61 |
+
and SHA-256). `SHA256SUMS` covers the checkpoint and the accompanying inference
|
| 62 |
+
source snapshot. The snapshot is under `code/hb_baselines_v1/`; its requirements
|
| 63 |
+
record the training environment. Optimizer/resume state is excluded.
|
| 64 |
+
|
| 65 |
+
After downloading this repository and installing its inference dependencies,
|
| 66 |
+
load the checkpoint from the repository root:
|
| 67 |
+
|
| 68 |
+
```python
|
| 69 |
+
import sys
|
| 70 |
+
sys.path.insert(0, 'code/hb_baselines_v1')
|
| 71 |
+
from baselines.runtime import BaselinePolicy
|
| 72 |
+
|
| 73 |
+
policy = BaselinePolicy(
|
| 74 |
+
'a20-basket-transfer/b512-trimv2/step-004000',
|
| 75 |
+
device='cpu', policy='act', robot='g1',
|
| 76 |
+
)
|
| 77 |
+
print(policy.info())
|
| 78 |
+
```
|
| 79 |
+
|
| 80 |
+
The saved weights passed SHA-256 verification and strict CPU loading before upload.
|
| 81 |
+
The offline metrics in `config.json` use training frames; they are not held-out
|
| 82 |
+
or closed-loop task success rates.
|
| 83 |
+
|
| 84 |
+
This release uses the accompanying benchmark baseline loader. The earlier
|
| 85 |
+
`epoch-XXX` releases retain their original Psi0 ACT loader and file format.
|
a20-basket-transfer/b512-trimv2/step-004000/SHA256SUMS
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
1dbec854e53d5c9098c3c51b4df35f33c1916abc0016f702be64d4e279382b65 a20-basket-transfer/b512-trimv2/step-004000/config.json
|
| 2 |
+
42235f4f164febb7136fafcd899c7fa2ac4a558fab9615a0565de74acf8b856c a20-basket-transfer/b512-trimv2/step-004000/model.pt
|
| 3 |
+
63d34ce738d8866211aece1c1dbca648e4a8ffbb732a6b2bf5ffca45d5646a3a a20-basket-transfer/b512-trimv2/step-004000/protocol.json
|
| 4 |
+
0a8ee3ccab6e183804c08066a9e7eb207d9b13ca38c0e596ce5d58c8302d7929 code/hb_baselines_v1/baselines/__init__.py
|
| 5 |
+
3db95cd8e4e436875e11f1054a99d250ca7d94e0127909090b58730402340f19 code/hb_baselines_v1/baselines/act_nets.py
|
| 6 |
+
38a66937bb92393a3f1ce0644b249da28d582a4fd03d134b7743e6037abd88b9 code/hb_baselines_v1/baselines/nets.py
|
| 7 |
+
750d4c6193aabcacc0f53df26c2c51f64b3f836b940b32ccb5c69f5959419afa code/hb_baselines_v1/baselines/policies.py
|
| 8 |
+
bb211f66038e53efd08ee3ec03e133d8bb206ec36cc608d349b4fad3a61e874b code/hb_baselines_v1/baselines/requirements.txt
|
| 9 |
+
5d680d59124ca83f9c2088f8e1738395b87ddc58798acf7815e163102738b7ae code/hb_baselines_v1/baselines/runtime.py
|
a20-basket-transfer/b512-trimv2/step-004000/config.json
ADDED
|
@@ -0,0 +1,884 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"policy": {
|
| 3 |
+
"policy": "act",
|
| 4 |
+
"n_cameras": 2,
|
| 5 |
+
"state_dim": 44,
|
| 6 |
+
"action_dim": 76,
|
| 7 |
+
"horizon": 16,
|
| 8 |
+
"backbone": "resnet18",
|
| 9 |
+
"backbone_weights": "IMAGENET1K_V1",
|
| 10 |
+
"backbone_norm": "frozen_bn",
|
| 11 |
+
"hidden_dim": 384,
|
| 12 |
+
"num_layers": 4,
|
| 13 |
+
"num_heads": 8,
|
| 14 |
+
"mlp_ratio": 4.0,
|
| 15 |
+
"dropout": 0.1,
|
| 16 |
+
"time_embed_dim": 128,
|
| 17 |
+
"num_inference_steps": null,
|
| 18 |
+
"num_train_timesteps": 100,
|
| 19 |
+
"beta_schedule": "squaredcos_cap_v2",
|
| 20 |
+
"prediction_type": "epsilon",
|
| 21 |
+
"clip_sample": true,
|
| 22 |
+
"act_hidden_dim": 512,
|
| 23 |
+
"dim_feedforward": 3200,
|
| 24 |
+
"enc_layers": 4,
|
| 25 |
+
"dec_layers": 7,
|
| 26 |
+
"nheads": 8,
|
| 27 |
+
"latent_dim": 32,
|
| 28 |
+
"kl_weight": 10.0,
|
| 29 |
+
"extra": {}
|
| 30 |
+
},
|
| 31 |
+
"contract": {
|
| 32 |
+
"name": "g1_sonic_dfx6",
|
| 33 |
+
"robot": "g1",
|
| 34 |
+
"cameras": [
|
| 35 |
+
"ego_view",
|
| 36 |
+
"chest"
|
| 37 |
+
],
|
| 38 |
+
"state": [
|
| 39 |
+
[
|
| 40 |
+
"observation.state",
|
| 41 |
+
0,
|
| 42 |
+
29
|
| 43 |
+
],
|
| 44 |
+
[
|
| 45 |
+
"observation.inspire_left_hand_state",
|
| 46 |
+
0,
|
| 47 |
+
6
|
| 48 |
+
],
|
| 49 |
+
[
|
| 50 |
+
"observation.inspire_right_hand_state",
|
| 51 |
+
0,
|
| 52 |
+
6
|
| 53 |
+
],
|
| 54 |
+
[
|
| 55 |
+
"observation.projected_gravity",
|
| 56 |
+
0,
|
| 57 |
+
3
|
| 58 |
+
]
|
| 59 |
+
],
|
| 60 |
+
"action": [
|
| 61 |
+
[
|
| 62 |
+
"action.motion_token",
|
| 63 |
+
0,
|
| 64 |
+
64
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
"observation.inspire_left_hand_state",
|
| 68 |
+
0,
|
| 69 |
+
6
|
| 70 |
+
],
|
| 71 |
+
[
|
| 72 |
+
"observation.inspire_right_hand_state",
|
| 73 |
+
0,
|
| 74 |
+
6
|
| 75 |
+
]
|
| 76 |
+
],
|
| 77 |
+
"state_dim": 44,
|
| 78 |
+
"action_dim": 76,
|
| 79 |
+
"action_space": "sonic_dfx6",
|
| 80 |
+
"body_dims": 29
|
| 81 |
+
},
|
| 82 |
+
"image_hw": [
|
| 83 |
+
168,
|
| 84 |
+
224
|
| 85 |
+
],
|
| 86 |
+
"task_text": "Grasp the basket handle with the right hand from the v10 round table, walk while raising it, place and release it on the long desk, then withdraw the open right hand diagonally backward and upward without an additional downward arm return.",
|
| 87 |
+
"dataset": {
|
| 88 |
+
"name": "a20-basket-transfer-pre-reach-trim-expert-v2",
|
| 89 |
+
"root": "/mnt/data0/zuo/Humanoid_benchmark/data/baselines/a20-basket-transfer-pre-reach-trim-expert-v2",
|
| 90 |
+
"robot_type": null,
|
| 91 |
+
"fps": 30.0,
|
| 92 |
+
"episodes": [
|
| 93 |
+
0,
|
| 94 |
+
1,
|
| 95 |
+
2,
|
| 96 |
+
3,
|
| 97 |
+
4,
|
| 98 |
+
5,
|
| 99 |
+
6,
|
| 100 |
+
7,
|
| 101 |
+
8,
|
| 102 |
+
9,
|
| 103 |
+
10,
|
| 104 |
+
11,
|
| 105 |
+
12,
|
| 106 |
+
13,
|
| 107 |
+
14,
|
| 108 |
+
15,
|
| 109 |
+
16,
|
| 110 |
+
17,
|
| 111 |
+
18,
|
| 112 |
+
19,
|
| 113 |
+
20,
|
| 114 |
+
21,
|
| 115 |
+
22,
|
| 116 |
+
23,
|
| 117 |
+
24,
|
| 118 |
+
25,
|
| 119 |
+
26,
|
| 120 |
+
27,
|
| 121 |
+
28,
|
| 122 |
+
29,
|
| 123 |
+
30,
|
| 124 |
+
31,
|
| 125 |
+
32,
|
| 126 |
+
33,
|
| 127 |
+
34,
|
| 128 |
+
35,
|
| 129 |
+
36,
|
| 130 |
+
37,
|
| 131 |
+
38,
|
| 132 |
+
39,
|
| 133 |
+
40,
|
| 134 |
+
41,
|
| 135 |
+
42,
|
| 136 |
+
43,
|
| 137 |
+
44,
|
| 138 |
+
45,
|
| 139 |
+
46,
|
| 140 |
+
47,
|
| 141 |
+
48,
|
| 142 |
+
49,
|
| 143 |
+
50,
|
| 144 |
+
51,
|
| 145 |
+
52,
|
| 146 |
+
53,
|
| 147 |
+
54,
|
| 148 |
+
55,
|
| 149 |
+
56,
|
| 150 |
+
57,
|
| 151 |
+
58,
|
| 152 |
+
59,
|
| 153 |
+
60,
|
| 154 |
+
61,
|
| 155 |
+
62,
|
| 156 |
+
63,
|
| 157 |
+
64,
|
| 158 |
+
65,
|
| 159 |
+
66,
|
| 160 |
+
67,
|
| 161 |
+
68,
|
| 162 |
+
69,
|
| 163 |
+
70,
|
| 164 |
+
71,
|
| 165 |
+
72,
|
| 166 |
+
73,
|
| 167 |
+
74,
|
| 168 |
+
75,
|
| 169 |
+
76,
|
| 170 |
+
77,
|
| 171 |
+
78,
|
| 172 |
+
79,
|
| 173 |
+
80,
|
| 174 |
+
81,
|
| 175 |
+
82,
|
| 176 |
+
83,
|
| 177 |
+
84,
|
| 178 |
+
85,
|
| 179 |
+
86,
|
| 180 |
+
87,
|
| 181 |
+
88,
|
| 182 |
+
89,
|
| 183 |
+
90,
|
| 184 |
+
91,
|
| 185 |
+
92,
|
| 186 |
+
93,
|
| 187 |
+
94,
|
| 188 |
+
95,
|
| 189 |
+
96,
|
| 190 |
+
97,
|
| 191 |
+
98,
|
| 192 |
+
99
|
| 193 |
+
],
|
| 194 |
+
"train_episodes": [
|
| 195 |
+
0,
|
| 196 |
+
1,
|
| 197 |
+
2,
|
| 198 |
+
3,
|
| 199 |
+
4,
|
| 200 |
+
5,
|
| 201 |
+
6,
|
| 202 |
+
7,
|
| 203 |
+
8,
|
| 204 |
+
9,
|
| 205 |
+
10,
|
| 206 |
+
11,
|
| 207 |
+
12,
|
| 208 |
+
13,
|
| 209 |
+
14,
|
| 210 |
+
15,
|
| 211 |
+
16,
|
| 212 |
+
17,
|
| 213 |
+
18,
|
| 214 |
+
19,
|
| 215 |
+
20,
|
| 216 |
+
21,
|
| 217 |
+
22,
|
| 218 |
+
23,
|
| 219 |
+
24,
|
| 220 |
+
25,
|
| 221 |
+
26,
|
| 222 |
+
27,
|
| 223 |
+
28,
|
| 224 |
+
29,
|
| 225 |
+
30,
|
| 226 |
+
31,
|
| 227 |
+
32,
|
| 228 |
+
33,
|
| 229 |
+
34,
|
| 230 |
+
35,
|
| 231 |
+
36,
|
| 232 |
+
37,
|
| 233 |
+
38,
|
| 234 |
+
39,
|
| 235 |
+
40,
|
| 236 |
+
41,
|
| 237 |
+
42,
|
| 238 |
+
43,
|
| 239 |
+
44,
|
| 240 |
+
45,
|
| 241 |
+
46,
|
| 242 |
+
47,
|
| 243 |
+
48,
|
| 244 |
+
49,
|
| 245 |
+
50,
|
| 246 |
+
51,
|
| 247 |
+
52,
|
| 248 |
+
53,
|
| 249 |
+
54,
|
| 250 |
+
55,
|
| 251 |
+
56,
|
| 252 |
+
57,
|
| 253 |
+
58,
|
| 254 |
+
59,
|
| 255 |
+
60,
|
| 256 |
+
61,
|
| 257 |
+
62,
|
| 258 |
+
63,
|
| 259 |
+
64,
|
| 260 |
+
65,
|
| 261 |
+
66,
|
| 262 |
+
67,
|
| 263 |
+
68,
|
| 264 |
+
69,
|
| 265 |
+
70,
|
| 266 |
+
71,
|
| 267 |
+
72,
|
| 268 |
+
73,
|
| 269 |
+
74,
|
| 270 |
+
75,
|
| 271 |
+
76,
|
| 272 |
+
77,
|
| 273 |
+
78,
|
| 274 |
+
79,
|
| 275 |
+
80,
|
| 276 |
+
81,
|
| 277 |
+
82,
|
| 278 |
+
83,
|
| 279 |
+
84,
|
| 280 |
+
85,
|
| 281 |
+
86,
|
| 282 |
+
87,
|
| 283 |
+
88,
|
| 284 |
+
89,
|
| 285 |
+
90,
|
| 286 |
+
91,
|
| 287 |
+
92,
|
| 288 |
+
93,
|
| 289 |
+
94,
|
| 290 |
+
95,
|
| 291 |
+
96,
|
| 292 |
+
97,
|
| 293 |
+
98,
|
| 294 |
+
99
|
| 295 |
+
],
|
| 296 |
+
"val_episodes": [],
|
| 297 |
+
"train_frames": 54433,
|
| 298 |
+
"git_commit": null
|
| 299 |
+
},
|
| 300 |
+
"training": {
|
| 301 |
+
"steps": 4000,
|
| 302 |
+
"batch_size": 512,
|
| 303 |
+
"lr": 0.0001,
|
| 304 |
+
"betas": [
|
| 305 |
+
0.95,
|
| 306 |
+
0.999
|
| 307 |
+
],
|
| 308 |
+
"weight_decay": 1e-06,
|
| 309 |
+
"warmup": 500,
|
| 310 |
+
"schedule": "linear warm-up + cosine",
|
| 311 |
+
"backbone_lr_scale": 0.1,
|
| 312 |
+
"ema": 0.9999,
|
| 313 |
+
"shift_px": 0,
|
| 314 |
+
"amp": true,
|
| 315 |
+
"seed": 0,
|
| 316 |
+
"augmentation": {
|
| 317 |
+
"spec": "docs/augmentation_v2.md",
|
| 318 |
+
"version": "hb-aug-v2-20261109",
|
| 319 |
+
"implementation": "evaluation/augmentation/hb_aug_v2.py",
|
| 320 |
+
"visual": {
|
| 321 |
+
"effects": [
|
| 322 |
+
"exposure",
|
| 323 |
+
"contrast",
|
| 324 |
+
"saturation",
|
| 325 |
+
"hue",
|
| 326 |
+
"gamma",
|
| 327 |
+
"temperature",
|
| 328 |
+
"rotation_crop",
|
| 329 |
+
"noise",
|
| 330 |
+
"gaussian_blur",
|
| 331 |
+
"jpeg",
|
| 332 |
+
"motion_blur",
|
| 333 |
+
"sharpen",
|
| 334 |
+
"defocus",
|
| 335 |
+
"light_shadow",
|
| 336 |
+
"wb_channel"
|
| 337 |
+
],
|
| 338 |
+
"boosted_per_sample": 1,
|
| 339 |
+
"boost": 1.5,
|
| 340 |
+
"pixel_scale": "H / 224",
|
| 341 |
+
"future_targets": "none (one observation frame)"
|
| 342 |
+
},
|
| 343 |
+
"proprio": {
|
| 344 |
+
"robot": "g1",
|
| 345 |
+
"body_dims": 29,
|
| 346 |
+
"bias_deg": 2.0,
|
| 347 |
+
"bias_scope": "per_sample",
|
| 348 |
+
"noise_deg": 0.25,
|
| 349 |
+
"noise_clip_sigma": 3,
|
| 350 |
+
"delay_probability": 0.0,
|
| 351 |
+
"history_drop_probability": 0.0,
|
| 352 |
+
"velocity": false
|
| 353 |
+
},
|
| 354 |
+
"native_image_augmentation": "off",
|
| 355 |
+
"evaluation": "off"
|
| 356 |
+
},
|
| 357 |
+
"preflight": {
|
| 358 |
+
"samples": 64,
|
| 359 |
+
"state_dim": 44,
|
| 360 |
+
"body_dims": 29,
|
| 361 |
+
"images_changed": 64,
|
| 362 |
+
"body_values_moved": 1.0,
|
| 363 |
+
"max_body_offset_deg": 2.5382,
|
| 364 |
+
"actions_bit_identical": true,
|
| 365 |
+
"non_body_state_bit_identical": true,
|
| 366 |
+
"eval_items_deterministic": 8
|
| 367 |
+
}
|
| 368 |
+
},
|
| 369 |
+
"stats": {
|
| 370 |
+
"state": {
|
| 371 |
+
"min": [
|
| 372 |
+
-0.6335107088088989,
|
| 373 |
+
-0.26151371002197266,
|
| 374 |
+
-0.09143047779798508,
|
| 375 |
+
0.13051827251911163,
|
| 376 |
+
-0.41364213824272156,
|
| 377 |
+
-0.17374181747436523,
|
| 378 |
+
-0.5706103444099426,
|
| 379 |
+
-0.4567093253135681,
|
| 380 |
+
-0.5945078730583191,
|
| 381 |
+
0.07693764567375183,
|
| 382 |
+
-0.479587197303772,
|
| 383 |
+
-0.23942920565605164,
|
| 384 |
+
-0.1249256581068039,
|
| 385 |
+
-0.061801809817552567,
|
| 386 |
+
0.03293042629957199,
|
| 387 |
+
-0.15965673327445984,
|
| 388 |
+
0.12444422394037247,
|
| 389 |
+
-1.0301204919815063,
|
| 390 |
+
0.8110364079475403,
|
| 391 |
+
-0.42373916506767273,
|
| 392 |
+
-0.2393926978111267,
|
| 393 |
+
-0.1671462506055832,
|
| 394 |
+
-1.8559280633926392,
|
| 395 |
+
-2.1003689765930176,
|
| 396 |
+
-0.44611114263534546,
|
| 397 |
+
-0.86998051404953,
|
| 398 |
+
-1.5242679119110107,
|
| 399 |
+
-0.9486506581306458,
|
| 400 |
+
-0.4465007185935974,
|
| 401 |
+
0.9997791647911072,
|
| 402 |
+
0.9987788796424866,
|
| 403 |
+
0.9989608526229858,
|
| 404 |
+
0.9997321963310242,
|
| 405 |
+
0.8891316056251526,
|
| 406 |
+
0.9935978651046753,
|
| 407 |
+
0.3987571895122528,
|
| 408 |
+
0.39748135209083557,
|
| 409 |
+
0.3998531103134155,
|
| 410 |
+
0.47865480184555054,
|
| 411 |
+
0.43634313344955444,
|
| 412 |
+
0.0,
|
| 413 |
+
-0.1312161237001419,
|
| 414 |
+
-0.10554340481758118,
|
| 415 |
+
-1.0
|
| 416 |
+
],
|
| 417 |
+
"max": [
|
| 418 |
+
0.18651676177978516,
|
| 419 |
+
0.2880381643772125,
|
| 420 |
+
0.3991033434867859,
|
| 421 |
+
1.1868021488189697,
|
| 422 |
+
0.30963531136512756,
|
| 423 |
+
0.25351187586784363,
|
| 424 |
+
0.13313187658786774,
|
| 425 |
+
0.14919418096542358,
|
| 426 |
+
0.09004810452461243,
|
| 427 |
+
1.1367807388305664,
|
| 428 |
+
0.47997909784317017,
|
| 429 |
+
0.1897573471069336,
|
| 430 |
+
0.12687286734580994,
|
| 431 |
+
0.0903186947107315,
|
| 432 |
+
0.2110750675201416,
|
| 433 |
+
0.1764557808637619,
|
| 434 |
+
0.3972950279712677,
|
| 435 |
+
-0.03375900536775589,
|
| 436 |
+
1.248238205909729,
|
| 437 |
+
0.5087170004844666,
|
| 438 |
+
0.16197925806045532,
|
| 439 |
+
0.19902198016643524,
|
| 440 |
+
0.7476708292961121,
|
| 441 |
+
-0.14924407005310059,
|
| 442 |
+
1.3937729597091675,
|
| 443 |
+
1.4777758121490479,
|
| 444 |
+
1.449870228767395,
|
| 445 |
+
0.9068933725357056,
|
| 446 |
+
1.5030572414398193,
|
| 447 |
+
1.0,
|
| 448 |
+
1.0,
|
| 449 |
+
1.0,
|
| 450 |
+
1.0,
|
| 451 |
+
1.0,
|
| 452 |
+
1.0,
|
| 453 |
+
1.0,
|
| 454 |
+
1.0,
|
| 455 |
+
1.0,
|
| 456 |
+
1.0,
|
| 457 |
+
1.0,
|
| 458 |
+
1.0,
|
| 459 |
+
0.1443370282649994,
|
| 460 |
+
0.07133471965789795,
|
| 461 |
+
-0.9889927506446838
|
| 462 |
+
],
|
| 463 |
+
"mean": [
|
| 464 |
+
-0.1197492680031697,
|
| 465 |
+
0.07687621598947185,
|
| 466 |
+
0.13623676943730387,
|
| 467 |
+
0.27067508540983654,
|
| 468 |
+
-0.09364010490166123,
|
| 469 |
+
-0.029264338937400346,
|
| 470 |
+
-0.0877177892591824,
|
| 471 |
+
-0.09172362643767557,
|
| 472 |
+
-0.21603681153788365,
|
| 473 |
+
0.27020221177162185,
|
| 474 |
+
-0.13314246080400155,
|
| 475 |
+
0.01521604484593622,
|
| 476 |
+
-0.007014541196278249,
|
| 477 |
+
0.023597627586334522,
|
| 478 |
+
0.1362211304918607,
|
| 479 |
+
0.0044590163081436405,
|
| 480 |
+
0.24020097902181153,
|
| 481 |
+
-0.5506130059849405,
|
| 482 |
+
0.986759154493458,
|
| 483 |
+
-0.11353825983460156,
|
| 484 |
+
-0.09008970046721287,
|
| 485 |
+
0.00793797976488734,
|
| 486 |
+
-0.7956446111257796,
|
| 487 |
+
-0.6433268364566035,
|
| 488 |
+
0.35943391980855405,
|
| 489 |
+
0.4128302732079997,
|
| 490 |
+
-0.6341984046200151,
|
| 491 |
+
0.17366417734106818,
|
| 492 |
+
0.31817584543570415,
|
| 493 |
+
0.9999920738393157,
|
| 494 |
+
0.9999916277741105,
|
| 495 |
+
0.9999916507452171,
|
| 496 |
+
0.9999910946907014,
|
| 497 |
+
0.9975380262153739,
|
| 498 |
+
0.9997842168412904,
|
| 499 |
+
0.7431049855982732,
|
| 500 |
+
0.743061001937713,
|
| 501 |
+
0.7431612987122399,
|
| 502 |
+
0.7812160503121215,
|
| 503 |
+
0.7544858488771042,
|
| 504 |
+
0.1884228588481359,
|
| 505 |
+
-0.018600662889153487,
|
| 506 |
+
-0.001923185563505277,
|
| 507 |
+
-0.9992875029526394
|
| 508 |
+
],
|
| 509 |
+
"std": [
|
| 510 |
+
0.1225902736805545,
|
| 511 |
+
0.0667315519538753,
|
| 512 |
+
0.06966628355722553,
|
| 513 |
+
0.1683343132651939,
|
| 514 |
+
0.11676670853146011,
|
| 515 |
+
0.06393707008498987,
|
| 516 |
+
0.14262675997248406,
|
| 517 |
+
0.07183651035230894,
|
| 518 |
+
0.07077858012951907,
|
| 519 |
+
0.1583747884788023,
|
| 520 |
+
0.09609718753190293,
|
| 521 |
+
0.06937572380392895,
|
| 522 |
+
0.038858334068535276,
|
| 523 |
+
0.01853271444550659,
|
| 524 |
+
0.019156535689633315,
|
| 525 |
+
0.04755913941308977,
|
| 526 |
+
0.041089601727671066,
|
| 527 |
+
0.14354888870689778,
|
| 528 |
+
0.053966848435702465,
|
| 529 |
+
0.13684428975351073,
|
| 530 |
+
0.05453949581291963,
|
| 531 |
+
0.06076597347825228,
|
| 532 |
+
0.6370602259123855,
|
| 533 |
+
0.4013113120474627,
|
| 534 |
+
0.24111485368872668,
|
| 535 |
+
0.5381053688248473,
|
| 536 |
+
0.48085827035516315,
|
| 537 |
+
0.1527991524681821,
|
| 538 |
+
0.44871163018722837,
|
| 539 |
+
1.2824078270394207e-05,
|
| 540 |
+
2.1003630589963823e-05,
|
| 541 |
+
1.8574155779181667e-05,
|
| 542 |
+
1.5382720229173254e-05,
|
| 543 |
+
0.0031309164055460465,
|
| 544 |
+
0.0001241612656891375,
|
| 545 |
+
0.2938442161025196,
|
| 546 |
+
0.29381668166139846,
|
| 547 |
+
0.29367033348300187,
|
| 548 |
+
0.25040401472179635,
|
| 549 |
+
0.2708879748387615,
|
| 550 |
+
0.3732468841625382,
|
| 551 |
+
0.027734659598288042,
|
| 552 |
+
0.01745881392269428,
|
| 553 |
+
0.0008838855519788744
|
| 554 |
+
]
|
| 555 |
+
},
|
| 556 |
+
"action": {
|
| 557 |
+
"min": [
|
| 558 |
+
-0.125,
|
| 559 |
+
-0.5,
|
| 560 |
+
-0.375,
|
| 561 |
+
-0.375,
|
| 562 |
+
-0.625,
|
| 563 |
+
-0.5625,
|
| 564 |
+
-0.4375,
|
| 565 |
+
-0.25,
|
| 566 |
+
-0.375,
|
| 567 |
+
-0.1875,
|
| 568 |
+
-0.625,
|
| 569 |
+
-0.25,
|
| 570 |
+
-0.25,
|
| 571 |
+
-0.375,
|
| 572 |
+
-0.3125,
|
| 573 |
+
-0.5,
|
| 574 |
+
-0.1875,
|
| 575 |
+
-0.25,
|
| 576 |
+
-0.5,
|
| 577 |
+
-0.375,
|
| 578 |
+
-0.4375,
|
| 579 |
+
-0.5,
|
| 580 |
+
-0.3125,
|
| 581 |
+
-0.5,
|
| 582 |
+
-0.5,
|
| 583 |
+
0.0,
|
| 584 |
+
-0.4375,
|
| 585 |
+
-0.5,
|
| 586 |
+
-0.5,
|
| 587 |
+
-0.375,
|
| 588 |
+
-0.0625,
|
| 589 |
+
-0.125,
|
| 590 |
+
-0.375,
|
| 591 |
+
-0.1875,
|
| 592 |
+
0.0625,
|
| 593 |
+
-0.6875,
|
| 594 |
+
-0.1875,
|
| 595 |
+
-0.5,
|
| 596 |
+
-0.375,
|
| 597 |
+
-0.3125,
|
| 598 |
+
-0.4375,
|
| 599 |
+
-0.5625,
|
| 600 |
+
-0.375,
|
| 601 |
+
-0.125,
|
| 602 |
+
-0.5625,
|
| 603 |
+
-0.4375,
|
| 604 |
+
-0.375,
|
| 605 |
+
-0.25,
|
| 606 |
+
-0.1875,
|
| 607 |
+
-0.5625,
|
| 608 |
+
-0.375,
|
| 609 |
+
-0.1875,
|
| 610 |
+
-0.5,
|
| 611 |
+
-0.5625,
|
| 612 |
+
-0.3125,
|
| 613 |
+
-0.3125,
|
| 614 |
+
-0.5,
|
| 615 |
+
-0.125,
|
| 616 |
+
-0.625,
|
| 617 |
+
-0.3125,
|
| 618 |
+
-0.5625,
|
| 619 |
+
-0.1875,
|
| 620 |
+
-0.3125,
|
| 621 |
+
-0.125,
|
| 622 |
+
0.9997791647911072,
|
| 623 |
+
0.9987788796424866,
|
| 624 |
+
0.9989608526229858,
|
| 625 |
+
0.9997321963310242,
|
| 626 |
+
0.8891316056251526,
|
| 627 |
+
0.9935978651046753,
|
| 628 |
+
0.3987571895122528,
|
| 629 |
+
0.39748135209083557,
|
| 630 |
+
0.3998531103134155,
|
| 631 |
+
0.47865480184555054,
|
| 632 |
+
0.43634313344955444,
|
| 633 |
+
0.0
|
| 634 |
+
],
|
| 635 |
+
"max": [
|
| 636 |
+
0.5625,
|
| 637 |
+
0.375,
|
| 638 |
+
0.375,
|
| 639 |
+
0.4375,
|
| 640 |
+
0.25,
|
| 641 |
+
0.25,
|
| 642 |
+
0.1875,
|
| 643 |
+
0.25,
|
| 644 |
+
0.3125,
|
| 645 |
+
0.1875,
|
| 646 |
+
0.125,
|
| 647 |
+
0.375,
|
| 648 |
+
0.5,
|
| 649 |
+
0.25,
|
| 650 |
+
0.3125,
|
| 651 |
+
0.25,
|
| 652 |
+
0.375,
|
| 653 |
+
0.5625,
|
| 654 |
+
0.1875,
|
| 655 |
+
0.25,
|
| 656 |
+
0.25,
|
| 657 |
+
0.1875,
|
| 658 |
+
0.5,
|
| 659 |
+
0.3125,
|
| 660 |
+
0.0625,
|
| 661 |
+
0.5,
|
| 662 |
+
0.0,
|
| 663 |
+
0.1875,
|
| 664 |
+
0.3125,
|
| 665 |
+
0.375,
|
| 666 |
+
0.6875,
|
| 667 |
+
0.5,
|
| 668 |
+
0.25,
|
| 669 |
+
0.5,
|
| 670 |
+
0.375,
|
| 671 |
+
0.125,
|
| 672 |
+
0.6875,
|
| 673 |
+
0.1875,
|
| 674 |
+
0.375,
|
| 675 |
+
0.25,
|
| 676 |
+
0.125,
|
| 677 |
+
0.375,
|
| 678 |
+
0.1875,
|
| 679 |
+
0.5,
|
| 680 |
+
0.3125,
|
| 681 |
+
0.5,
|
| 682 |
+
0.5,
|
| 683 |
+
0.4375,
|
| 684 |
+
0.5,
|
| 685 |
+
0.1875,
|
| 686 |
+
0.5,
|
| 687 |
+
0.3125,
|
| 688 |
+
0.625,
|
| 689 |
+
0.125,
|
| 690 |
+
0.25,
|
| 691 |
+
0.5625,
|
| 692 |
+
0.5,
|
| 693 |
+
0.3125,
|
| 694 |
+
0.125,
|
| 695 |
+
0.1875,
|
| 696 |
+
0.25,
|
| 697 |
+
0.625,
|
| 698 |
+
0.4375,
|
| 699 |
+
0.6875,
|
| 700 |
+
1.0,
|
| 701 |
+
1.0,
|
| 702 |
+
1.0,
|
| 703 |
+
1.0,
|
| 704 |
+
1.0,
|
| 705 |
+
1.0,
|
| 706 |
+
1.0,
|
| 707 |
+
1.0,
|
| 708 |
+
1.0,
|
| 709 |
+
1.0,
|
| 710 |
+
1.0,
|
| 711 |
+
1.0
|
| 712 |
+
],
|
| 713 |
+
"mean": [
|
| 714 |
+
0.28530257380633073,
|
| 715 |
+
0.0012216853746808002,
|
| 716 |
+
0.02519611265225139,
|
| 717 |
+
0.0920742013117043,
|
| 718 |
+
-0.18735762313302592,
|
| 719 |
+
-0.18916948358532507,
|
| 720 |
+
-0.10082578582844966,
|
| 721 |
+
-0.04547218599011629,
|
| 722 |
+
0.009826300222291624,
|
| 723 |
+
-0.09046442415446512,
|
| 724 |
+
-0.3906258611504051,
|
| 725 |
+
0.07456643947605313,
|
| 726 |
+
0.06761982620836625,
|
| 727 |
+
0.016528346774934324,
|
| 728 |
+
0.02783008469127184,
|
| 729 |
+
-0.15926115591644774,
|
| 730 |
+
0.137793250417945,
|
| 731 |
+
0.13872558925651718,
|
| 732 |
+
-0.17794123050355484,
|
| 733 |
+
-0.04058314809031286,
|
| 734 |
+
-0.1081088218543898,
|
| 735 |
+
-0.27256788161593154,
|
| 736 |
+
0.0295489408998218,
|
| 737 |
+
-0.12704953796410265,
|
| 738 |
+
-0.2065647217680451,
|
| 739 |
+
0.257109657744383,
|
| 740 |
+
-0.2610296143883306,
|
| 741 |
+
-0.11359147943343192,
|
| 742 |
+
-0.08978239303363768,
|
| 743 |
+
0.042958775007807766,
|
| 744 |
+
0.3583063123472893,
|
| 745 |
+
0.2295861425973215,
|
| 746 |
+
0.005530882001726894,
|
| 747 |
+
0.18030882001726894,
|
| 748 |
+
0.22869399077765326,
|
| 749 |
+
-0.3416688865210442,
|
| 750 |
+
0.16757757242849006,
|
| 751 |
+
-0.24212104789374092,
|
| 752 |
+
-0.08830580713905167,
|
| 753 |
+
0.03962554883985817,
|
| 754 |
+
-0.24867382837616886,
|
| 755 |
+
-0.16334300883655137,
|
| 756 |
+
-0.10593298183087466,
|
| 757 |
+
0.29390833685448164,
|
| 758 |
+
-0.17902857641504236,
|
| 759 |
+
-0.02676455459004648,
|
| 760 |
+
-0.010649560009553029,
|
| 761 |
+
0.006596412102952253,
|
| 762 |
+
0.19015693604982273,
|
| 763 |
+
-0.28608220197306783,
|
| 764 |
+
0.0342829717267099,
|
| 765 |
+
0.05214208292763581,
|
| 766 |
+
0.2372308617933974,
|
| 767 |
+
-0.27289282236878365,
|
| 768 |
+
-0.07418638509727556,
|
| 769 |
+
0.21441496886080136,
|
| 770 |
+
-0.07936362133264747,
|
| 771 |
+
0.07053166277809417,
|
| 772 |
+
-0.2592969797732993,
|
| 773 |
+
-0.04738279168886521,
|
| 774 |
+
-0.25777561405764887,
|
| 775 |
+
0.3476016387118108,
|
| 776 |
+
0.0341980048867415,
|
| 777 |
+
0.4095493542520162,
|
| 778 |
+
0.9999920738393157,
|
| 779 |
+
0.9999916277741105,
|
| 780 |
+
0.9999916507452171,
|
| 781 |
+
0.9999910946907014,
|
| 782 |
+
0.9975380262153739,
|
| 783 |
+
0.9997842168412904,
|
| 784 |
+
0.7431049855982732,
|
| 785 |
+
0.743061001937713,
|
| 786 |
+
0.7431612987122399,
|
| 787 |
+
0.7812160503121215,
|
| 788 |
+
0.7544858488771042,
|
| 789 |
+
0.1884228588481359
|
| 790 |
+
],
|
| 791 |
+
"std": [
|
| 792 |
+
0.13976769962393334,
|
| 793 |
+
0.2042750041966315,
|
| 794 |
+
0.11249063031363368,
|
| 795 |
+
0.11082072512754977,
|
| 796 |
+
0.1564752219884858,
|
| 797 |
+
0.17244514813212275,
|
| 798 |
+
0.10524673666978752,
|
| 799 |
+
0.09606056085676273,
|
| 800 |
+
0.16248529891535804,
|
| 801 |
+
0.06517700714473815,
|
| 802 |
+
0.12267993314050843,
|
| 803 |
+
0.09188274452085451,
|
| 804 |
+
0.1817845505649146,
|
| 805 |
+
0.13895894808224718,
|
| 806 |
+
0.09471602567899642,
|
| 807 |
+
0.143892040083983,
|
| 808 |
+
0.13123846053152619,
|
| 809 |
+
0.17169478968550717,
|
| 810 |
+
0.099377781857111,
|
| 811 |
+
0.12335366669054255,
|
| 812 |
+
0.09243992450340514,
|
| 813 |
+
0.12474594719512408,
|
| 814 |
+
0.1211368699762344,
|
| 815 |
+
0.17473771543792177,
|
| 816 |
+
0.12139112019256279,
|
| 817 |
+
0.08058301151688785,
|
| 818 |
+
0.08181288643740524,
|
| 819 |
+
0.12245444611527911,
|
| 820 |
+
0.15642136427791328,
|
| 821 |
+
0.16023434329274994,
|
| 822 |
+
0.1749952692685118,
|
| 823 |
+
0.10352440920325795,
|
| 824 |
+
0.07368975064774456,
|
| 825 |
+
0.13144910448634894,
|
| 826 |
+
0.04419890783153379,
|
| 827 |
+
0.18157602689607938,
|
| 828 |
+
0.15703202636240324,
|
| 829 |
+
0.1308473547559705,
|
| 830 |
+
0.10877569321547828,
|
| 831 |
+
0.06509046280547963,
|
| 832 |
+
0.08347560937172435,
|
| 833 |
+
0.19809736217235097,
|
| 834 |
+
0.06719381956707862,
|
| 835 |
+
0.09127596366580104,
|
| 836 |
+
0.13233099033714146,
|
| 837 |
+
0.25952623468134783,
|
| 838 |
+
0.21598709847307782,
|
| 839 |
+
0.10931842674892184,
|
| 840 |
+
0.11294459446909082,
|
| 841 |
+
0.1403015515249487,
|
| 842 |
+
0.10231818070157317,
|
| 843 |
+
0.10139944441893624,
|
| 844 |
+
0.288021039372521,
|
| 845 |
+
0.11780041132456433,
|
| 846 |
+
0.11650297357712408,
|
| 847 |
+
0.21262101617713844,
|
| 848 |
+
0.28703233994958033,
|
| 849 |
+
0.09814627765272926,
|
| 850 |
+
0.21616444128412057,
|
| 851 |
+
0.06262758949048293,
|
| 852 |
+
0.1745534315389492,
|
| 853 |
+
0.17455467068976818,
|
| 854 |
+
0.10468632106020986,
|
| 855 |
+
0.18477106893909007,
|
| 856 |
+
1.2824078270394207e-05,
|
| 857 |
+
2.1003630589963823e-05,
|
| 858 |
+
1.8574155779181667e-05,
|
| 859 |
+
1.5382720229173254e-05,
|
| 860 |
+
0.0031309164055460465,
|
| 861 |
+
0.0001241612656891375,
|
| 862 |
+
0.2938442161025196,
|
| 863 |
+
0.29381668166139846,
|
| 864 |
+
0.29367033348300187,
|
| 865 |
+
0.25040401472179635,
|
| 866 |
+
0.2708879748387615,
|
| 867 |
+
0.3732468841625382
|
| 868 |
+
]
|
| 869 |
+
}
|
| 870 |
+
},
|
| 871 |
+
"code_commit": "028df1bb7024fb1e3d176de7e60c84d3333cd97f",
|
| 872 |
+
"step": 4000,
|
| 873 |
+
"weights": "ema",
|
| 874 |
+
"offline_eval": {
|
| 875 |
+
"mse": 0.005647905636578798,
|
| 876 |
+
"mse_row0": 0.003931598272174597,
|
| 877 |
+
"mse_motion_token": 0.0046808067709207535,
|
| 878 |
+
"mse_inspire_left_hand_state": 0.0018608566606417298,
|
| 879 |
+
"mse_inspire_right_hand_state": 0.01975069008767605,
|
| 880 |
+
"samples": 256,
|
| 881 |
+
"frames": "train"
|
| 882 |
+
},
|
| 883 |
+
"format": "hb_baselines/1"
|
| 884 |
+
}
|
a20-basket-transfer/b512-trimv2/step-004000/model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42235f4f164febb7136fafcd899c7fa2ac4a558fab9615a0565de74acf8b856c
|
| 3 |
+
size 336137451
|
a20-basket-transfer/b512-trimv2/step-004000/protocol.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"format": "hb_baselines/1",
|
| 3 |
+
"step": 4000,
|
| 4 |
+
"policy": "act",
|
| 5 |
+
"files": {
|
| 6 |
+
"model.pt": {
|
| 7 |
+
"bytes": 336137451,
|
| 8 |
+
"sha256": "42235f4f164febb7136fafcd899c7fa2ac4a558fab9615a0565de74acf8b856c"
|
| 9 |
+
}
|
| 10 |
+
}
|
| 11 |
+
}
|
code/hb_baselines_v1/baselines/__init__.py
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""FM-DiT, DP (Diffusion Policy, DDPM-DiT) and ACT visuomotor baselines of the Humanoid Benchmark.
|
| 2 |
+
|
| 3 |
+
Ported from DextraVerse's imitation-learning core (`dextraverse/algorithms/il/models/{fm_dit,ddpm_dit,act}.py` and
|
| 4 |
+
their networks), torch only. `train.py` trains one on a task's LeRobot v2.1 expert dataset through a robot contract
|
| 5 |
+
(`data.CONTRACTS`: G1 state44/action76 or H2 state78/action75); `runtime.BaselinePolicy` serves a checkpoint to the
|
| 6 |
+
G1 evaluation adapters (`evaluation/policy/{FMDiT,DP,ACT}/model.py`, via `adapters.py`) and to the H2 adapter
|
| 7 |
+
(`debug/newton/h2_policy_adapters/baseline.py`). Usage and the environment: evaluation/README.md#baselines.
|
| 8 |
+
"""
|
code/hb_baselines_v1/baselines/act_nets.py
ADDED
|
@@ -0,0 +1,615 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""ACT (Zhao et al. 2023, "Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware") network core: the
|
| 2 |
+
ResNet backbone with frozen BatchNorm and sine position embedding, the DETR encoder-decoder transformer and the CVAE
|
| 3 |
+
action-chunk decoder.
|
| 4 |
+
|
| 5 |
+
Ported unchanged from DextraVerse (`dextraverse/algorithms/il/models/nets/act/`), which vendors the ACT repository's
|
| 6 |
+
`detr/models/{backbone,position_encoding,transformer,detr_vae}.py` (Apache-2.0, (c) Facebook, Inc. and its
|
| 7 |
+
affiliates; see THIRD_PARTY_NOTICES.md) with the NestedTensor/argparse plumbing removed, explicit `qpos_dim` /
|
| 8 |
+
`action_dim` instead of the ALOHA 14-DoF constants, and one backbone shared by every camera (upstream behaviour).
|
| 9 |
+
The policy uses `return_intermediate_dec=False`: `Transformer.forward(...)[0]` is the final decoder layer.
|
| 10 |
+
"""
|
| 11 |
+
from __future__ import annotations
|
| 12 |
+
|
| 13 |
+
import copy
|
| 14 |
+
import math
|
| 15 |
+
from typing import Optional
|
| 16 |
+
|
| 17 |
+
import numpy as np
|
| 18 |
+
import torch
|
| 19 |
+
import torch.nn.functional as F
|
| 20 |
+
import torchvision
|
| 21 |
+
from torch import Tensor, nn
|
| 22 |
+
from torchvision.models._utils import IntermediateLayerGetter
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
class PositionEmbeddingSine(nn.Module):
|
| 26 |
+
"""Standard DETR sine embedding over a ``(B, C, H, W)`` feature map."""
|
| 27 |
+
|
| 28 |
+
def __init__(
|
| 29 |
+
self, num_pos_feats: int = 64, temperature: int = 10000, normalize: bool = False
|
| 30 |
+
) -> None:
|
| 31 |
+
super().__init__()
|
| 32 |
+
self.num_pos_feats = num_pos_feats
|
| 33 |
+
self.temperature = temperature
|
| 34 |
+
self.normalize = normalize
|
| 35 |
+
self.scale = 2 * math.pi
|
| 36 |
+
|
| 37 |
+
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
| 38 |
+
not_mask = torch.ones((1, x.shape[-2], x.shape[-1]), device=x.device)
|
| 39 |
+
y_embed = not_mask.cumsum(1, dtype=torch.float32)
|
| 40 |
+
x_embed = not_mask.cumsum(2, dtype=torch.float32)
|
| 41 |
+
if self.normalize:
|
| 42 |
+
eps = 1e-6
|
| 43 |
+
y_embed = y_embed / (y_embed[:, -1:, :] + eps) * self.scale
|
| 44 |
+
x_embed = x_embed / (x_embed[:, :, -1:] + eps) * self.scale
|
| 45 |
+
|
| 46 |
+
dim_t = torch.arange(self.num_pos_feats, dtype=torch.float32, device=x.device)
|
| 47 |
+
dim_t = self.temperature ** (2 * (dim_t // 2) / self.num_pos_feats)
|
| 48 |
+
|
| 49 |
+
pos_x = x_embed[:, :, :, None] / dim_t
|
| 50 |
+
pos_y = y_embed[:, :, :, None] / dim_t
|
| 51 |
+
pos_x = torch.stack(
|
| 52 |
+
(pos_x[:, :, :, 0::2].sin(), pos_x[:, :, :, 1::2].cos()), dim=4
|
| 53 |
+
).flatten(3)
|
| 54 |
+
pos_y = torch.stack(
|
| 55 |
+
(pos_y[:, :, :, 0::2].sin(), pos_y[:, :, :, 1::2].cos()), dim=4
|
| 56 |
+
).flatten(3)
|
| 57 |
+
return torch.cat((pos_y, pos_x), dim=3).permute(0, 3, 1, 2)
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
class FrozenBatchNorm2d(nn.Module):
|
| 61 |
+
"""BatchNorm2d with fixed statistics and affine parameters (the DETR/ACT backbone norm)."""
|
| 62 |
+
|
| 63 |
+
def __init__(self, n: int) -> None:
|
| 64 |
+
super().__init__()
|
| 65 |
+
self.register_buffer("weight", torch.ones(n))
|
| 66 |
+
self.register_buffer("bias", torch.zeros(n))
|
| 67 |
+
self.register_buffer("running_mean", torch.zeros(n))
|
| 68 |
+
self.register_buffer("running_var", torch.ones(n))
|
| 69 |
+
|
| 70 |
+
def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict, *args):
|
| 71 |
+
state_dict.pop(prefix + "num_batches_tracked", None)
|
| 72 |
+
super()._load_from_state_dict(state_dict, prefix, local_metadata, strict, *args)
|
| 73 |
+
|
| 74 |
+
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
| 75 |
+
w = self.weight.reshape(1, -1, 1, 1)
|
| 76 |
+
b = self.bias.reshape(1, -1, 1, 1)
|
| 77 |
+
rv = self.running_var.reshape(1, -1, 1, 1)
|
| 78 |
+
rm = self.running_mean.reshape(1, -1, 1, 1)
|
| 79 |
+
scale = w * (rv + 1e-5).rsqrt()
|
| 80 |
+
return x * scale + (b - rm * scale)
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
class Backbone(nn.Module):
|
| 84 |
+
"""ResNet trunk returning the layer4 feature map."""
|
| 85 |
+
|
| 86 |
+
def __init__(self, name: str = "resnet18", weights: str | None = None) -> None:
|
| 87 |
+
super().__init__()
|
| 88 |
+
trunk = getattr(torchvision.models, name)(
|
| 89 |
+
replace_stride_with_dilation=[False, False, False],
|
| 90 |
+
weights=weights,
|
| 91 |
+
norm_layer=FrozenBatchNorm2d,
|
| 92 |
+
)
|
| 93 |
+
self.body = IntermediateLayerGetter(trunk, return_layers={"layer4": "0"})
|
| 94 |
+
self.num_channels = 512 if name in ("resnet18", "resnet34") else 2048
|
| 95 |
+
|
| 96 |
+
def forward(self, x: torch.Tensor) -> dict[str, torch.Tensor]:
|
| 97 |
+
return self.body(x)
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
class Joiner(nn.Sequential):
|
| 101 |
+
"""Backbone + position embedding, returning matched feature/position lists."""
|
| 102 |
+
|
| 103 |
+
def __init__(self, backbone: Backbone, position_embedding: PositionEmbeddingSine) -> None:
|
| 104 |
+
super().__init__(backbone, position_embedding)
|
| 105 |
+
self.num_channels = backbone.num_channels
|
| 106 |
+
|
| 107 |
+
def forward(self, x: torch.Tensor) -> tuple[list[torch.Tensor], list[torch.Tensor]]:
|
| 108 |
+
features = list(self[0](x).values())
|
| 109 |
+
pos = [self[1](f).to(f.dtype) for f in features]
|
| 110 |
+
return features, pos
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
def build_backbone(
|
| 114 |
+
name: str = "resnet18", hidden_dim: int = 512, weights: str | None = None
|
| 115 |
+
) -> Joiner:
|
| 116 |
+
"""The ACT camera backbone: ResNet + sine embedding sized to the transformer width."""
|
| 117 |
+
return Joiner(Backbone(name, weights=weights), PositionEmbeddingSine(hidden_dim // 2))
|
| 118 |
+
|
| 119 |
+
|
| 120 |
+
class Transformer(nn.Module):
|
| 121 |
+
def __init__(
|
| 122 |
+
self,
|
| 123 |
+
d_model=512,
|
| 124 |
+
nhead=8,
|
| 125 |
+
num_encoder_layers=6,
|
| 126 |
+
num_decoder_layers=6,
|
| 127 |
+
dim_feedforward=2048,
|
| 128 |
+
dropout=0.1,
|
| 129 |
+
activation="relu",
|
| 130 |
+
normalize_before=False,
|
| 131 |
+
return_intermediate_dec=False,
|
| 132 |
+
):
|
| 133 |
+
super().__init__()
|
| 134 |
+
|
| 135 |
+
encoder_layer = TransformerEncoderLayer(
|
| 136 |
+
d_model, nhead, dim_feedforward, dropout, activation, normalize_before
|
| 137 |
+
)
|
| 138 |
+
encoder_norm = nn.LayerNorm(d_model) if normalize_before else None
|
| 139 |
+
self.encoder = TransformerEncoder(encoder_layer, num_encoder_layers, encoder_norm)
|
| 140 |
+
|
| 141 |
+
decoder_layer = TransformerDecoderLayer(
|
| 142 |
+
d_model, nhead, dim_feedforward, dropout, activation, normalize_before
|
| 143 |
+
)
|
| 144 |
+
decoder_norm = nn.LayerNorm(d_model)
|
| 145 |
+
self.decoder = TransformerDecoder(
|
| 146 |
+
decoder_layer,
|
| 147 |
+
num_decoder_layers,
|
| 148 |
+
decoder_norm,
|
| 149 |
+
return_intermediate=return_intermediate_dec,
|
| 150 |
+
)
|
| 151 |
+
|
| 152 |
+
self._reset_parameters()
|
| 153 |
+
|
| 154 |
+
self.d_model = d_model
|
| 155 |
+
self.nhead = nhead
|
| 156 |
+
|
| 157 |
+
def _reset_parameters(self):
|
| 158 |
+
for p in self.parameters():
|
| 159 |
+
if p.dim() > 1:
|
| 160 |
+
nn.init.xavier_uniform_(p)
|
| 161 |
+
|
| 162 |
+
def forward(
|
| 163 |
+
self,
|
| 164 |
+
src,
|
| 165 |
+
mask,
|
| 166 |
+
query_embed,
|
| 167 |
+
pos_embed,
|
| 168 |
+
latent_input=None,
|
| 169 |
+
proprio_input=None,
|
| 170 |
+
additional_pos_embed=None,
|
| 171 |
+
):
|
| 172 |
+
# TODO flatten only when input has H and W
|
| 173 |
+
if len(src.shape) == 4: # has H and W
|
| 174 |
+
# flatten NxCxHxW to HWxNxC
|
| 175 |
+
bs, c, h, w = src.shape
|
| 176 |
+
src = src.flatten(2).permute(2, 0, 1)
|
| 177 |
+
pos_embed = pos_embed.flatten(2).permute(2, 0, 1).repeat(1, bs, 1)
|
| 178 |
+
query_embed = query_embed.unsqueeze(1).repeat(1, bs, 1)
|
| 179 |
+
# mask = mask.flatten(1)
|
| 180 |
+
|
| 181 |
+
additional_pos_embed = additional_pos_embed.unsqueeze(1).repeat(
|
| 182 |
+
1, bs, 1
|
| 183 |
+
) # seq, bs, dim
|
| 184 |
+
pos_embed = torch.cat([additional_pos_embed, pos_embed], axis=0)
|
| 185 |
+
|
| 186 |
+
addition_input = torch.stack([latent_input, proprio_input], axis=0)
|
| 187 |
+
src = torch.cat([addition_input, src], axis=0)
|
| 188 |
+
else:
|
| 189 |
+
assert len(src.shape) == 3
|
| 190 |
+
# flatten NxHWxC to HWxNxC
|
| 191 |
+
bs, hw, c = src.shape
|
| 192 |
+
src = src.permute(1, 0, 2)
|
| 193 |
+
pos_embed = pos_embed.unsqueeze(1).repeat(1, bs, 1)
|
| 194 |
+
query_embed = query_embed.unsqueeze(1).repeat(1, bs, 1)
|
| 195 |
+
|
| 196 |
+
tgt = torch.zeros_like(query_embed)
|
| 197 |
+
memory = self.encoder(src, src_key_padding_mask=mask, pos=pos_embed)
|
| 198 |
+
hs = self.decoder(
|
| 199 |
+
tgt, memory, memory_key_padding_mask=mask, pos=pos_embed, query_pos=query_embed
|
| 200 |
+
)
|
| 201 |
+
hs = hs.transpose(1, 2)
|
| 202 |
+
return hs
|
| 203 |
+
|
| 204 |
+
|
| 205 |
+
class TransformerEncoder(nn.Module):
|
| 206 |
+
def __init__(self, encoder_layer, num_layers, norm=None):
|
| 207 |
+
super().__init__()
|
| 208 |
+
self.layers = _get_clones(encoder_layer, num_layers)
|
| 209 |
+
self.num_layers = num_layers
|
| 210 |
+
self.norm = norm
|
| 211 |
+
|
| 212 |
+
def forward(
|
| 213 |
+
self,
|
| 214 |
+
src,
|
| 215 |
+
mask: Optional[Tensor] = None,
|
| 216 |
+
src_key_padding_mask: Optional[Tensor] = None,
|
| 217 |
+
pos: Optional[Tensor] = None,
|
| 218 |
+
):
|
| 219 |
+
output = src
|
| 220 |
+
|
| 221 |
+
for layer in self.layers:
|
| 222 |
+
output = layer(
|
| 223 |
+
output, src_mask=mask, src_key_padding_mask=src_key_padding_mask, pos=pos
|
| 224 |
+
)
|
| 225 |
+
|
| 226 |
+
if self.norm is not None:
|
| 227 |
+
output = self.norm(output)
|
| 228 |
+
|
| 229 |
+
return output
|
| 230 |
+
|
| 231 |
+
|
| 232 |
+
class TransformerDecoder(nn.Module):
|
| 233 |
+
def __init__(self, decoder_layer, num_layers, norm=None, return_intermediate=False):
|
| 234 |
+
super().__init__()
|
| 235 |
+
self.layers = _get_clones(decoder_layer, num_layers)
|
| 236 |
+
self.num_layers = num_layers
|
| 237 |
+
self.norm = norm
|
| 238 |
+
self.return_intermediate = return_intermediate
|
| 239 |
+
|
| 240 |
+
def forward(
|
| 241 |
+
self,
|
| 242 |
+
tgt,
|
| 243 |
+
memory,
|
| 244 |
+
tgt_mask: Optional[Tensor] = None,
|
| 245 |
+
memory_mask: Optional[Tensor] = None,
|
| 246 |
+
tgt_key_padding_mask: Optional[Tensor] = None,
|
| 247 |
+
memory_key_padding_mask: Optional[Tensor] = None,
|
| 248 |
+
pos: Optional[Tensor] = None,
|
| 249 |
+
query_pos: Optional[Tensor] = None,
|
| 250 |
+
):
|
| 251 |
+
output = tgt
|
| 252 |
+
|
| 253 |
+
intermediate = []
|
| 254 |
+
|
| 255 |
+
for layer in self.layers:
|
| 256 |
+
output = layer(
|
| 257 |
+
output,
|
| 258 |
+
memory,
|
| 259 |
+
tgt_mask=tgt_mask,
|
| 260 |
+
memory_mask=memory_mask,
|
| 261 |
+
tgt_key_padding_mask=tgt_key_padding_mask,
|
| 262 |
+
memory_key_padding_mask=memory_key_padding_mask,
|
| 263 |
+
pos=pos,
|
| 264 |
+
query_pos=query_pos,
|
| 265 |
+
)
|
| 266 |
+
if self.return_intermediate:
|
| 267 |
+
intermediate.append(self.norm(output))
|
| 268 |
+
|
| 269 |
+
if self.norm is not None:
|
| 270 |
+
output = self.norm(output)
|
| 271 |
+
if self.return_intermediate:
|
| 272 |
+
intermediate.pop()
|
| 273 |
+
intermediate.append(output)
|
| 274 |
+
|
| 275 |
+
if self.return_intermediate:
|
| 276 |
+
return torch.stack(intermediate)
|
| 277 |
+
|
| 278 |
+
return output.unsqueeze(0)
|
| 279 |
+
|
| 280 |
+
|
| 281 |
+
class TransformerEncoderLayer(nn.Module):
|
| 282 |
+
def __init__(
|
| 283 |
+
self,
|
| 284 |
+
d_model,
|
| 285 |
+
nhead,
|
| 286 |
+
dim_feedforward=2048,
|
| 287 |
+
dropout=0.1,
|
| 288 |
+
activation="relu",
|
| 289 |
+
normalize_before=False,
|
| 290 |
+
):
|
| 291 |
+
super().__init__()
|
| 292 |
+
self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
|
| 293 |
+
# Implementation of Feedforward model
|
| 294 |
+
self.linear1 = nn.Linear(d_model, dim_feedforward)
|
| 295 |
+
self.dropout = nn.Dropout(dropout)
|
| 296 |
+
self.linear2 = nn.Linear(dim_feedforward, d_model)
|
| 297 |
+
|
| 298 |
+
self.norm1 = nn.LayerNorm(d_model)
|
| 299 |
+
self.norm2 = nn.LayerNorm(d_model)
|
| 300 |
+
self.dropout1 = nn.Dropout(dropout)
|
| 301 |
+
self.dropout2 = nn.Dropout(dropout)
|
| 302 |
+
|
| 303 |
+
self.activation = _get_activation_fn(activation)
|
| 304 |
+
self.normalize_before = normalize_before
|
| 305 |
+
|
| 306 |
+
def with_pos_embed(self, tensor, pos: Optional[Tensor]):
|
| 307 |
+
return tensor if pos is None else tensor + pos
|
| 308 |
+
|
| 309 |
+
def forward_post(
|
| 310 |
+
self,
|
| 311 |
+
src,
|
| 312 |
+
src_mask: Optional[Tensor] = None,
|
| 313 |
+
src_key_padding_mask: Optional[Tensor] = None,
|
| 314 |
+
pos: Optional[Tensor] = None,
|
| 315 |
+
):
|
| 316 |
+
q = k = self.with_pos_embed(src, pos)
|
| 317 |
+
src2 = self.self_attn(
|
| 318 |
+
q, k, value=src, attn_mask=src_mask, key_padding_mask=src_key_padding_mask
|
| 319 |
+
)[0]
|
| 320 |
+
src = src + self.dropout1(src2)
|
| 321 |
+
src = self.norm1(src)
|
| 322 |
+
src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
|
| 323 |
+
src = src + self.dropout2(src2)
|
| 324 |
+
src = self.norm2(src)
|
| 325 |
+
return src
|
| 326 |
+
|
| 327 |
+
def forward_pre(
|
| 328 |
+
self,
|
| 329 |
+
src,
|
| 330 |
+
src_mask: Optional[Tensor] = None,
|
| 331 |
+
src_key_padding_mask: Optional[Tensor] = None,
|
| 332 |
+
pos: Optional[Tensor] = None,
|
| 333 |
+
):
|
| 334 |
+
src2 = self.norm1(src)
|
| 335 |
+
q = k = self.with_pos_embed(src2, pos)
|
| 336 |
+
src2 = self.self_attn(
|
| 337 |
+
q, k, value=src2, attn_mask=src_mask, key_padding_mask=src_key_padding_mask
|
| 338 |
+
)[0]
|
| 339 |
+
src = src + self.dropout1(src2)
|
| 340 |
+
src2 = self.norm2(src)
|
| 341 |
+
src2 = self.linear2(self.dropout(self.activation(self.linear1(src2))))
|
| 342 |
+
src = src + self.dropout2(src2)
|
| 343 |
+
return src
|
| 344 |
+
|
| 345 |
+
def forward(
|
| 346 |
+
self,
|
| 347 |
+
src,
|
| 348 |
+
src_mask: Optional[Tensor] = None,
|
| 349 |
+
src_key_padding_mask: Optional[Tensor] = None,
|
| 350 |
+
pos: Optional[Tensor] = None,
|
| 351 |
+
):
|
| 352 |
+
if self.normalize_before:
|
| 353 |
+
return self.forward_pre(src, src_mask, src_key_padding_mask, pos)
|
| 354 |
+
return self.forward_post(src, src_mask, src_key_padding_mask, pos)
|
| 355 |
+
|
| 356 |
+
|
| 357 |
+
class TransformerDecoderLayer(nn.Module):
|
| 358 |
+
def __init__(
|
| 359 |
+
self,
|
| 360 |
+
d_model,
|
| 361 |
+
nhead,
|
| 362 |
+
dim_feedforward=2048,
|
| 363 |
+
dropout=0.1,
|
| 364 |
+
activation="relu",
|
| 365 |
+
normalize_before=False,
|
| 366 |
+
):
|
| 367 |
+
super().__init__()
|
| 368 |
+
self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
|
| 369 |
+
self.multihead_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
|
| 370 |
+
# Implementation of Feedforward model
|
| 371 |
+
self.linear1 = nn.Linear(d_model, dim_feedforward)
|
| 372 |
+
self.dropout = nn.Dropout(dropout)
|
| 373 |
+
self.linear2 = nn.Linear(dim_feedforward, d_model)
|
| 374 |
+
|
| 375 |
+
self.norm1 = nn.LayerNorm(d_model)
|
| 376 |
+
self.norm2 = nn.LayerNorm(d_model)
|
| 377 |
+
self.norm3 = nn.LayerNorm(d_model)
|
| 378 |
+
self.dropout1 = nn.Dropout(dropout)
|
| 379 |
+
self.dropout2 = nn.Dropout(dropout)
|
| 380 |
+
self.dropout3 = nn.Dropout(dropout)
|
| 381 |
+
|
| 382 |
+
self.activation = _get_activation_fn(activation)
|
| 383 |
+
self.normalize_before = normalize_before
|
| 384 |
+
|
| 385 |
+
def with_pos_embed(self, tensor, pos: Optional[Tensor]):
|
| 386 |
+
return tensor if pos is None else tensor + pos
|
| 387 |
+
|
| 388 |
+
def forward_post(
|
| 389 |
+
self,
|
| 390 |
+
tgt,
|
| 391 |
+
memory,
|
| 392 |
+
tgt_mask: Optional[Tensor] = None,
|
| 393 |
+
memory_mask: Optional[Tensor] = None,
|
| 394 |
+
tgt_key_padding_mask: Optional[Tensor] = None,
|
| 395 |
+
memory_key_padding_mask: Optional[Tensor] = None,
|
| 396 |
+
pos: Optional[Tensor] = None,
|
| 397 |
+
query_pos: Optional[Tensor] = None,
|
| 398 |
+
):
|
| 399 |
+
q = k = self.with_pos_embed(tgt, query_pos)
|
| 400 |
+
tgt2 = self.self_attn(
|
| 401 |
+
q, k, value=tgt, attn_mask=tgt_mask, key_padding_mask=tgt_key_padding_mask
|
| 402 |
+
)[0]
|
| 403 |
+
tgt = tgt + self.dropout1(tgt2)
|
| 404 |
+
tgt = self.norm1(tgt)
|
| 405 |
+
tgt2 = self.multihead_attn(
|
| 406 |
+
query=self.with_pos_embed(tgt, query_pos),
|
| 407 |
+
key=self.with_pos_embed(memory, pos),
|
| 408 |
+
value=memory,
|
| 409 |
+
attn_mask=memory_mask,
|
| 410 |
+
key_padding_mask=memory_key_padding_mask,
|
| 411 |
+
)[0]
|
| 412 |
+
tgt = tgt + self.dropout2(tgt2)
|
| 413 |
+
tgt = self.norm2(tgt)
|
| 414 |
+
tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt))))
|
| 415 |
+
tgt = tgt + self.dropout3(tgt2)
|
| 416 |
+
tgt = self.norm3(tgt)
|
| 417 |
+
return tgt
|
| 418 |
+
|
| 419 |
+
def forward_pre(
|
| 420 |
+
self,
|
| 421 |
+
tgt,
|
| 422 |
+
memory,
|
| 423 |
+
tgt_mask: Optional[Tensor] = None,
|
| 424 |
+
memory_mask: Optional[Tensor] = None,
|
| 425 |
+
tgt_key_padding_mask: Optional[Tensor] = None,
|
| 426 |
+
memory_key_padding_mask: Optional[Tensor] = None,
|
| 427 |
+
pos: Optional[Tensor] = None,
|
| 428 |
+
query_pos: Optional[Tensor] = None,
|
| 429 |
+
):
|
| 430 |
+
tgt2 = self.norm1(tgt)
|
| 431 |
+
q = k = self.with_pos_embed(tgt2, query_pos)
|
| 432 |
+
tgt2 = self.self_attn(
|
| 433 |
+
q, k, value=tgt2, attn_mask=tgt_mask, key_padding_mask=tgt_key_padding_mask
|
| 434 |
+
)[0]
|
| 435 |
+
tgt = tgt + self.dropout1(tgt2)
|
| 436 |
+
tgt2 = self.norm2(tgt)
|
| 437 |
+
tgt2 = self.multihead_attn(
|
| 438 |
+
query=self.with_pos_embed(tgt2, query_pos),
|
| 439 |
+
key=self.with_pos_embed(memory, pos),
|
| 440 |
+
value=memory,
|
| 441 |
+
attn_mask=memory_mask,
|
| 442 |
+
key_padding_mask=memory_key_padding_mask,
|
| 443 |
+
)[0]
|
| 444 |
+
tgt = tgt + self.dropout2(tgt2)
|
| 445 |
+
tgt2 = self.norm3(tgt)
|
| 446 |
+
tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt2))))
|
| 447 |
+
tgt = tgt + self.dropout3(tgt2)
|
| 448 |
+
return tgt
|
| 449 |
+
|
| 450 |
+
def forward(
|
| 451 |
+
self,
|
| 452 |
+
tgt,
|
| 453 |
+
memory,
|
| 454 |
+
tgt_mask: Optional[Tensor] = None,
|
| 455 |
+
memory_mask: Optional[Tensor] = None,
|
| 456 |
+
tgt_key_padding_mask: Optional[Tensor] = None,
|
| 457 |
+
memory_key_padding_mask: Optional[Tensor] = None,
|
| 458 |
+
pos: Optional[Tensor] = None,
|
| 459 |
+
query_pos: Optional[Tensor] = None,
|
| 460 |
+
):
|
| 461 |
+
if self.normalize_before:
|
| 462 |
+
return self.forward_pre(
|
| 463 |
+
tgt,
|
| 464 |
+
memory,
|
| 465 |
+
tgt_mask,
|
| 466 |
+
memory_mask,
|
| 467 |
+
tgt_key_padding_mask,
|
| 468 |
+
memory_key_padding_mask,
|
| 469 |
+
pos,
|
| 470 |
+
query_pos,
|
| 471 |
+
)
|
| 472 |
+
return self.forward_post(
|
| 473 |
+
tgt,
|
| 474 |
+
memory,
|
| 475 |
+
tgt_mask,
|
| 476 |
+
memory_mask,
|
| 477 |
+
tgt_key_padding_mask,
|
| 478 |
+
memory_key_padding_mask,
|
| 479 |
+
pos,
|
| 480 |
+
query_pos,
|
| 481 |
+
)
|
| 482 |
+
|
| 483 |
+
|
| 484 |
+
def _get_clones(module, N):
|
| 485 |
+
return nn.ModuleList([copy.deepcopy(module) for i in range(N)])
|
| 486 |
+
|
| 487 |
+
|
| 488 |
+
def _get_activation_fn(activation):
|
| 489 |
+
"""Return an activation function given a string."""
|
| 490 |
+
if activation == "relu":
|
| 491 |
+
return F.relu
|
| 492 |
+
if activation == "gelu":
|
| 493 |
+
return F.gelu
|
| 494 |
+
raise RuntimeError(f"activation should be relu/gelu, not {activation}.")
|
| 495 |
+
|
| 496 |
+
|
| 497 |
+
|
| 498 |
+
def reparametrize(mu: torch.Tensor, logvar: torch.Tensor) -> torch.Tensor:
|
| 499 |
+
std = logvar.div(2).exp()
|
| 500 |
+
return mu + std * torch.randn_like(std)
|
| 501 |
+
|
| 502 |
+
|
| 503 |
+
def get_sinusoid_encoding_table(n_position: int, d_hid: int) -> torch.Tensor:
|
| 504 |
+
def angle_vec(position: int) -> list[float]:
|
| 505 |
+
return [position / np.power(10000, 2 * (j // 2) / d_hid) for j in range(d_hid)]
|
| 506 |
+
|
| 507 |
+
table = np.array([angle_vec(i) for i in range(n_position)])
|
| 508 |
+
table[:, 0::2] = np.sin(table[:, 0::2])
|
| 509 |
+
table[:, 1::2] = np.cos(table[:, 1::2])
|
| 510 |
+
return torch.FloatTensor(table).unsqueeze(0)
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def build_style_encoder(
|
| 514 |
+
hidden_dim: int, nheads: int, dim_feedforward: int, enc_layers: int, dropout: float
|
| 515 |
+
) -> TransformerEncoder:
|
| 516 |
+
"""The CVAE style encoder (a plain transformer encoder over [CLS, qpos, action seq])."""
|
| 517 |
+
layer = TransformerEncoderLayer(hidden_dim, nheads, dim_feedforward, dropout, "relu", False)
|
| 518 |
+
return TransformerEncoder(layer, enc_layers, norm=None)
|
| 519 |
+
|
| 520 |
+
|
| 521 |
+
class DETRVAE(nn.Module):
|
| 522 |
+
"""CVAE decoder: (qpos, images[, action seq]) → ``num_queries`` future actions."""
|
| 523 |
+
|
| 524 |
+
def __init__(
|
| 525 |
+
self,
|
| 526 |
+
backbone: Joiner,
|
| 527 |
+
transformer: Transformer,
|
| 528 |
+
encoder: TransformerEncoder,
|
| 529 |
+
*,
|
| 530 |
+
qpos_dim: int,
|
| 531 |
+
action_dim: int,
|
| 532 |
+
num_queries: int,
|
| 533 |
+
latent_dim: int = 32,
|
| 534 |
+
) -> None:
|
| 535 |
+
super().__init__()
|
| 536 |
+
self.num_queries = num_queries
|
| 537 |
+
self.transformer = transformer
|
| 538 |
+
self.encoder = encoder
|
| 539 |
+
hidden_dim = transformer.d_model
|
| 540 |
+
self.action_head = nn.Linear(hidden_dim, action_dim)
|
| 541 |
+
self.query_embed = nn.Embedding(num_queries, hidden_dim)
|
| 542 |
+
self.backbone = backbone # ONE backbone shared by every camera (upstream behavior)
|
| 543 |
+
self.input_proj = nn.Conv2d(backbone.num_channels, hidden_dim, kernel_size=1)
|
| 544 |
+
self.input_proj_robot_state = nn.Linear(qpos_dim, hidden_dim)
|
| 545 |
+
|
| 546 |
+
# CVAE style encoder inputs
|
| 547 |
+
self.latent_dim = latent_dim
|
| 548 |
+
self.cls_embed = nn.Embedding(1, hidden_dim)
|
| 549 |
+
self.encoder_action_proj = nn.Linear(action_dim, hidden_dim)
|
| 550 |
+
self.encoder_joint_proj = nn.Linear(qpos_dim, hidden_dim)
|
| 551 |
+
self.latent_proj = nn.Linear(hidden_dim, latent_dim * 2)
|
| 552 |
+
self.register_buffer(
|
| 553 |
+
"pos_table", get_sinusoid_encoding_table(1 + 1 + num_queries, hidden_dim)
|
| 554 |
+
)
|
| 555 |
+
# decoder side
|
| 556 |
+
self.latent_out_proj = nn.Linear(latent_dim, hidden_dim)
|
| 557 |
+
self.additional_pos_embed = nn.Embedding(2, hidden_dim) # latent + proprio slots
|
| 558 |
+
|
| 559 |
+
def forward(
|
| 560 |
+
self,
|
| 561 |
+
qpos: torch.Tensor,
|
| 562 |
+
images: torch.Tensor,
|
| 563 |
+
actions: torch.Tensor | None = None,
|
| 564 |
+
is_pad: torch.Tensor | None = None,
|
| 565 |
+
) -> tuple[torch.Tensor, tuple[torch.Tensor | None, torch.Tensor | None]]:
|
| 566 |
+
"""``qpos (B, Dq)``, ``images (B, ncam, C, H, W)``; train passes ``actions (B, T, Da)``."""
|
| 567 |
+
is_training = actions is not None
|
| 568 |
+
bs = qpos.shape[0]
|
| 569 |
+
if is_training:
|
| 570 |
+
action_embed = self.encoder_action_proj(actions)
|
| 571 |
+
qpos_embed = self.encoder_joint_proj(qpos).unsqueeze(1)
|
| 572 |
+
cls_embed = self.cls_embed.weight.unsqueeze(0).repeat(bs, 1, 1)
|
| 573 |
+
encoder_input = torch.cat([cls_embed, qpos_embed, action_embed], dim=1)
|
| 574 |
+
encoder_input = encoder_input.permute(1, 0, 2)
|
| 575 |
+
if is_pad is None:
|
| 576 |
+
is_pad = torch.zeros(bs, actions.shape[1], dtype=torch.bool, device=qpos.device)
|
| 577 |
+
cls_joint_is_pad = torch.full((bs, 2), False, device=qpos.device)
|
| 578 |
+
key_pad = torch.cat([cls_joint_is_pad, is_pad], dim=1)
|
| 579 |
+
pos_embed = self.pos_table.clone().detach().permute(1, 0, 2)
|
| 580 |
+
encoder_output = self.encoder(
|
| 581 |
+
encoder_input, pos=pos_embed, src_key_padding_mask=key_pad
|
| 582 |
+
)[0]
|
| 583 |
+
latent_info = self.latent_proj(encoder_output)
|
| 584 |
+
mu = latent_info[:, : self.latent_dim]
|
| 585 |
+
logvar = latent_info[:, self.latent_dim :]
|
| 586 |
+
latent_input = self.latent_out_proj(reparametrize(mu, logvar))
|
| 587 |
+
else:
|
| 588 |
+
mu = logvar = None
|
| 589 |
+
latent_sample = torch.zeros(bs, self.latent_dim, device=qpos.device)
|
| 590 |
+
latent_input = self.latent_out_proj(latent_sample)
|
| 591 |
+
|
| 592 |
+
all_cam_features, all_cam_pos = [], []
|
| 593 |
+
for cam_id in range(images.shape[1]):
|
| 594 |
+
features, pos = self.backbone(images[:, cam_id])
|
| 595 |
+
all_cam_features.append(self.input_proj(features[0]))
|
| 596 |
+
all_cam_pos.append(pos[0])
|
| 597 |
+
proprio_input = self.input_proj_robot_state(qpos)
|
| 598 |
+
src = torch.cat(all_cam_features, dim=3) # cameras fold into the width axis
|
| 599 |
+
pos = torch.cat(all_cam_pos, dim=3)
|
| 600 |
+
hs = self.transformer(
|
| 601 |
+
src,
|
| 602 |
+
None,
|
| 603 |
+
self.query_embed.weight,
|
| 604 |
+
pos,
|
| 605 |
+
latent_input,
|
| 606 |
+
proprio_input,
|
| 607 |
+
self.additional_pos_embed.weight,
|
| 608 |
+
)[0]
|
| 609 |
+
return self.action_head(hs), (mu, logvar)
|
| 610 |
+
|
| 611 |
+
|
| 612 |
+
def kl_divergence(mu: torch.Tensor, logvar: torch.Tensor) -> torch.Tensor:
|
| 613 |
+
"""Total KL(q(z|x) || N(0, I)), summed over latent dims, meaned over the batch."""
|
| 614 |
+
klds = -0.5 * (1 + logvar - mu.pow(2) - logvar.exp())
|
| 615 |
+
return klds.sum(1).mean()
|
code/hb_baselines_v1/baselines/nets.py
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Networks of the FM-DiT and DP (DDPM-DiT) baselines: the AdaLN DiT action backbone and the camera + state encoder.
|
| 2 |
+
|
| 3 |
+
Ported from DextraVerse's imitation-learning core (`dextraverse/algorithms/il/models/nets/dit.py`, `layers.py`,
|
| 4 |
+
`positional_embedding.py`, `vision/backbones.py`, `vision/encoder.py`), unchanged in architecture and initialization.
|
| 5 |
+
Left out: the ROVE improvement embedding, the spatial-softmax / R3M / tactile options and the inpainting path (the
|
| 6 |
+
baselines always condition through the global observation feature). Added: the ResNet's normalization choice
|
| 7 |
+
(`get_resnet`): DextraVerse's GroupNorm for a backbone trained from scratch, or BatchNorm frozen at the pretrained
|
| 8 |
+
statistics (the DETR / ACT practice) for an ImageNet-initialized backbone that is fine-tuned with the policy.
|
| 9 |
+
"""
|
| 10 |
+
from __future__ import annotations
|
| 11 |
+
|
| 12 |
+
import math
|
| 13 |
+
|
| 14 |
+
import torch
|
| 15 |
+
import torch.nn as nn
|
| 16 |
+
import torch.nn.functional as F
|
| 17 |
+
import torchvision
|
| 18 |
+
|
| 19 |
+
IMAGENET_MEAN = (0.485, 0.456, 0.406)
|
| 20 |
+
IMAGENET_STD = (0.229, 0.224, 0.225)
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
class SinusoidalPosEmb(nn.Module):
|
| 24 |
+
def __init__(self, dim):
|
| 25 |
+
super().__init__()
|
| 26 |
+
self.dim = dim
|
| 27 |
+
|
| 28 |
+
def forward(self, x):
|
| 29 |
+
half_dim = self.dim // 2
|
| 30 |
+
emb = math.log(10000) / (half_dim - 1)
|
| 31 |
+
emb = torch.exp(torch.arange(half_dim, device=x.device) * -emb)
|
| 32 |
+
emb = x[:, None] * emb[None, :]
|
| 33 |
+
return torch.cat((emb.sin(), emb.cos()), dim=-1)
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
class RotaryPosEmb(nn.Module):
|
| 37 |
+
"""Rotary position embedding over each attention head's (S, head_dim) slice."""
|
| 38 |
+
|
| 39 |
+
def __init__(self, dim):
|
| 40 |
+
super().__init__()
|
| 41 |
+
self.dim = dim
|
| 42 |
+
self.register_buffer('inv_freq', 1.0 / (10000 ** (torch.arange(0, dim, 2).float() / dim)))
|
| 43 |
+
|
| 44 |
+
def forward(self, x): # x: (B, heads, S, head_dim)
|
| 45 |
+
t = torch.arange(x.shape[-2], device=x.device, dtype=self.inv_freq.dtype)
|
| 46 |
+
freqs = torch.outer(t, self.inv_freq.to(x.device))
|
| 47 |
+
emb = torch.cat([freqs, freqs], dim=-1)
|
| 48 |
+
cos, sin = emb.cos()[None, None], emb.sin()[None, None]
|
| 49 |
+
x1, x2 = x[..., : x.shape[-1] // 2], x[..., x.shape[-1] // 2:]
|
| 50 |
+
return x * cos + torch.cat([-x2, x1], dim=-1) * sin
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
class Mlp(nn.Module):
|
| 54 |
+
"""The ViT MLP (timm.layers.Mlp) as DextraVerse's nets/layers.py."""
|
| 55 |
+
|
| 56 |
+
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.0):
|
| 57 |
+
super().__init__()
|
| 58 |
+
out_features = out_features or in_features
|
| 59 |
+
hidden_features = hidden_features or in_features
|
| 60 |
+
self.fc1 = nn.Linear(in_features, hidden_features)
|
| 61 |
+
self.act = act_layer()
|
| 62 |
+
self.drop1 = nn.Dropout(drop)
|
| 63 |
+
self.norm = nn.Identity()
|
| 64 |
+
self.fc2 = nn.Linear(hidden_features, out_features)
|
| 65 |
+
self.drop2 = nn.Dropout(drop)
|
| 66 |
+
|
| 67 |
+
def forward(self, x):
|
| 68 |
+
return self.drop2(self.fc2(self.norm(self.drop1(self.act(self.fc1(x))))))
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
class Attention(nn.Module):
|
| 72 |
+
def __init__(self, dim, num_heads=8, qkv_bias=True, attn_drop=0.0, proj_drop=0.0, qk_norm=True):
|
| 73 |
+
super().__init__()
|
| 74 |
+
assert dim % num_heads == 0, 'dim should be divisible by num_heads'
|
| 75 |
+
self.num_heads = num_heads
|
| 76 |
+
self.head_dim = dim // num_heads
|
| 77 |
+
self.attn_drop = attn_drop
|
| 78 |
+
self.proj_drop = nn.Dropout(proj_drop)
|
| 79 |
+
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
|
| 80 |
+
self.q_norm = nn.LayerNorm(self.head_dim) if qk_norm else nn.Identity()
|
| 81 |
+
self.k_norm = nn.LayerNorm(self.head_dim) if qk_norm else nn.Identity()
|
| 82 |
+
self.proj = nn.Linear(dim, dim)
|
| 83 |
+
self.rope = RotaryPosEmb(self.head_dim)
|
| 84 |
+
|
| 85 |
+
def forward(self, x):
|
| 86 |
+
B, S, C = x.shape
|
| 87 |
+
qkv = self.qkv(x).reshape(B, S, 3, self.num_heads, self.head_dim).permute(2, 0, 3, 1, 4)
|
| 88 |
+
q, k, v = qkv.unbind(0)
|
| 89 |
+
q, k = self.rope(self.q_norm(q)), self.rope(self.k_norm(k))
|
| 90 |
+
x = F.scaled_dot_product_attention(q, k, v, dropout_p=self.attn_drop if self.training else 0.0)
|
| 91 |
+
return self.proj_drop(self.proj(x.transpose(1, 2).reshape(B, S, C)))
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
class AdaLNBlock(nn.Module):
|
| 95 |
+
"""Adaptive-LayerNorm transformer block as in DiT (Peebles et al. 2022)."""
|
| 96 |
+
|
| 97 |
+
def __init__(self, dim, num_heads, mlp_ratio=4.0, dropout=0.0):
|
| 98 |
+
super().__init__()
|
| 99 |
+
self.norm1 = nn.LayerNorm(dim, elementwise_affine=False, eps=1e-6)
|
| 100 |
+
self.attn = Attention(dim, num_heads=num_heads, attn_drop=dropout, proj_drop=dropout)
|
| 101 |
+
self.norm2 = nn.LayerNorm(dim, elementwise_affine=False, eps=1e-6)
|
| 102 |
+
self.mlp = Mlp(in_features=dim, hidden_features=int(dim * mlp_ratio),
|
| 103 |
+
act_layer=lambda: nn.GELU(approximate='tanh'), drop=0)
|
| 104 |
+
self.ada_ln = nn.Sequential(nn.SiLU(), nn.Linear(dim, 6 * dim))
|
| 105 |
+
self.dim = dim
|
| 106 |
+
nn.init.constant_(self.ada_ln[-1].weight, 0)
|
| 107 |
+
nn.init.constant_(self.ada_ln[-1].bias, 0)
|
| 108 |
+
|
| 109 |
+
def forward(self, x, t, c):
|
| 110 |
+
B = x.shape[0]
|
| 111 |
+
gamma1, gamma2, scale1, scale2, shift1, shift2 = self.ada_ln(F.silu(t + c)).view(B, 6, 1, self.dim).unbind(1)
|
| 112 |
+
x = x + self.attn(self.norm1(x).mul(scale1.add(1)).add_(shift1)).mul_(gamma1)
|
| 113 |
+
return x + self.mlp(self.norm2(x).mul(scale2.add(1)).add_(shift2)).mul_(gamma2)
|
| 114 |
+
|
| 115 |
+
|
| 116 |
+
class FlowTransformer(nn.Module):
|
| 117 |
+
"""DiT action backbone: AdaLN blocks over the H action tokens, conditioned on time_embed(t) + cond_embed(obs).
|
| 118 |
+
|
| 119 |
+
As DextraVerse, the generic Xavier initialization runs after the blocks' zero init of their AdaLN projection, so
|
| 120 |
+
it is not the full AdaLN-Zero recipe (kept: it is the reference's training behaviour)."""
|
| 121 |
+
|
| 122 |
+
def __init__(self, input_dim, condition_dim, hidden_dim, output_dim, num_layers, num_heads, mlp_ratio=4.0,
|
| 123 |
+
dropout=0.1, time_embed_dim=256):
|
| 124 |
+
super().__init__()
|
| 125 |
+
self.input_proj = nn.Linear(input_dim, hidden_dim)
|
| 126 |
+
self.time_embed = nn.Sequential(SinusoidalPosEmb(time_embed_dim), nn.Linear(time_embed_dim, time_embed_dim * 4),
|
| 127 |
+
nn.Mish(), nn.Linear(time_embed_dim * 4, hidden_dim))
|
| 128 |
+
self.cond_embed = nn.Linear(condition_dim, hidden_dim)
|
| 129 |
+
self.transformer_blocks = nn.ModuleList(
|
| 130 |
+
[AdaLNBlock(hidden_dim, num_heads, mlp_ratio=mlp_ratio, dropout=dropout) for _ in range(num_layers)])
|
| 131 |
+
self.norm = nn.LayerNorm(hidden_dim)
|
| 132 |
+
self.out_proj = nn.Linear(hidden_dim, output_dim)
|
| 133 |
+
|
| 134 |
+
def basic_init(module):
|
| 135 |
+
if isinstance(module, nn.Linear):
|
| 136 |
+
nn.init.xavier_uniform_(module.weight)
|
| 137 |
+
if module.bias is not None:
|
| 138 |
+
nn.init.constant_(module.bias, 0)
|
| 139 |
+
|
| 140 |
+
self.apply(basic_init)
|
| 141 |
+
nn.init.normal_(self.time_embed[1].weight, std=0.02)
|
| 142 |
+
nn.init.normal_(self.time_embed[3].weight, std=0.02)
|
| 143 |
+
|
| 144 |
+
def forward(self, x, t, global_cond):
|
| 145 |
+
if not torch.is_tensor(t):
|
| 146 |
+
t = torch.tensor(t, device=x.device)
|
| 147 |
+
if t.ndim == 0:
|
| 148 |
+
t = t.expand(x.shape[0])
|
| 149 |
+
x = self.input_proj(x)
|
| 150 |
+
t = self.time_embed(t)
|
| 151 |
+
c = self.cond_embed(global_cond)
|
| 152 |
+
for block in self.transformer_blocks:
|
| 153 |
+
x = block(x, t, c)
|
| 154 |
+
return self.out_proj(self.norm(x))
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
def replace_batchnorm_with_groupnorm(module: nn.Module) -> nn.Module:
|
| 158 |
+
"""DextraVerse's use_group_norm: every BatchNorm2d becomes GroupNorm(num_features // 16 groups)."""
|
| 159 |
+
for name, child in module.named_children():
|
| 160 |
+
if isinstance(child, nn.BatchNorm2d):
|
| 161 |
+
setattr(module, name, nn.GroupNorm(num_groups=child.num_features // 16, num_channels=child.num_features))
|
| 162 |
+
else:
|
| 163 |
+
replace_batchnorm_with_groupnorm(child)
|
| 164 |
+
return module
|
| 165 |
+
|
| 166 |
+
|
| 167 |
+
NORMS = ('group', 'frozen_bn')
|
| 168 |
+
|
| 169 |
+
|
| 170 |
+
def get_resnet(name='resnet18', weights=None, norm='group') -> nn.Module:
|
| 171 |
+
"""A torchvision ResNet with its classifier removed: (N, 3, H, W) -> (N, 512) globally pooled.
|
| 172 |
+
|
| 173 |
+
weights: torchvision weights name (e.g. 'IMAGENET1K_V1') to initialize from, or None (random initialization;
|
| 174 |
+
a checkpoint load supplies every weight). norm: 'group' replaces every BatchNorm with GroupNorm (DextraVerse's
|
| 175 |
+
use_group_norm, for training from scratch: pretrained BatchNorm statistics and affine are dropped); 'frozen_bn'
|
| 176 |
+
keeps BatchNorm frozen at its (pretrained) running statistics and affine, the convolutions fine-tune."""
|
| 177 |
+
if norm == 'frozen_bn':
|
| 178 |
+
from .act_nets import FrozenBatchNorm2d
|
| 179 |
+
resnet = getattr(torchvision.models, name)(weights=weights, norm_layer=FrozenBatchNorm2d)
|
| 180 |
+
elif norm == 'group':
|
| 181 |
+
resnet = replace_batchnorm_with_groupnorm(getattr(torchvision.models, name)(weights=weights))
|
| 182 |
+
else:
|
| 183 |
+
raise ValueError(f'norm must be one of {NORMS}, got {norm!r}')
|
| 184 |
+
resnet.fc = nn.Identity()
|
| 185 |
+
return resnet
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
class ImageStateEncoder(nn.Module):
|
| 189 |
+
"""DextraVerse MultiImageObsEncoder as configured for FM-DiT / DDPM-DiT: one ResNet shared by every camera
|
| 190 |
+
(share_rgb_model; `get_resnet` weights and norm), ImageNet normalization of the [0, 1] images, the pooled features
|
| 191 |
+
of each camera in the contract's camera order, then the normalized state.
|
| 192 |
+
Output (B, n_cameras * 512 + state_dim)."""
|
| 193 |
+
|
| 194 |
+
def __init__(self, n_cameras, state_dim, backbone='resnet18', weights=None, norm='group'):
|
| 195 |
+
super().__init__()
|
| 196 |
+
self.rgb = get_resnet(backbone, weights=weights, norm=norm)
|
| 197 |
+
self.n_cameras, self.state_dim = int(n_cameras), int(state_dim)
|
| 198 |
+
self.register_buffer('mean', torch.tensor(IMAGENET_MEAN).view(1, 3, 1, 1), persistent=False)
|
| 199 |
+
self.register_buffer('std', torch.tensor(IMAGENET_STD).view(1, 3, 1, 1), persistent=False)
|
| 200 |
+
self.feature_dim = self.n_cameras * (512 if backbone in ('resnet18', 'resnet34') else 2048) + self.state_dim
|
| 201 |
+
|
| 202 |
+
def forward(self, images, state):
|
| 203 |
+
"""images (B, n_cameras, 3, H, W) in [0, 1]; state (B, state_dim) normalized."""
|
| 204 |
+
B = images.shape[0]
|
| 205 |
+
x = (images.flatten(0, 1) - self.mean) / self.std
|
| 206 |
+
features = self.rgb(x).reshape(B, -1) # camera features side by side, in camera order
|
| 207 |
+
return torch.cat([features, state], dim=-1)
|
code/hb_baselines_v1/baselines/policies.py
ADDED
|
@@ -0,0 +1,281 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""The three baseline policies behind one contract, ported from DextraVerse's imitation-learning core:
|
| 2 |
+
|
| 3 |
+
- `fm_dit`, `FMDiTPolicy` (reference: dextraverse/algorithms/il/models/fm_dit.py + fm_base.py): flow matching, MSE on
|
| 4 |
+
the velocity `a - noise`; sampled with 10 midpoint steps from noise (20 DiT calls);
|
| 5 |
+
- `dp`, `DPPolicy` (ddpm_dit.py + ddpm_base.py: Diffusion Policy with a DiT backbone): DDPM epsilon MSE over 100
|
| 6 |
+
steps; sampled with the 100 DDPM steps;
|
| 7 |
+
- `act`, `ACTPolicy` (act.py + nets/act/): L1 + `kl_weight` x KL of the CVAE; decoded from the zero latent in one pass.
|
| 8 |
+
|
| 9 |
+
Contract (every policy): `compute_loss(images, state, action) -> (loss, metrics)` and
|
| 10 |
+
`predict(images, state, generator) -> (action, normalized action)`; images (B, n_cameras, 3, H, W) float in [0, 1],
|
| 11 |
+
state (B, state_dim) and action (B, horizon, action_dim) in physical units. Each policy owns its `Normalizer`
|
| 12 |
+
(DextraVerse's LinearNormalizer 'limits' mode: state and action to [-1, 1] per dimension, constant dimensions shifted
|
| 13 |
+
to 0), saved in its state dict. One observation frame (n_obs_steps 1: the current images and state); the chunk's row 0
|
| 14 |
+
is the action of the observation's own frame (the LeRobot rows t..t+horizon-1). The configuration that builds a
|
| 15 |
+
policy is a plain dict (`PolicyConfig` fields), stored in the checkpoint.
|
| 16 |
+
|
| 17 |
+
The ResNet18 starts from torchvision's ImageNet-1k weights (`backbone_weights` 'IMAGENET1K_V1', the default since
|
| 18 |
+
2026-11-16) and is fine-tuned with the policy, its BatchNorm frozen at the pretrained statistics (`backbone_norm`
|
| 19 |
+
'frozen_bn', as ACT always does); `backbone_weights` None trains from scratch with DextraVerse's GroupNorm encoder
|
| 20 |
+
(FM-DiT, DP) or ACT's frozen-BatchNorm one. A checkpoint load builds the structure without fetching any weights.
|
| 21 |
+
"""
|
| 22 |
+
from __future__ import annotations
|
| 23 |
+
|
| 24 |
+
from dataclasses import asdict, dataclass, field, replace
|
| 25 |
+
|
| 26 |
+
import torch
|
| 27 |
+
import torch.nn as nn
|
| 28 |
+
import torch.nn.functional as F
|
| 29 |
+
|
| 30 |
+
from .act_nets import DETRVAE, Transformer, build_backbone, build_style_encoder, kl_divergence
|
| 31 |
+
from .nets import IMAGENET_MEAN, IMAGENET_STD, FlowTransformer, ImageStateEncoder
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
@dataclass
|
| 35 |
+
class PolicyConfig:
|
| 36 |
+
"""Everything that builds a policy (stored in the checkpoint's config.json). Model defaults are DextraVerse's
|
| 37 |
+
configs/algorithm/il/model/{fm_dit,ddpm_dit,act}.yaml."""
|
| 38 |
+
policy: str
|
| 39 |
+
n_cameras: int
|
| 40 |
+
state_dim: int
|
| 41 |
+
action_dim: int
|
| 42 |
+
horizon: int = 16
|
| 43 |
+
backbone: str = 'resnet18'
|
| 44 |
+
backbone_weights: str | None = 'IMAGENET1K_V1' # torchvision weights to initialize from; None = from scratch
|
| 45 |
+
backbone_norm: str | None = None # 'frozen_bn' or 'group'; None: frozen_bn when pretrained or ACT, else group
|
| 46 |
+
# FM-DiT / DP (DiT backbone)
|
| 47 |
+
hidden_dim: int = 384
|
| 48 |
+
num_layers: int = 4
|
| 49 |
+
num_heads: int = 8
|
| 50 |
+
mlp_ratio: float = 4.0
|
| 51 |
+
dropout: float = 0.1
|
| 52 |
+
time_embed_dim: int = 128
|
| 53 |
+
num_inference_steps: int | None = None # None: FM-DiT 10 midpoint steps, DP every training timestep (100)
|
| 54 |
+
# DP noise schedule (diffusers DDPMScheduler)
|
| 55 |
+
num_train_timesteps: int = 100
|
| 56 |
+
beta_schedule: str = 'squaredcos_cap_v2'
|
| 57 |
+
prediction_type: str = 'epsilon'
|
| 58 |
+
clip_sample: bool = True
|
| 59 |
+
# ACT
|
| 60 |
+
act_hidden_dim: int = 512
|
| 61 |
+
dim_feedforward: int = 3200
|
| 62 |
+
enc_layers: int = 4
|
| 63 |
+
dec_layers: int = 7
|
| 64 |
+
nheads: int = 8
|
| 65 |
+
latent_dim: int = 32
|
| 66 |
+
kl_weight: float = 10.0
|
| 67 |
+
extra: dict = field(default_factory=dict)
|
| 68 |
+
|
| 69 |
+
def __post_init__(self):
|
| 70 |
+
if self.backbone_norm is None:
|
| 71 |
+
self.backbone_norm = 'frozen_bn' if self.backbone_weights or self.policy == 'act' else 'group'
|
| 72 |
+
if self.policy == 'act' and self.backbone_norm != 'frozen_bn':
|
| 73 |
+
raise ValueError("ACT's backbone keeps frozen BatchNorm (backbone_norm 'frozen_bn')")
|
| 74 |
+
|
| 75 |
+
@classmethod
|
| 76 |
+
def from_dict(cls, data: dict) -> PolicyConfig:
|
| 77 |
+
known = {k: v for k, v in data.items() if k in cls.__dataclass_fields__}
|
| 78 |
+
return cls(**known)
|
| 79 |
+
|
| 80 |
+
def to_dict(self) -> dict:
|
| 81 |
+
return asdict(self)
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
class Normalizer(nn.Module):
|
| 85 |
+
"""Per-dimension affine map to [-1, 1] from the training data's min/max (DextraVerse LinearNormalizer, mode
|
| 86 |
+
'limits', fit_offset, range_eps 1e-4): x_n = x * scale + offset; a dimension whose range is below range_eps gets
|
| 87 |
+
scale 1 and maps its value to 0."""
|
| 88 |
+
|
| 89 |
+
def __init__(self, dim: int):
|
| 90 |
+
super().__init__()
|
| 91 |
+
self.register_buffer('scale', torch.ones(dim))
|
| 92 |
+
self.register_buffer('offset', torch.zeros(dim))
|
| 93 |
+
|
| 94 |
+
@torch.no_grad()
|
| 95 |
+
def fit(self, minimum, maximum, range_eps=1e-4):
|
| 96 |
+
lo = torch.as_tensor(minimum, dtype=torch.float32)
|
| 97 |
+
hi = torch.as_tensor(maximum, dtype=torch.float32)
|
| 98 |
+
span = hi - lo
|
| 99 |
+
ignore = span < range_eps
|
| 100 |
+
span[ignore] = 2.0
|
| 101 |
+
scale = 2.0 / span
|
| 102 |
+
offset = -1.0 - scale * lo
|
| 103 |
+
offset[ignore] = -lo[ignore]
|
| 104 |
+
self.scale.copy_(scale)
|
| 105 |
+
self.offset.copy_(offset)
|
| 106 |
+
|
| 107 |
+
def normalize(self, x):
|
| 108 |
+
return x * self.scale + self.offset
|
| 109 |
+
|
| 110 |
+
def unnormalize(self, x):
|
| 111 |
+
return (x - self.offset) / self.scale
|
| 112 |
+
|
| 113 |
+
|
| 114 |
+
class BasePolicy(nn.Module):
|
| 115 |
+
name = ''
|
| 116 |
+
backbone_prefix = '' # state-dict prefix of the image backbone (its own learning rate in training)
|
| 117 |
+
|
| 118 |
+
def __init__(self, cfg: PolicyConfig, init_weights=None):
|
| 119 |
+
super().__init__()
|
| 120 |
+
self.cfg = cfg
|
| 121 |
+
self.state_norm = Normalizer(cfg.state_dim)
|
| 122 |
+
self.action_norm = Normalizer(cfg.action_dim)
|
| 123 |
+
|
| 124 |
+
def fit_normalizers(self, stats: dict):
|
| 125 |
+
self.state_norm.fit(stats['state']['min'], stats['state']['max'])
|
| 126 |
+
self.action_norm.fit(stats['action']['min'], stats['action']['max'])
|
| 127 |
+
|
| 128 |
+
@property
|
| 129 |
+
def sampling_steps(self) -> int:
|
| 130 |
+
return 1
|
| 131 |
+
|
| 132 |
+
def compute_loss(self, images, state, action):
|
| 133 |
+
raise NotImplementedError
|
| 134 |
+
|
| 135 |
+
def predict(self, images, state, generator=None):
|
| 136 |
+
raise NotImplementedError
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
class DiTPolicy(BasePolicy):
|
| 140 |
+
"""Shared by FM-DiT and DP: the shared-ResNet image + state encoder and the AdaLN DiT over the action chunk
|
| 141 |
+
(global observation conditioning, DextraVerse obs_as_global_cond)."""
|
| 142 |
+
backbone_prefix = 'obs_encoder.rgb.'
|
| 143 |
+
|
| 144 |
+
def __init__(self, cfg: PolicyConfig, init_weights=None):
|
| 145 |
+
super().__init__(cfg)
|
| 146 |
+
self.obs_encoder = ImageStateEncoder(cfg.n_cameras, cfg.state_dim, backbone=cfg.backbone,
|
| 147 |
+
weights=init_weights, norm=cfg.backbone_norm)
|
| 148 |
+
self.model = FlowTransformer(input_dim=cfg.action_dim, condition_dim=self.obs_encoder.feature_dim,
|
| 149 |
+
hidden_dim=cfg.hidden_dim, output_dim=cfg.action_dim, num_layers=cfg.num_layers,
|
| 150 |
+
num_heads=cfg.num_heads, mlp_ratio=cfg.mlp_ratio, dropout=cfg.dropout,
|
| 151 |
+
time_embed_dim=cfg.time_embed_dim)
|
| 152 |
+
|
| 153 |
+
def condition(self, images, state):
|
| 154 |
+
return self.obs_encoder(images, self.state_norm.normalize(state))
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
class FMDiTPolicy(DiTPolicy):
|
| 158 |
+
"""Flow-matching DiT (DextraVerse FlowMatchingDiTImagePolicy): x_t = (1 - t) noise + t a, t ~ U(0, 1), the DiT
|
| 159 |
+
regresses the velocity a - noise; sampling integrates t = 0 -> 1 with the midpoint rule."""
|
| 160 |
+
name = 'fm_dit'
|
| 161 |
+
|
| 162 |
+
@property
|
| 163 |
+
def sampling_steps(self) -> int:
|
| 164 |
+
return int(self.cfg.num_inference_steps or 10)
|
| 165 |
+
|
| 166 |
+
def compute_loss(self, images, state, action):
|
| 167 |
+
cond = self.condition(images, state)
|
| 168 |
+
target = self.action_norm.normalize(action)
|
| 169 |
+
noise = torch.randn_like(target)
|
| 170 |
+
t = torch.rand(target.shape[0], device=target.device)
|
| 171 |
+
te = t.view(-1, 1, 1)
|
| 172 |
+
x_t = (1 - te) * noise + te * target
|
| 173 |
+
loss = F.mse_loss(self.model(x_t, t, cond), target - noise)
|
| 174 |
+
return loss, dict(fm=float(loss.detach()))
|
| 175 |
+
|
| 176 |
+
@torch.no_grad()
|
| 177 |
+
def predict(self, images, state, generator=None):
|
| 178 |
+
cond = self.condition(images, state)
|
| 179 |
+
B, steps = images.shape[0], self.sampling_steps
|
| 180 |
+
x = torch.randn((B, self.cfg.horizon, self.cfg.action_dim), device=cond.device, dtype=cond.dtype,
|
| 181 |
+
generator=generator)
|
| 182 |
+
times = torch.linspace(0, 1.0, steps + 1, device=cond.device)
|
| 183 |
+
for i in range(steps):
|
| 184 |
+
t0 = times[i].view(1).expand(B)
|
| 185 |
+
t1 = times[i + 1].view(1).expand(B)
|
| 186 |
+
dt = (t1 - t0).view(-1, 1, 1)
|
| 187 |
+
x_mid = x + self.model(x, t0, cond) * dt / 2
|
| 188 |
+
x = x + dt * self.model(x_mid, t0 + (t1 - t0) / 2, cond)
|
| 189 |
+
return self.action_norm.unnormalize(x), x
|
| 190 |
+
|
| 191 |
+
|
| 192 |
+
class DPPolicy(DiTPolicy):
|
| 193 |
+
"""Diffusion Policy with the DiT backbone (DextraVerse DiffusionDiTImagePolicy, ddpm_dit.yaml): DDPM with 100
|
| 194 |
+
training steps, squaredcos_cap_v2 betas, fixed_small variance, clipped samples, epsilon prediction; sampled with
|
| 195 |
+
every training step (100 DiT calls)."""
|
| 196 |
+
name = 'dp'
|
| 197 |
+
|
| 198 |
+
def __init__(self, cfg: PolicyConfig, init_weights=None):
|
| 199 |
+
super().__init__(cfg, init_weights)
|
| 200 |
+
from diffusers.schedulers.scheduling_ddpm import DDPMScheduler
|
| 201 |
+
self.noise_scheduler = DDPMScheduler(num_train_timesteps=cfg.num_train_timesteps, beta_start=0.0001,
|
| 202 |
+
beta_end=0.02, beta_schedule=cfg.beta_schedule,
|
| 203 |
+
variance_type='fixed_small', clip_sample=cfg.clip_sample,
|
| 204 |
+
prediction_type=cfg.prediction_type)
|
| 205 |
+
|
| 206 |
+
@property
|
| 207 |
+
def sampling_steps(self) -> int:
|
| 208 |
+
return int(self.cfg.num_inference_steps or self.cfg.num_train_timesteps)
|
| 209 |
+
|
| 210 |
+
def compute_loss(self, images, state, action):
|
| 211 |
+
cond = self.condition(images, state)
|
| 212 |
+
target = self.action_norm.normalize(action)
|
| 213 |
+
noise = torch.randn_like(target)
|
| 214 |
+
t = torch.randint(0, self.noise_scheduler.config.num_train_timesteps, (target.shape[0],),
|
| 215 |
+
device=target.device).long()
|
| 216 |
+
noisy = self.noise_scheduler.add_noise(target, noise, t)
|
| 217 |
+
pred = self.model(noisy, t, cond)
|
| 218 |
+
goal = noise if self.cfg.prediction_type == 'epsilon' else target
|
| 219 |
+
loss = F.mse_loss(pred, goal)
|
| 220 |
+
return loss, dict(ddpm=float(loss.detach()))
|
| 221 |
+
|
| 222 |
+
@torch.no_grad()
|
| 223 |
+
def predict(self, images, state, generator=None):
|
| 224 |
+
cond = self.condition(images, state)
|
| 225 |
+
scheduler = self.noise_scheduler
|
| 226 |
+
x = torch.randn((images.shape[0], self.cfg.horizon, self.cfg.action_dim), device=cond.device,
|
| 227 |
+
dtype=cond.dtype, generator=generator)
|
| 228 |
+
scheduler.set_timesteps(self.sampling_steps, device=cond.device)
|
| 229 |
+
for t in scheduler.timesteps:
|
| 230 |
+
x = scheduler.step(self.model(x, t.to(cond.device), cond), t, x, generator=generator).prev_sample
|
| 231 |
+
return self.action_norm.unnormalize(x), x
|
| 232 |
+
|
| 233 |
+
|
| 234 |
+
class ACTPolicy(BasePolicy):
|
| 235 |
+
"""ACT (DextraVerse ACTImagePolicy, act.yaml): ImageNet-normalized cameras through one ResNet with frozen
|
| 236 |
+
BatchNorm (spatial tokens, no pooling), the normalized state as qpos, a CVAE style encoder over the action chunk in
|
| 237 |
+
training, the DETR decoder with `horizon` queries; loss L1 + kl_weight x KL; inference decodes from the zero
|
| 238 |
+
latent (deterministic)."""
|
| 239 |
+
name = 'act'
|
| 240 |
+
backbone_prefix = 'model.backbone.'
|
| 241 |
+
|
| 242 |
+
def __init__(self, cfg: PolicyConfig, init_weights=None):
|
| 243 |
+
super().__init__(cfg)
|
| 244 |
+
transformer = Transformer(d_model=cfg.act_hidden_dim, nhead=cfg.nheads, num_encoder_layers=cfg.enc_layers,
|
| 245 |
+
num_decoder_layers=cfg.dec_layers, dim_feedforward=cfg.dim_feedforward,
|
| 246 |
+
dropout=cfg.dropout, return_intermediate_dec=False)
|
| 247 |
+
self.model = DETRVAE(build_backbone(cfg.backbone, hidden_dim=cfg.act_hidden_dim, weights=init_weights),
|
| 248 |
+
transformer,
|
| 249 |
+
build_style_encoder(cfg.act_hidden_dim, cfg.nheads, cfg.dim_feedforward, cfg.enc_layers,
|
| 250 |
+
cfg.dropout),
|
| 251 |
+
qpos_dim=cfg.state_dim, action_dim=cfg.action_dim, num_queries=cfg.horizon,
|
| 252 |
+
latent_dim=cfg.latent_dim)
|
| 253 |
+
self.register_buffer('mean', torch.tensor(IMAGENET_MEAN).view(1, 1, 3, 1, 1), persistent=False)
|
| 254 |
+
self.register_buffer('std', torch.tensor(IMAGENET_STD).view(1, 1, 3, 1, 1), persistent=False)
|
| 255 |
+
|
| 256 |
+
def compute_loss(self, images, state, action):
|
| 257 |
+
target = self.action_norm.normalize(action)
|
| 258 |
+
a_hat, (mu, logvar) = self.model(self.state_norm.normalize(state), (images - self.mean) / self.std,
|
| 259 |
+
actions=target)
|
| 260 |
+
l1 = F.l1_loss(a_hat, target)
|
| 261 |
+
kl = kl_divergence(mu, logvar)
|
| 262 |
+
return l1 + self.cfg.kl_weight * kl, dict(l1=float(l1.detach()), kl=float(kl.detach()))
|
| 263 |
+
|
| 264 |
+
@torch.no_grad()
|
| 265 |
+
def predict(self, images, state, generator=None): # noqa: ARG002 - deterministic (zero latent)
|
| 266 |
+
a_hat, _ = self.model(self.state_norm.normalize(state), (images - self.mean) / self.std)
|
| 267 |
+
return self.action_norm.unnormalize(a_hat), a_hat
|
| 268 |
+
|
| 269 |
+
|
| 270 |
+
POLICIES = {cls.name: cls for cls in (FMDiTPolicy, DPPolicy, ACTPolicy)}
|
| 271 |
+
LABELS = {'fm_dit': 'FM-DiT', 'dp': 'DP (DDPM-DiT)', 'act': 'ACT'}
|
| 272 |
+
|
| 273 |
+
|
| 274 |
+
def build_policy(cfg: PolicyConfig | dict, pretrained: bool = True) -> BasePolicy:
|
| 275 |
+
"""The policy of `cfg`; pretrained=True initializes the backbone from cfg.backbone_weights (training),
|
| 276 |
+
False builds the same structure with random weights (a checkpoint load, which must not download anything)."""
|
| 277 |
+
cfg = cfg if isinstance(cfg, PolicyConfig) else PolicyConfig.from_dict(cfg)
|
| 278 |
+
if cfg.policy not in POLICIES:
|
| 279 |
+
raise KeyError(f'unknown baseline {cfg.policy!r}; one of {sorted(POLICIES)}')
|
| 280 |
+
cfg = replace(cfg) # a copy (resolved backbone_norm)
|
| 281 |
+
return POLICIES[cfg.policy](cfg, init_weights=cfg.backbone_weights if pretrained else None)
|
code/hb_baselines_v1/baselines/requirements.txt
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Environment of the FM-DiT / DP / ACT baselines (training and the policy server), Python 3.12, CUDA 12.8 wheels:
|
| 2 |
+
# uv venv <env> --python 3.12
|
| 3 |
+
# uv pip install --python <env>/bin/python -r evaluation/baselines/requirements.txt \
|
| 4 |
+
# --extra-index-url https://download.pytorch.org/whl/cu128 --index-strategy unsafe-best-match
|
| 5 |
+
torch==2.9.0+cu128
|
| 6 |
+
torchvision==0.24.0+cu128
|
| 7 |
+
diffusers==0.35.1
|
| 8 |
+
av==15.1.0
|
| 9 |
+
pyarrow==23.0.1
|
| 10 |
+
numpy==2.2.6
|
| 11 |
+
opencv-python-headless==4.11.0.86
|
| 12 |
+
pytest==8.4.2
|
code/hb_baselines_v1/baselines/runtime.py
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Checkpoints and inference of the baselines.
|
| 2 |
+
|
| 3 |
+
A checkpoint is a directory written by train.py (`<run>/checkpoints/step-NNNNNN/`, `final` links the last one):
|
| 4 |
+
|
| 5 |
+
- `model.pt`: torch.save of {format, config (the config.json text), state_dict}: the EMA weights (or the raw ones when
|
| 6 |
+
EMA is off) with the policy's state and action normalizers, loaded strictly with `weights_only=True`;
|
| 7 |
+
- `config.json`: the policy configuration, the contract (robot, cameras, state and action columns), the image size,
|
| 8 |
+
the training task text, dataset, episodes, recipe and statistics;
|
| 9 |
+
- `protocol.json`: model.pt's size and SHA-256.
|
| 10 |
+
|
| 11 |
+
`BaselinePolicy.predict` takes the live frames of the checkpoint's cameras (any size; resized with data.resize_frame,
|
| 12 |
+
as the training cache), the physical state of the contract and a seed, and returns the physical (horizon,
|
| 13 |
+
action_dim) chunk with its normalized form; row 0 is the action of the observation's frame.
|
| 14 |
+
"""
|
| 15 |
+
from __future__ import annotations
|
| 16 |
+
|
| 17 |
+
import hashlib
|
| 18 |
+
import json
|
| 19 |
+
from pathlib import Path
|
| 20 |
+
|
| 21 |
+
import numpy as np
|
| 22 |
+
|
| 23 |
+
FORMAT = 'hb_baselines/1'
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
def sha256(path) -> str:
|
| 27 |
+
digest = hashlib.sha256()
|
| 28 |
+
with Path(path).open('rb') as stream:
|
| 29 |
+
for block in iter(lambda: stream.read(16 << 20), b''):
|
| 30 |
+
digest.update(block)
|
| 31 |
+
return digest.hexdigest()
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
def save_checkpoint(folder, policy, config: dict):
|
| 35 |
+
"""Write model.pt, config.json and protocol.json of `policy` (an nn.Module) into `folder`."""
|
| 36 |
+
import torch
|
| 37 |
+
folder = Path(folder)
|
| 38 |
+
folder.mkdir(parents=True, exist_ok=True)
|
| 39 |
+
text = json.dumps(dict(config, format=FORMAT), indent=1)
|
| 40 |
+
state = {k: v.detach().cpu().contiguous() for k, v in policy.state_dict().items()}
|
| 41 |
+
torch.save(dict(format=FORMAT, config=text, state_dict=state), folder / 'model.pt.tmp')
|
| 42 |
+
(folder / 'model.pt.tmp').replace(folder / 'model.pt')
|
| 43 |
+
(folder / 'config.json').write_text(text)
|
| 44 |
+
(folder / 'protocol.json').write_text(json.dumps(dict(
|
| 45 |
+
format=FORMAT, step=config.get('step'), policy=config['policy']['policy'],
|
| 46 |
+
files={'model.pt': dict(bytes=(folder / 'model.pt').stat().st_size, sha256=sha256(folder / 'model.pt'))}),
|
| 47 |
+
indent=1))
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
def load_checkpoint(folder, device='cpu', verify=True):
|
| 51 |
+
"""(policy in eval mode on `device`, config dict) of a checkpoint directory."""
|
| 52 |
+
import torch
|
| 53 |
+
from .policies import build_policy
|
| 54 |
+
folder = Path(folder)
|
| 55 |
+
if verify:
|
| 56 |
+
protocol = json.loads((folder / 'protocol.json').read_text())
|
| 57 |
+
entry = protocol['files']['model.pt']
|
| 58 |
+
if (folder / 'model.pt').stat().st_size != entry['bytes']:
|
| 59 |
+
raise ValueError(f'{folder}/model.pt differs from protocol.json')
|
| 60 |
+
payload = torch.load(folder / 'model.pt', map_location='cpu', weights_only=True)
|
| 61 |
+
if payload.get('format') != FORMAT:
|
| 62 |
+
raise ValueError(f"{folder}: format {payload.get('format')!r}, expected {FORMAT}")
|
| 63 |
+
config = json.loads(payload['config'])
|
| 64 |
+
if json.loads((folder / 'config.json').read_text()) != config:
|
| 65 |
+
raise ValueError(f'{folder}: config.json differs from the one inside model.pt')
|
| 66 |
+
policy = build_policy(config['policy'], pretrained=False) # every weight comes from model.pt
|
| 67 |
+
policy.load_state_dict(payload['state_dict'], strict=True)
|
| 68 |
+
return policy.to(device).eval(), config
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
class BaselinePolicy:
|
| 72 |
+
"""A loaded checkpoint for closed-loop inference (one request at a time)."""
|
| 73 |
+
|
| 74 |
+
def __init__(self, checkpoint, device='cuda:0', policy: str | None = None, robot: str | None = None):
|
| 75 |
+
import torch
|
| 76 |
+
self.torch = torch
|
| 77 |
+
self.device = torch.device(device)
|
| 78 |
+
self.model, self.config = load_checkpoint(checkpoint, device=self.device)
|
| 79 |
+
self.checkpoint = str(Path(checkpoint).resolve())
|
| 80 |
+
name, contract = self.config['policy']['policy'], self.config['contract']
|
| 81 |
+
if policy is not None and name != policy:
|
| 82 |
+
raise ValueError(f'{checkpoint} is a {name!r} checkpoint, not {policy!r}')
|
| 83 |
+
if robot is not None and contract['robot'] != robot:
|
| 84 |
+
raise ValueError(f"{checkpoint} was trained for {contract['robot']!r} ({contract['name']}), not {robot!r}")
|
| 85 |
+
self.name, self.contract = name, contract
|
| 86 |
+
self.cameras = tuple(contract['cameras'])
|
| 87 |
+
self.image_hw = tuple(self.config['image_hw'])
|
| 88 |
+
self.horizon = int(self.config['policy']['horizon'])
|
| 89 |
+
self.state_dim, self.action_dim = int(contract['state_dim']), int(contract['action_dim'])
|
| 90 |
+
self.sampling_steps = int(self.model.sampling_steps)
|
| 91 |
+
self.task_text = self.config.get('task_text')
|
| 92 |
+
|
| 93 |
+
def info(self) -> dict:
|
| 94 |
+
return dict(model=self.name, checkpoint=self.checkpoint, step=self.config.get('step'),
|
| 95 |
+
contract=self.contract['name'], views=list(self.cameras), image_hw=list(self.image_hw),
|
| 96 |
+
action_chunk=self.horizon, action_dim=self.action_dim, state_dim=self.state_dim,
|
| 97 |
+
sampling_steps=self.sampling_steps, task_text=self.task_text,
|
| 98 |
+
training_data=self.config.get('dataset', {}).get('name'))
|
| 99 |
+
|
| 100 |
+
def images_tensor(self, images: dict):
|
| 101 |
+
from .data import resize_frame
|
| 102 |
+
missing = [c for c in self.cameras if c not in images]
|
| 103 |
+
if missing:
|
| 104 |
+
raise KeyError(f'missing cameras {missing}; the checkpoint reads {list(self.cameras)}')
|
| 105 |
+
frames = np.stack([resize_frame(np.asarray(images[c]), self.image_hw) for c in self.cameras])
|
| 106 |
+
x = self.torch.from_numpy(frames).to(self.device).permute(0, 3, 1, 2).float().div_(255.)
|
| 107 |
+
return x.unsqueeze(0) # (1, n_cameras, 3, h, w)
|
| 108 |
+
|
| 109 |
+
def predict(self, images: dict, state, seed: int = 0):
|
| 110 |
+
"""(action (horizon, action_dim) float32 physical, normalized (horizon, action_dim) float32)."""
|
| 111 |
+
torch = self.torch
|
| 112 |
+
state = np.asarray(state, np.float32).reshape(-1)
|
| 113 |
+
if state.shape != (self.state_dim,) or not np.isfinite(state).all():
|
| 114 |
+
raise ValueError(f'expected a finite state of {self.state_dim} values, got {state.shape}')
|
| 115 |
+
generator = torch.Generator(device=self.device)
|
| 116 |
+
generator.manual_seed(int(seed) % (2 ** 63 - 1))
|
| 117 |
+
with torch.inference_mode():
|
| 118 |
+
action, raw = self.model.predict(self.images_tensor(images),
|
| 119 |
+
torch.from_numpy(state)[None].to(self.device), generator=generator)
|
| 120 |
+
action = action[0].float().cpu().numpy()
|
| 121 |
+
if action.shape != (self.horizon, self.action_dim) or not np.isfinite(action).all():
|
| 122 |
+
raise ValueError(f'invalid prediction {action.shape}')
|
| 123 |
+
return np.ascontiguousarray(action, np.float32), raw[0].float().cpu().numpy().astype(np.float32)
|