CyberDJ commited on
Commit
ea13b78
·
verified ·
1 Parent(s): 7c31a78

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -3
README.md CHANGED
@@ -1,3 +1,39 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
4
+ ---
5
+ license: apache-2.0
6
+ ---
7
+ # Pi05 official implementation trained on VLABench datasets.
8
+ This repository provides the official release of the Pi0 model trained with the whole VLABench's official primitive tasks dataset.
9
+
10
+
11
+ # Evaluation
12
+ To run this checkpoint, please clone this repo: https://github.com/Shiduo-zh/openpi, and checkout to the branch `main`.
13
+ Assume that you download this checkpoints and put it in the directory `checkpoints`, to run the policy as server, please run:
14
+ ```sh
15
+ bash vla_bench_scipts/serve_policy.sh pi0_ft_vlabench_primitive checkpoints/VLABench/pi0-primitive-10task/29999/
16
+ ```
17
+
18
+ After serving the policy, open another terminal and run:
19
+ ```sh
20
+ bash vla_bench_scipts/multi_run_vlabench.sh <Your path to store the evaluate results>
21
+ ```
22
+
23
+ # Train
24
+ To reproduce the training result, please run the training script with the config `pi05_ft_vlabench_primitive`.
25
+ ```sh
26
+ XLA_PYTHON_CLIENT_MEM_FRACTION=0.95 uv run scripts/train.py pi0_ft_vlabench_primitive --exp-name=pi0_ft_vlabench_primitive --overwrite
27
+ ```
28
+
29
+ Our checkpoint is trained on 8 H100 for 30k iterations, with 5000 episodes data acrossing 10 tasks.
30
+
31
+ # Reference Results
32
+ The reference success rate of this model is:
33
+ | Track | add_condiment | insert_flower | select_book | select_chemistry_tube | select_drink | select_fruit | select_mahjong | select_painting | select_poker | select_toy | Avg_SR |
34
+ |----------------------------|---------------|---------------|-----------------|-----------------|--------------------|--------------------|-----------------|-----------------|-------------------|-------------------|--------|
35
+ | track_1_in_distribution | 0.66 | 0.18 | 0.694 | 0.52 | 0.52 | 0.38 | 0.25 | 0.46 | 0.54 | 0.5 | 0.47 |
36
+ | track_2_cross_category | 0.14 | 0.04 | 0.064 | 0.12 | 0.224 | 0.46 | 0.02 | 0.26 | 0.26 | 0.36 | 0.212 |
37
+ | track_3_common_sense | 0.34 | 0.22 | 0.417 | 0.7 | 0.08 | 0.083 | 0.125 | 0.5 | 0.06 | 0.38 | 0.291 |
38
+ | track_4_semantic_instruction | 0.26 | 0.02 | 0.311 | 0.06 | 0.1 | 0.06 | 0.12 | 0.56 | 0.12 | 0.12 | 0.173 |
39
+ | track_6_unseen_texture | 0.56 | 0.1 | 0.714 | 0.28 | 0.44 | 0.30 | 0.02 | 0.3 | 0.28 | 0.18 | 0.322 |