tangger/openpi
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add norm stats reloading documentation

Browse Source
This commit is contained in:
Karl Pertsch
2025-02-27 23:44:56 +00:00
parent d0b6231bd3
commit 42e4838aca
2 changed files with 71 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -148,6 +148,8 @@ XLA_PYTHON_CLIENT_MEM_FRACTION=0.9 uv run scripts/train.py pi0_fast_libero --exp
The command will log training progress to the console and save checkpoints to the `checkpoints` directory. You can also monitor training progress on the Weights & Biases dashboard. For maximally using the GPU memory, set `XLA_PYTHON_CLIENT_MEM_FRACTION=0.9` before running training -- this enables JAX to use up to 90% of the GPU memory (vs. the default of 75%).
**Note:** We provide functionality for *reloading* normalization statistics for state / action normalization from pre-training. This can be beneficial if you are fine-tuning to a new task on a robot that was part of our pre-training mixture. For more details on how to reload normalization statistics, see the [norm_stats.md](docs/norm_stats.md) file.
### 3. Spinning up a policy server and running inference
Once training is complete, we can run inference by spinning up a policy server and then querying it from a Libero evaluation script. Launching a model server is easy (we use the checkpoint for iteration 20,000 for this example, modify as needed):