Skip to content

How to fix the bug of loading trained model for evaluation #340

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

How to fix the bug of loading trained model for evaluation #340

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
24dfecf
v0.2.0
puyuan1996 Apr 1, 2025
35d4b1f
Merge branch 'opendilab:main' into main
xiongjyu Apr 2, 2025
f14980e
Merge branch 'opendilab:main' into main
xiongjyu Apr 2, 2025
98c8caa
how to fix the bug of loading trained model for evaluation
xiongjyu Apr 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 10 additions & 4 deletions zoo/jericho/configs/jericho_unizero_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,13 +185,19 @@ def main(env_id: str = 'detective.z5', seed: int = 0, max_env_step: int = int(1e
f"nlayer{num_layers}_embed{embed_dim}_Htrain{num_unroll_steps}-"
f"Hinfer{infer_context_length}_bs{batch_size}_seed{seed}"
)
from lzero.entry import train_unizero
from lzero.entry import train_unizero, eval_muzero
main_config.policy.model_path = '/mnt/afs/niuyazhe/xiongjyu/LightZero/data_lz/data_unizero_jericho/bge-base-en-v1.5/rr_0.1_mtd_F/uz_detectiv_ms50_ass-10_nlayer2_embed768_Htrain10-Hinfer4_bs64_seed0'
# Launch the training process
train_unizero(
# train_unizero(
# [main_config, create_config],
# seed=seed,
# model_path=main_config.policy.model_path,
# max_env_step=max_env_step,
# )
eval_muzero(
[main_config, create_config],
seed=seed,
model_path=main_config.policy.model_path,
max_env_step=max_env_step,
)


Expand Down Expand Up @@ -221,4 +227,4 @@ def main(env_id: str = 'detective.z5', seed: int = 0, max_env_step: int = int(1e
# def run(max_env_step: int):
# main(args.env, args.seed, max_env_step=max_env_step)
# import cProfile
# cProfile.run(f"run({10000})", filename="./zoo/jericho/detective_unizero_cprofile_10k_envstep", sort="cumulative")
# cProfile.run(f"run({10000})", filename="./zoo/jericho/detective_unizero_cprofile_10k_envstep", sort="cumulative")