ValueError: Observation Spaces Do Not Match

[KasSkadi]

When running the following command:

python run_sb3_eval.py --save_path "experiments" --agent custom_isp_single_ddpg --model_path "envs/checkpoints/best_model.zip" --isp_inp_original False --param_noise_std 0.02 --target_policy_noise 0.04 --max_step 10 --replay_size 16384 --joint_obs False --truncate_param True --truncate_retouch_mean True --epochs 1000 --train_freq -1 --ema_rate 0.993 --ddpg_gamma 0.90 --loss_type psnr --reward_scale 0.01 --wb_param_dist_mode 1 --isp dataset --eval_use_best_img False --obs_stack_step True --obs_stack_stop True --timestep 800000 --dataset_dir "./datasets"/exp_wb_sat_chs

The following error is raised:

Traceback (most recent call last):
  File "/mnt/c/Projects/RLPixTuner/envs/run_sb3_eval.py", line 292, in <module>
    model = CustomTD3.load(args.model_path, env=eval_env)
  File "/mnt/c/Projects/RLPixTuner/envs/stable_baselines3/common/base_class.py", line 714, in load
    check_for_correct_spaces(env, data["observation_space"], data["action_space"])
  File "/mnt/c/Projects/RLPixTuner/envs/stable_baselines3/common/utils.py", line 229, in check_for_correct_spaces
    raise ValueError(f"Observation spaces do not match: {observation_space} != {env.observation_space}")
ValueError: Observation spaces do not match: Dict('image': Box(0.0, 1.0, (12, 64, 64), float32), 'vector': Box(-1.0, 1.0, (11,), float32)) != Dict('image': Box(0.0, 1.0, (12, 64, 64), float32), 'vector': Box(-1.0, 1.0, (10,), float32))

Any insights or suggestions to resolve this issue would be greatly appreciated! Thank you! 🙏