概要
若想训练自己的场景，数据集的重要性不做过多赘述，下面就基于 robomimic 和 robosuite 构建自己的数据集进行讲解，同时，也会附上 train 和 run 的流程，这样，就形成了闭环。
自建数据集
采集数据
采集数据可使用脚本 collect_human_demonstrations.py 完成,在采集过程中,需要自己定义 env 的相关信息,在实际使用时,存在以下几个问题：
- 无法控制机器人精准的完成抓取工作
- 机器人在某些姿态下,运动会出现漂移的情况
格式转换
该功能脚本为 convert_robosuite.py,在进行执行是:
$ python conversion/convert_robosuite.py --dataset /path/to/demo.hdf5
生成OBS用于训练
python dataset_states_to_obs.py --dataset demo_myliftdraw.hdf5 --output AAA.hdf5
BUG记录
Bug1
在进行 conver_to_robosuite时，也有个小bug，当数据集中 demo数量较少时，比如为1，那么 convert 就会失败，这是因为在进行 split 时数据太少导致的，
"""
Helper script to convert a dataset collected using robosuite into an hdf5 compatible with
this repository. Takes a dataset path corresponding to the demo.hdf5 file containing the
demonstrations. It modifies the dataset in-place. By default, the script also creates a
90-10 train-validation split.
For more information on collecting datasets with robosuite, see the code link and documentation
link below.
Code: https://github.com/ARISE-Initiative/robosuite/blob/offline_study/robosuite/scripts/collect_human_demonstrations.py
Documentation: https://robosuite.ai/docs/algorithms/demonstrations.html
Example usage:
python convert_robosuite.py --dataset /path/to/your/demo.hdf5
"""
import h5py
import json
import argparse
import robomimic.envs.env_base as EB
from robomimic.scripts.split_train_val import split_train_val_from_hdf5
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--dataset",
type=str,
help="path to input hdf5 dataset",
)
args = parser.parse_args()
f = h5py.File(args.dataset, "a") # edit mode
# import ipdb; ipdb.set_trace()
# store env meta
env_name = f["data"].attrs["env"]
env_info = json.loads(f["data"].attrs["env_info"])
env_meta = dict(
type=EB.EnvType.ROBOSUITE_TYPE,
env_name=env_name,
env_version=f["data"].attrs["repository_version"],
env_kwargs=env_info,
)
if "env_args" in f["data"].attrs:
del f["data"].attrs["env_args"]
f["data"].attrs["env_args"] = json.dumps(env_meta, indent=4)
print("====== Stored env meta ======")
print(f["data"].attrs["env_args"])
# store metadata about number of samples
total_samples = 0
for ep in f["data"]:
# ensure model-xml is in per-episode metadata
assert "model_file" in f["data/{}".format(ep)].attrs
# add "num_samples" into per-episode metadata
if "num_samples" in f["data/{}".format(ep)].attrs:
del f["data/{}".format(ep)].attrs["num_samples"]
n_sample = f["data/{}/actions".format(ep)].shape[0]
f["data/{}".format(ep)].attrs["num_samples"] = n_sample
total_samples += n_sample
# add total samples to global metadata
if "total" in f["data"].attrs:
del f["data"].attrs["total"]
f["data"].attrs["total"] = total_samples
f.close()
# create 90-10 train-validation split in the dataset
split_train_val_from_hdf5(hdf5_path=args.dataset, val_ratio=0.1)
最后一行，只需要将 val_ration = 1 就可以了。
Bug2
描述:同样的操作过程,用自己新建的 env环境类生成数据,在进行 obs 生成时报错,但是用官方的 env 是没有问题的
解决方法：不要试图随性构建自己的模型库，因为这玩意是按照固定路径搜索的，坑坑坑，忙了半天，发现是路径的问题，里面有个 robosuite 的固定关键词，这个会影响 to obs 的。
Train && Test
Train 需要调用的脚本是：
$ python robomimic/robomimic/scripts/train.py --config bc_rnn.json
Test调用的脚本为：
$ python robomimic/robomimic/scripts/un_trained_agent.py --agent /path/to/model.pth --n_rollouts 50 --horizon 400 --seed 0 --video_path /path/to/output.mp4 --camera_names agentview robot0_eye_in_hand
在进行训练时，需要对算法进行配置，即导入的 json 文件，以下是一个配置文件的案例，该文件来源于 mimicgen 生成的，其中，里面 有对于算法的部分参数， 比如 "algo_name": "bc",如果功底不够深厚的话，建议大家只改下数据集的 path 就可以了:
{
"algo_name": "bc",
"experiment": {
"name": "source_draw_low_dim",
"validate": false,
"logging": {
"terminal_output_to_txt": true,
"log_tb": true,
"log_wandb": false,
"wandb_proj_name": "debug"
},
"save": {
"enabled": true,
"every_n_seconds": null,
"every_n_epochs": 50,
"epochs": [],
"on_best_validation": false,
"on_best_rollout_return": false,
"on_best_rollout_success_rate": true
},
"epoch_every_n_steps": 100,
"validation_epoch_every_n_steps": 10,
"env": null,
"additional_envs": null,
"render": false,
"render_video": true,
"keep_all_videos": false,
"video_skip": 5,
"rollout": {
"enabled": true,
"n": 50,
"horizon": 400,
"rate": 50,
"warmstart": 0,
"terminate_on_success": true
}
},
"train": {
"data": "/home/idm/Documents/mimicgen/robosuite/robosuite/scripts/generate_dataset/tmp/draw_data/demo_obs.hdf5",
"output_dir": "/home/idm/Documents/mimicgen/robosuite/robosuite/scripts/generate_dataset/tmp/draw_data/trained_models",
"num_data_workers": 0,
"hdf5_cache_mode": "all",
"hdf5_use_swmr": true,
"hdf5_load_next_obs": false,
"hdf5_normalize_obs": false,
"hdf5_filter_key": null,
"hdf5_validation_filter_key": null,
"seq_length": 10,
"pad_seq_length": true,
"frame_stack": 1,
"pad_frame_stack": true,
"dataset_keys": [
"actions",
"rewards",
"dones"
],
"goal_mode": null,
"cuda": true,
"batch_size": 100,
"num_epochs": 2000,
"seed": 1
},
"algo": {
"optim_params": {
"policy": {
"optimizer_type": "adam",
"learning_rate": {
"initial": 0.001,
"decay_factor": 0.1,
"epoch_schedule": [],
"scheduler_type": "multistep"
},
"regularization": {
"L2": 0.0
}
}
},
"loss": {
"l2_weight": 1.0,
"l1_weight": 0.0,
"cos_weight": 0.0
},
"actor_layer_dims": [],
"gaussian": {
"enabled": false,
"fixed_std": false,
"init_std": 0.1,
"min_std": 0.01,
"std_activation": "softplus",
"low_noise_eval": true
},
"gmm": {
"enabled": true,
"num_modes": 5,
"min_std": 0.0001,
"std_activation": "softplus",
"low_noise_eval": true
},
"vae": {
"enabled": false,
"latent_dim": 14,
"latent_clip": null,
"kl_weight": 1.0,
"decoder": {
"is_conditioned": true,
"reconstruction_sum_across_elements": false
},
"prior": {
"learn": false,
"is_conditioned": false,
"use_gmm": false,
"gmm_num_modes": 10,
"gmm_learn_weights": false,
"use_categorical": false,
"categorical_dim": 10,
"categorical_gumbel_softmax_hard": false,
"categorical_init_temp": 1.0,
"categorical_temp_anneal_step": 0.001,
"categorical_min_temp": 0.3
},
"encoder_layer_dims": [
300,
400
],
"decoder_layer_dims": [
300,
400
],
"prior_layer_dims": [
300,
400
]
},
"rnn": {
"enabled": true,
"horizon": 10,
"hidden_dim": 400,
"rnn_type": "LSTM",
"num_layers": 2,
"open_loop": false,
"kwargs": {
"bidirectional": false
}
},
"transformer": {
"enabled": false,
"context_length": 10,
"embed_dim": 512,
"num_layers": 6,
"num_heads": 8,
"emb_dropout": 0.1,
"attn_dropout": 0.1,
"block_output_dropout": 0.1,
"sinusoidal_embedding": false,
"activation": "gelu",
"supervise_all_steps": false,
"nn_parameter_for_timesteps": true
}
},
"observation": {
"modalities": {
"obs": {
"low_dim": [
"robot0_eef_pos",
"robot0_eef_quat",
"robot0_gripper_qpos",
"object"
],
"rgb": [],
"depth": [],
"scan": []
},
"goal": {
"low_dim": [],
"rgb": [],
"depth": [],
"scan": []
}
},
"encoder": {
"low_dim": {
"core_class": null,
"core_kwargs": {},
"obs_randomizer_class": null,
"obs_randomizer_kwargs": {}
},
"rgb": {
"core_class": "VisualCore",
"core_kwargs": {},
"obs_randomizer_class": null,
"obs_randomizer_kwargs": {}
},
"depth": {
"core_class": "VisualCore",
"core_kwargs": {},
"obs_randomizer_class": null,
"obs_randomizer_kwargs": {}
},
"scan": {
"core_class": "ScanCore",
"core_kwargs": {},
"obs_randomizer_class": null,
"obs_randomizer_kwargs": {}
}
}
},
"meta": {
"hp_base_config_file": null,
"hp_keys": [],
"hp_values": []
}
}
部分训练截图如下，可以看出，因数据太少，导致模型不收敛：
参考资料
RoboMimic
