87 lines
2.5 KiB
Python
87 lines
2.5 KiB
Python
#!/usr/bin/env python
|
|
|
|
# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import json
|
|
from copy import deepcopy
|
|
|
|
import torch
|
|
from datasets import Dataset
|
|
from huggingface_hub import DatasetCard
|
|
|
|
from lerobot.common.datasets.push_dataset_to_hub.utils import calculate_episode_data_index
|
|
from lerobot.common.datasets.utils import (
|
|
create_lerobot_dataset_card,
|
|
flatten_dict,
|
|
hf_transform_to_torch,
|
|
unflatten_dict,
|
|
)
|
|
|
|
|
|
def test_default_parameters():
|
|
card = create_lerobot_dataset_card()
|
|
assert isinstance(card, DatasetCard)
|
|
assert card.data.tags == ["LeRobot"]
|
|
assert card.data.task_categories == ["robotics"]
|
|
assert card.data.configs == [
|
|
{
|
|
"config_name": "default",
|
|
"data_files": "data/*/*.parquet",
|
|
}
|
|
]
|
|
|
|
|
|
def test_with_tags():
|
|
tags = ["tag1", "tag2"]
|
|
card = create_lerobot_dataset_card(tags=tags)
|
|
assert card.data.tags == ["LeRobot", "tag1", "tag2"]
|
|
|
|
|
|
def test_calculate_episode_data_index():
|
|
dataset = Dataset.from_dict(
|
|
{
|
|
"timestamp": [0.1, 0.2, 0.3, 0.4, 0.5, 0.6],
|
|
"index": [0, 1, 2, 3, 4, 5],
|
|
"episode_index": [0, 0, 1, 2, 2, 2],
|
|
},
|
|
)
|
|
dataset.set_transform(hf_transform_to_torch)
|
|
episode_data_index = calculate_episode_data_index(dataset)
|
|
assert torch.equal(episode_data_index["from"], torch.tensor([0, 2, 3]))
|
|
assert torch.equal(episode_data_index["to"], torch.tensor([2, 3, 6]))
|
|
|
|
|
|
def test_flatten_unflatten_dict():
|
|
d = {
|
|
"obs": {
|
|
"min": 0,
|
|
"max": 1,
|
|
"mean": 2,
|
|
"std": 3,
|
|
},
|
|
"action": {
|
|
"min": 4,
|
|
"max": 5,
|
|
"mean": 6,
|
|
"std": 7,
|
|
},
|
|
}
|
|
|
|
original_d = deepcopy(d)
|
|
d = unflatten_dict(flatten_dict(d))
|
|
|
|
# test equality between nested dicts
|
|
assert json.dumps(original_d, sort_keys=True) == json.dumps(d, sort_keys=True), f"{original_d} != {d}"
|