mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-29 04:36:04 +00:00
3dd19d043e
* feat(depth): add depth quantization helpers and tests
* feat(video): add ffv1 to supported codecs
* feat(depth): persist depth metadata
* feat(depth): extend quantization tools to better fit the encoding/decoding pipeline
* feat(depth): plumb DepthEncoderConfig through LeRobotDataset and DatasetWriter
* feat(depth): wire StreamingVideoEncoder + writer to depth encoder
* feat(depth): wire DatasetReader to decode_depth_frames
* feat(cameras/realsense): expose async depth in metric meters
* feat(features): route 2D camera shapes to observation.depth.<key>
* feat(robots/so_follower): emit + populate depth keys when use_depth
* feat(record): plumb DepthEncoderConfig through lerobot-record
* feat(viz): render depth observations as rr.DepthImage in Viridis
* feat(depth maps writer): adding support for raw depth maps recording with image writer
* chore(format): format code
* feat(depth shape): ensuring depth maps shape is always including the channel
* feat(is_depth): simplifying is_depth nested name + legacy support
* fix(stop_event): fixing stop_event race condition in camera classes
* fix(plumbing): fixing missing parts in the depth maps pipeline
* chore(typos): fixing typos
* test(fix): fixing exisiting tests to still work with latest features
* tests(depth): adding new tests for depth integration validation
* feat(pix_fmt channels): use PyAv to check get pixel formats number of channels
* feat(refactor): refactor DepthEncoderConfig quantization pipeline, so that the methods do not live in the config class. Add pixel format - channels validation.Move the default pixel format for depth in the config file.
* fix(pre-commit): fixing mutable defautl value
* fix(info): fixing info metadata update when is_depth_map was set
* tests(typos): fixing typos in tests
* fix(realsense): fixing typo in realsense serial number
* fix(normalization): restricting 255 normalization to non depth/uint8 images only
* fix(typo): fixing typo
* fix(TIFF): add missing quantization and cleanup for TIFF files
* feat(batched dequantization): optimizing dequantize_depth for torch based batched dequantization
* feat(tools): adding depth support in LeRobotDataset edition tools
* test(aggregate): extending aggregation tests to depth frames
* test(cleaning): cleaning up tests
* fix(from_video_info): fixing early validation issue in from_video_info
* fix(typo): fixing typo
* fix(is_depth): adding missing doctrings and is_depth arguments in video decoding functions
Co-authored-by: Wensi (Vince) Ai <59036629+wensi-ai@users.noreply.github.com>
* fix(depth units): fixing depth units output for the realsense cameras
* feat(output unit): adding support for output unit specification at dataset reading/training time
Co-authored-by: Wensi (Vince) Ai <59036629+wensi-ai@users.noreply.github.com>
* test(depth): cleaning up depth tests
* test(depth encoding): updating and cleaning video/depth encoding tests
* chore(format): formatting code
* docs(depth): improving depth maps docs
* test(fix): fixing depth tests
* test(dataset tools): adding missing tests for new dataset edition tools features
* chore(format): formatting code
* fix(pyav check): fixing PyAV option validation for integer codec options by normalizing
numeric values before calling `is_integer()`
Co-authored-by: Wensi (Vince) Ai <59036629+wensi-ai@users.noreply.github.com>
* docs(mermaid): fixing mermaid diagram
* fix(rebase): rebase follow up corrections
* feat(dataset tools): adding missing docstrings and features for depth fill support in dataset edition tools
* docs(docstring): updating docstrings
* docs(dataset tools): updating docs
* fix(save images): fixing image saving in dataset tools
* fix(update video info): fixing update video info logic to match the recording and editing use cases
* test(reencode): fixing reencoding monkeypatch
* fix(review): add Claude review
* chore(format): format code
* fix(update video info): ditching the differentiated approahces for video info update - video info are always updated unless for preserved keys.
* chore(rebase): fixing rebase merge conflicts
* test(visualization): fixing visualization tests
* feat(docstrings): adding explicit docstring for encoding parameters. Docstrigns will now show up as description in the CLI --help.
* feat(mm as default): adding a global DEFAULT_DEPTH_UNIT variable setting mm as default depth unit
* fix(RGB <-> camera): renaming camera_encoder to rgb_encoder for clarity
* chore(TODO): removing deprecated TODO
* doc(write_u16_plane): improving docstrings for write_u16_plane
* feat(units): adding constants for depth frames units (m and mm)
* fix(spam): replacing spamming warning but a debug log
* feat(leagcy metadata): adding automatic metadata update for legacy 'video.is_depth_map' feature
* fix(copy&reindex): fixing metadat reshaping for single channel frames
* fix(ImageNet): excluding dpeth frames from ImageNet stats
* fix(PyAV container seek): fixing initial PyAV container seek to be robust againsy codec choice
* feat(lerobot-dataset-viz): adding support for depth in lerobot-dataset-viz
* fix(compress): removing rerun compression for DepthImages
* fix(signle channel squeeze): fixing single channel squeezing
* chore(format): format code
* fix(streaming): adding support for dequantization in streaming_dataset.py
* refactor(read depth): factorizing depth reading methods for realsense camera and adding support for depth-only usage
* chore(renaming): fixing missed RGBEncoderConfig renamings
* docs(renaming): reflecting renamings in a clearer way in the docs
* chore(annotation): excluding depth from the annotation pipeline
* feat(robots): adding depth support in compatible follower robots
* feat(LeSadKiwi): excluding LeKiwi from depth support (for now)
* chore(fail): removing misplaced file
* chore(fail): removing misplaced file
* fix(remove ffv1): removing ffv1 as it does not support MP4
* docs(cheat sheet): adding depth and video encoding to the cheat sheet
* fix(lossless): tuning depth encoding parameters for lossless depth storage
* test(fix): fixing failing tests
* depth(ZMQ): excluding ZMQ from depth support
* Revert "depth(ZMQ): excluding ZMQ from depth support"
This reverts commit b95cf4e4c2.
* fix(image transforms): excluding depth frames from images transforms
* fix(typo): typo
* fix(stats): fixing stats computation for depth frames
* fix(TIFF vs. pytorch): adding an extra uint16 to float32 conversion for depth maps stored as raw TIFF images
* fix(typos): fixing typos
* test(dtype): fixing stats computation typing tests
---------
Signed-off-by: Steven Palma <imstevenpmwork@ieee.org>
Co-authored-by: Wensi (Vince) Ai <59036629+wensi-ai@users.noreply.github.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
Co-authored-by: Wensi Ai <wsai@stanford.edu>
77 lines
3.4 KiB
Python
77 lines
3.4 KiB
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.
|
|
|
|
from dataclasses import dataclass
|
|
|
|
from ..configs import CameraConfig, ColorMode, Cv2Rotation
|
|
|
|
|
|
@CameraConfig.register_subclass("intelrealsense")
|
|
@dataclass
|
|
class RealSenseCameraConfig(CameraConfig):
|
|
"""Configuration class for Intel RealSense cameras.
|
|
|
|
This class provides specialized configuration options for Intel RealSense cameras,
|
|
including support for depth sensing and device identification via serial number or name.
|
|
|
|
Example configurations for Intel RealSense D405:
|
|
```python
|
|
# Basic configurations
|
|
RealSenseCameraConfig("0123456789", 30, 1280, 720) # 1280x720 @ 30FPS
|
|
RealSenseCameraConfig("0123456789", 60, 640, 480) # 640x480 @ 60FPS
|
|
|
|
# Advanced configurations
|
|
RealSenseCameraConfig("0123456789", 30, 640, 480, use_depth=True) # With depth sensing
|
|
RealSenseCameraConfig("0123456789", 30, 640, 480, rotation=Cv2Rotation.ROTATE_90) # With 90° rotation
|
|
```
|
|
|
|
Attributes:
|
|
fps: Requested frames per second for the color stream.
|
|
width: Requested frame width in pixels for the color stream.
|
|
height: Requested frame height in pixels for the color stream.
|
|
serial_number_or_name: Unique serial number or human-readable name to identify the camera.
|
|
color_mode: Color mode for image output (RGB or BGR). Defaults to RGB.
|
|
use_rgb: Whether to enable the color stream. Defaults to True.
|
|
use_depth: Whether to enable depth stream. Defaults to False.
|
|
rotation: Image rotation setting (0°, 90°, 180°, or 270°). Defaults to no rotation.
|
|
warmup_s: Time reading frames before returning from connect (in seconds)
|
|
|
|
Note:
|
|
- Either name or serial_number must be specified.
|
|
- At least one of `use_rgb` or `use_depth` must be enabled.
|
|
- Depth stream configuration (if enabled) will use the same FPS as the color stream.
|
|
- The actual resolution and FPS may be adjusted by the camera to the nearest supported mode.
|
|
- For `fps`, `width` and `height`, either all of them need to be set, or none of them.
|
|
"""
|
|
|
|
serial_number_or_name: str
|
|
color_mode: ColorMode = ColorMode.RGB
|
|
use_rgb: bool = True
|
|
use_depth: bool = False
|
|
rotation: Cv2Rotation = Cv2Rotation.NO_ROTATION
|
|
warmup_s: int = 1
|
|
|
|
def __post_init__(self) -> None:
|
|
self.color_mode = ColorMode(self.color_mode)
|
|
self.rotation = Cv2Rotation(self.rotation)
|
|
|
|
if not self.use_rgb and not self.use_depth:
|
|
raise ValueError("At least one of `use_rgb` or `use_depth` must be enabled.")
|
|
|
|
values = (self.fps, self.width, self.height)
|
|
if any(v is not None for v in values) and any(v is None for v in values):
|
|
raise ValueError(
|
|
"For `fps`, `width` and `height`, either all of them need to be set, or none of them."
|
|
)
|