Skip to content

Command Line Interface

Command-line interface implementation.

dataphy.cli

Dataphy SDK CLI - Modern command-line interface for robotics data management.

Attributes

console = Console() module-attribute

original_make_metavar = click.core.Parameter.make_metavar module-attribute

app = typer.Typer(help='Dataphy SDK CLI - A comprehensive Python SDK for robotics data I/O, dataset management, and augmentation packs', rich_markup_mode=None, invoke_without_command=True, pretty_exceptions_enable=False, add_completion=False) module-attribute

dataset_app = typer.Typer(help='Dataset management commands', rich_markup_mode=None, pretty_exceptions_enable=False, add_completion=False, invoke_without_command=True) module-attribute

augment_app = typer.Typer(help='Augmentation commands', rich_markup_mode=None, pretty_exceptions_enable=False, add_completion=False, invoke_without_command=True) module-attribute

Functions

version_callback(value: bool)

Display version information in a styled panel.

Source code in src/dataphy/cli.py 
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
def version_callback(value: bool):
    """Display version information in a styled panel."""
    if value:
        from rich.console import Console
        from rich.panel import Panel

        # Hardcode version to avoid heavy imports
        __version__ = "0.1.0"

        console = Console()

        # Create the main content
        content = f"""[bold blue]Dataphy SDK v{__version__}[/bold blue]

[white]A comprehensive Python SDK for robotics data I/O, dataset management, and augmentation packs[/white]

[dim]Author:[/dim] [cyan]Dataphy Team[/cyan]
[dim]GitHub:[/dim] [link=https://github.com/dataphy/dataphy-sdk]https://github.com/dataphy/dataphy-sdk[/link]
[dim]Documentation:[/dim] [link=https://docs.dataphy.ai]https://docs.dataphy.ai[/link]

[dim]✨ Features:[/dim] [green]Dataset Loading[/green] • [green]Vision Augmentation[/green] • [green]Multi-Source Data[/green] • [green]CLI Interface[/green]"""

        # Create a panel with the content
        panel = Panel(
            content,
            title="[bold blue]Dataphy[/bold blue]",
            border_style="blue",
            padding=(1, 2)
        )

        console.print(panel)
        raise typer.Exit()

patched_make_metavar(self, ctx=None) -> str

Fixed make_metavar that accepts optional ctx parameter.

This is a compatibility fix for Click/Typer integration issues.

Parameters:

Name Type Description Default
self

The parameter instance

 required
ctx

Optional Click context

 None

Returns:

Type Description
str

The metavar string for the parameter
Source code in src/dataphy/cli.py 
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
def patched_make_metavar(self, ctx=None) -> str:
    """Fixed make_metavar that accepts optional ctx parameter.

    This is a compatibility fix for Click/Typer integration issues.

    Args:
        self: The parameter instance
        ctx: Optional Click context

    Returns:
        The metavar string for the parameter
    """
    if ctx is None:
        # Use a dummy context if none provided
        ctx = click.Context(click.Command('dummy'))
    return original_make_metavar(self, ctx)

main(ctx: typer.Context, help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'))

Dataphy SDK CLI - Modern data toolkit for physical AI.

This is the main entry point for the Dataphy CLI. It provides access to dataset management and augmentation commands through a modern, user-friendly interface.

Parameters:

Name Type Description Default
ctx Context

Typer context for command execution

 required
help_flag bool

Whether to show help information

 Option(False, '--help', '-h', help='Show help message')
Source code in src/dataphy/cli.py 
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
@app.callback(invoke_without_command=True)
def main(
    ctx: typer.Context,
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message")
):
    """Dataphy SDK CLI - Modern data toolkit for physical AI.

    This is the main entry point for the Dataphy CLI. It provides access to
    dataset management and augmentation commands through a modern, user-friendly
    interface.

    Args:
        ctx: Typer context for command execution
        help_flag: Whether to show help information
    """
    if help_flag or ctx.invoked_subcommand is None:
        # Show our fancy help when --help is used or no command is provided
        show_fancy_help()
        raise typer.Exit()

dataset_main(ctx: typer.Context, help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'))

Dataset management commands.

Entry point for dataset-related operations including loading, inspection, and management of robotics datasets.

Parameters:

Name Type Description Default
ctx Context

Typer context for command execution

 required
help_flag bool

Whether to show help information

 Option(False, '--help', '-h', help='Show help message')
Source code in src/dataphy/cli.py 
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
@dataset_app.callback(invoke_without_command=True)
def dataset_main(
    ctx: typer.Context,
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message")
):
    """Dataset management commands.

    Entry point for dataset-related operations including loading, inspection,
    and management of robotics datasets.

    Args:
        ctx: Typer context for command execution
        help_flag: Whether to show help information
    """
    if help_flag or ctx.invoked_subcommand is None:
        show_dataset_help()
        raise typer.Exit()

augment_main(ctx: typer.Context, help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'))

Augmentation commands.

Entry point for augmentation-related operations including applying vision transforms, creating augmentation pipelines, and managing augmentation configurations.

Parameters:

Name Type Description Default
ctx Context

Typer context for command execution

 required
help_flag bool

Whether to show help information

 Option(False, '--help', '-h', help='Show help message')
Source code in src/dataphy/cli.py 
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
@augment_app.callback(invoke_without_command=True)
def augment_main(
    ctx: typer.Context,
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message")
):
    """Augmentation commands.

    Entry point for augmentation-related operations including applying vision
    transforms, creating augmentation pipelines, and managing augmentation
    configurations.

    Args:
        ctx: Typer context for command execution
        help_flag: Whether to show help information
    """
    if help_flag or ctx.invoked_subcommand is None:
        show_augment_help()
        raise typer.Exit()

version()

Show version information.

Displays the current version of the Dataphy SDK with additional information about features and capabilities.

Source code in src/dataphy/cli.py 
160
161
162
163
164
165
166
167
@app.command()
def version():
    """Show version information.

    Displays the current version of the Dataphy SDK with additional
    information about features and capabilities.
    """
    version_callback(True)

show_fancy_help()

Display a modern, styled help menu.

Shows a comprehensive, visually appealing help interface for the Dataphy CLI, including command descriptions, examples, and feature highlights.

Source code in src/dataphy/cli.py 
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
def show_fancy_help():
    """Display a modern, styled help menu.

    Shows a comprehensive, visually appealing help interface for the Dataphy CLI,
    including command descriptions, examples, and feature highlights.
    """
    # Hardcode version to avoid heavy imports
    __version__ = "0.1.0"

    # Main title
    title = Text("🤖 Dataphy SDK CLI", style="bold blue")
    subtitle = Text(f"v{__version__} - Physical AI Data Toolkit", style="dim")

    # Description panel
    desc_panel = Panel(
        "[white]A comprehensive Python SDK for robotics data I/O, dataset management, and augmentation packs.\n"
        "Designed for physical AI applications with LeRobot integration.[/white]",
        title="[bold blue]About[/bold blue]",
        border_style="blue",
        padding=(1, 2)
    )

    # Commands table
    commands_table = Table(show_header=True, header_style="bold magenta", box=None)
    commands_table.add_column("🔧 Command", style="cyan", width=20)
    commands_table.add_column("📝 Description", style="white")
    commands_table.add_column("💡 Example", style="dim yellow")

    commands_table.add_row(
        "dataset fetch",
        "Download datasets from repositories",
        "dataphy dataset fetch --format lerobot --repo-id USER/REPO"
    )
    commands_table.add_row(
        "dataset info", 
        "Get dataset metadata and statistics",
        "dataphy dataset info --format lerobot --repo-id USER/REPO"
    )
    commands_table.add_row(
        "dataset load",
        "Load and inspect dataset contents",
        "dataphy dataset load --dataset-path ./data --episodes 0,1,2"
    )
    commands_table.add_row(
        "dataset visualize",
        "Interactive 2D visualization",
        "dataphy dataset visualize --format lerobot --dataset-path ./data --episodes 0,1,2"
    )
    commands_table.add_row(
        "augment vision",
        "Apply image augmentations",
        "dataphy augment vision --config aug.yaml --input ./images"
    )
    commands_table.add_row(
        "augment dataset",
        "Augment episodes or create augmented datasets",
        "dataphy augment dataset --dataset-path ./data --config aug.yaml --episodes 0,1,2"
    )
    commands_table.add_row(
        "version",
        "Show version information",
        "dataphy version"
    )

    commands_panel = Panel(
        commands_table,
        title="[bold green]📊 Available Commands[/bold green]",
        border_style="green",
        padding=(1, 2)
    )

    # Quick start panel
    quickstart = Text()
    quickstart.append("1. ", style="bold cyan")
    quickstart.append("Install: ", style="white")
    quickstart.append("poetry install --extras rerun\n", style="yellow")
    quickstart.append("2. ", style="bold cyan")
    quickstart.append("Fetch data: ", style="white")
    quickstart.append("dataphy dataset fetch --format lerobot --repo-id carpit680/giraffe_clean_desk2\n", style="yellow")
    quickstart.append("3. ", style="bold cyan")
    quickstart.append("Visualize: ", style="white")
    quickstart.append("dataphy dataset visualize --format lerobot --dataset-path ./dataset --episodes 0,1,2", style="yellow")

    quickstart_panel = Panel(
        quickstart,
        title="[bold yellow]🚀 Quick Start[/bold yellow]",
        border_style="yellow",
        padding=(1, 2)
    )

    # Links panel
    links_table = Table(show_header=False, box=None, padding=(0, 2))
    links_table.add_column("", style="cyan")
    links_table.add_column("", style="blue")

    links_table.add_row("📖 Documentation:", "https://docs.dataphy.ai")
    links_table.add_row("🐙 GitHub:", "https://github.com/dataphy/dataphy-sdk")
    links_table.add_row("💬 Issues:", "https://github.com/dataphy/dataphy-sdk/issues")

    links_panel = Panel(
        links_table,
        title="[bold cyan]🔗 Links[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    # Display everything
    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(desc_panel)
    console.print()
    console.print(commands_panel)
    console.print()
    console.print(quickstart_panel)
    console.print()
    console.print(links_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy COMMAND --help' for detailed command options[/dim]", justify="center")
    console.print()

show_dataset_help()

Display fancy help for dataset commands.

Source code in src/dataphy/cli.py 
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
def show_dataset_help():
    """Display fancy help for dataset commands."""
    # Hardcode version to avoid heavy imports
    __version__ = "0.1.0"

    title = Text("📊 Dataset Management", style="bold green")
    subtitle = Text("Fetch, load, inspect, and visualize robotics datasets", style="dim")

    # Commands table
    commands_table = Table(show_header=True, header_style="bold magenta", box=None)
    commands_table.add_column("🔧 Command", style="cyan", width=15)
    commands_table.add_column("📝 Description", style="white", width=35)
    commands_table.add_column("💡 Example", style="dim yellow")

    commands_table.add_row(
        "fetch",
        "Download datasets from repositories",
        "dataphy dataset fetch --format lerobot --repo-id USER/REPO --output ./data"
    )
    commands_table.add_row(
        "info", 
        "Get dataset metadata and statistics",
        "dataphy dataset info --format lerobot --repo-id USER/REPO"
    )
    commands_table.add_row(
        "load",
        "Load and inspect dataset contents",
        "dataphy dataset load --dataset-path ./data --info"
    )
    commands_table.add_row(
        "list-formats",
        "List all supported dataset formats",
        "dataphy dataset list-formats"
    )
    commands_table.add_row(
        "visualize",
        "Interactive 2D visualization with rerun.io",
        "dataphy dataset visualize --format lerobot --dataset-path ./data"
    )

    commands_panel = Panel(
        commands_table,
        title="[bold green]📊 Dataset Commands[/bold green]",
        border_style="green",
        padding=(1, 2)
    )

    # Usage examples
    examples = Text()
    examples.append("🔹 ", style="cyan")
    examples.append("Fetch LeRobot dataset:\n", style="bold white")
    examples.append("  dataphy dataset fetch --format lerobot --repo-id carpit680/giraffe_clean_desk2 --output ./data\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Load and inspect:\n", style="bold white")
    examples.append("  dataphy dataset load --dataset-path ./data --info\n", style="yellow")
    examples.append("  dataphy dataset load --dataset-path ./data --list-episodes\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Visualize in 2D:\n", style="bold white")
    examples.append("  dataphy dataset visualize --format lerobot --dataset-path ./data", style="yellow")

    examples_panel = Panel(
        examples,
        title="[bold cyan]🚀 Common Usage[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(commands_panel)
    console.print()
    console.print(examples_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy dataset COMMAND --help' for detailed command options[/dim]", justify="center")
    console.print()

show_augment_help()

Display fancy help for augmentation commands.

Source code in src/dataphy/cli.py 
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
def show_augment_help():
    """Display fancy help for augmentation commands."""
    # Hardcode version to avoid heavy imports
    __version__ = "0.1.0"

    title = Text("🎨 Data Augmentation", style="bold yellow")
    subtitle = Text("Apply visual augmentations to images and robotics datasets", style="dim")

    # Commands table
    commands_table = Table(show_header=True, header_style="bold magenta", box=None)
    commands_table.add_column("🔧 Command", style="cyan", width=15)
    commands_table.add_column("📝 Description", style="white", width=35)
    commands_table.add_column("💡 Example", style="dim yellow")

    commands_table.add_row(
        "vision",
        "Apply augmentations to image batches",
        "dataphy augment vision --config aug.yaml --input ./images --preview output.jpg"
    )
    commands_table.add_row(
        "dataset",
        "Augment episodes or entire datasets",
        "dataphy augment dataset --dataset-path ./data --config aug.yaml --episodes 0,1,2"
    )

    commands_panel = Panel(
        commands_table,
        title="[bold yellow]🎨 Augmentation Commands[/bold yellow]",
        border_style="yellow",
        padding=(1, 2)
    )

    # Usage examples
    examples = Text()
    examples.append("🔹 ", style="cyan")
    examples.append("Preview image augmentations:\n", style="bold white")
    examples.append("  dataphy augment vision --config examples/visionpack.yaml --input ./images --preview grid.jpg\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("List available episodes and cameras:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --list-episodes\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Augment episode by name:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --config aug.yaml --episode episode_000000 --cameras observation.images.webcam\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Augment episode by index (0=first episode):\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --config aug.yaml --episode 0 --cameras observation.images.webcam\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Augment all cameras with synchronized views:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --config aug.yaml --episode 0\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Create augmented dataset (3 versions per episode):\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --output-path ./augmented --config aug.yaml --num-augmented 3\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Augment specific episodes only:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --output-path ./aug --config aug.yaml --episodes 0,1,2 --num-augmented 2\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Restore from backup:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --restore episode_000000", style="yellow")

    examples_panel = Panel(
        examples,
        title="[bold cyan]🚀 Common Usage[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(commands_panel)
    console.print()
    console.print(examples_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy augment COMMAND --help' for detailed command options[/dim]", justify="center")
    console.print()

show_fetch_help()

Display fancy help for dataset fetch command.

Source code in src/dataphy/cli.py 
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
def show_fetch_help():
    """Display fancy help for dataset fetch command."""
    title = Text("📥 Dataset Fetch", style="bold green")
    subtitle = Text("Download datasets from various repositories", style="dim")

    # Description panel
    desc = Text()
    desc.append("Download robotics datasets from various sources including Hugging Face Hub, ", style="white")
    desc.append("with support for LeRobot format and flexible filtering options.", style="white")

    desc_panel = Panel(
        desc,
        title="[bold blue]Description[/bold blue]",
        border_style="blue",
        padding=(1, 2)
    )

    # Required arguments
    required_table = Table(show_header=True, header_style="bold red", box=None)
    required_table.add_column("Option", style="cyan", width=15)
    required_table.add_column("Description", style="white", width=40)
    required_table.add_column("Example", style="dim yellow")

    required_table.add_row(
        "--format",
        "Dataset format (currently supports 'lerobot')",
        "--format lerobot"
    )
    required_table.add_row(
        "--output",
        "Local directory to save the downloaded dataset",
        "--output ./my_dataset"
    )

    required_panel = Panel(
        required_table,
        title="[bold red]🔴 Required Options[/bold red]",
        border_style="red",
        padding=(1, 2)
    )

    # Optional arguments
    optional_table = Table(show_header=True, header_style="bold yellow", box=None)
    optional_table.add_column("Option", style="cyan", width=12)
    optional_table.add_column("Description", style="white", width=25)
    optional_table.add_column("Default", style="green", width=18)
    optional_table.add_column("Example", style="dim yellow", width=20)

    optional_table.add_row(
        "--repo-id",
        "Repository ID for the dataset",
        "carpit680/giraffe_clean_desk2",
        "--repo-id user/dataset-name"
    )
    optional_table.add_row(
        "--split",
        "Dataset split to download",
        "train",
        "--split train"
    )

    optional_table.add_row(
        "--revision",
        "Git revision/branch to use",
        "main",
        "--revision v1.0"
    )

    optional_panel = Panel(
        optional_table,
        title="[bold yellow]🟡 Optional Options[/bold yellow]",
        border_style="yellow",
        padding=(1, 2)
    )

    # Examples
    examples = Text()
    examples.append("🔹 ", style="cyan")
    examples.append("Basic LeRobot dataset download:\n", style="bold white")
    examples.append("  dataphy dataset fetch --format lerobot --output ./dataset\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Specific repository:\n", style="bold white")
    examples.append("  dataphy dataset fetch --format lerobot --repo-id carpit680/giraffe_clean_desk2 --output ./giraffe\n\n", style="yellow")



    examples_panel = Panel(
        examples,
        title="[bold cyan]🚀 Usage Examples[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(desc_panel)
    console.print()
    console.print(required_panel)
    console.print()
    console.print(optional_panel)
    console.print()
    console.print(examples_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy dataset --help' to see all dataset commands[/dim]", justify="center")
    console.print()

show_info_help()

Display fancy help for dataset info command.

Source code in src/dataphy/cli.py 
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
def show_info_help():
    """Display fancy help for dataset info command."""
    title = Text("📊 Dataset Info", style="bold blue")
    subtitle = Text("Get dataset metadata and statistics", style="dim")

    # Description panel
    desc = Text()
    desc.append("Retrieve detailed information about datasets from various sources including ", style="white")
    desc.append("Hugging Face Hub repositories and local datasets. Get metadata, statistics, and dataset structure.", style="white")

    desc_panel = Panel(
        desc,
        title="[bold blue]Description[/bold blue]",
        border_style="blue",
        padding=(1, 2)
    )

    # Required arguments
    required_table = Table(show_header=True, header_style="bold red", box=None)
    required_table.add_column("Option", style="cyan", width=15)
    required_table.add_column("Description", style="white", width=45)
    required_table.add_column("Example", style="dim yellow")

    required_table.add_row(
        "--format",
        "Dataset format (lerobot)",
        "--format lerobot"
    )

    required_panel = Panel(
        required_table,
        title="[bold red]🔴 Required Options[/bold red]",
        border_style="red",
        padding=(1, 2)
    )

    # Optional arguments
    optional_table = Table(show_header=True, header_style="bold yellow", box=None)
    optional_table.add_column("Option", style="cyan", width=15)
    optional_table.add_column("Description", style="white", width=40)
    optional_table.add_column("Default", style="green", width=20)
    optional_table.add_column("Example", style="dim yellow", width=20)

    optional_table.add_row(
        "--repo-id",
        "Hugging Face repository ID",
        "None",
        "--repo-id user/dataset"
    )

    optional_table.add_row(
        "--dataset-path",
        "Path to local dataset directory",
        "None",
        "--dataset-path ./dataset"
    )

    optional_panel = Panel(
        optional_table,
        title="[bold yellow]🟡 Optional Options[/bold yellow]",
        border_style="yellow",
        padding=(1, 2)
    )

    # Examples
    examples = Text()
    examples.append("🔹 ", style="cyan")
    examples.append("Get Hugging Face Hub dataset info:\n", style="bold white")
    examples.append("  dataphy dataset info --format lerobot --repo-id carpit680/giraffe_clean_desk2\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Get local dataset info:\n", style="bold white")
    examples.append("  dataphy dataset info --format lerobot --dataset-path ./my_dataset\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Get info for different Hugging Face repository:\n", style="bold white")
    examples.append("  dataphy dataset info --format lerobot --repo-id lerobot/svla_so100_sorting", style="yellow")

    examples_panel = Panel(
        examples,
        title="[bold cyan]🚀 Usage Examples[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(desc_panel)
    console.print()
    console.print(required_panel)
    console.print()
    console.print(optional_panel)
    console.print()
    console.print(examples_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy dataset --help' to see all dataset commands[/dim]", justify="center")
    console.print()

show_load_help()

Display fancy help for dataset load command.

Source code in src/dataphy/cli.py 
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
def show_load_help():
    """Display fancy help for dataset load command."""
    title = Text("📁 Dataset Load", style="bold green")
    subtitle = Text("Load and inspect dataset contents", style="dim")

    # Description panel
    desc = Text()
    desc.append("Load and inspect datasets from local directories. View dataset information, ", style="white")
    desc.append("list episodes, and examine specific episodes or timesteps.", style="white")

    desc_panel = Panel(
        desc,
        title="[bold blue]Description[/bold blue]",
        border_style="blue",
        padding=(1, 2)
    )

    # Required arguments
    required_table = Table(show_header=True, header_style="bold red", box=None)
    required_table.add_column("Option", style="cyan", width=15)
    required_table.add_column("Description", style="white", width=45)
    required_table.add_column("Example", style="dim yellow")

    required_table.add_row(
        "--dataset-path",
        "Path to dataset directory",
        "--dataset-path ./data"
    )

    required_panel = Panel(
        required_table,
        title="[bold red]🔴 Required Options[/bold red]",
        border_style="red",
        padding=(1, 2)
    )

    # Optional arguments
    optional_table = Table(show_header=True, header_style="bold yellow", box=None)
    optional_table.add_column("Option", style="cyan", width=15)
    optional_table.add_column("Description", style="white", width=35)
    optional_table.add_column("Default", style="green", width=15)
    optional_table.add_column("Example", style="dim yellow", width=20)

    optional_table.add_row(
        "--format",
        "Dataset format (auto-detected)",
        "auto",
        "--format lerobot"
    )
    optional_table.add_row(
        "--info",
        "Show dataset information",
        "False",
        "--info"
    )
    optional_table.add_row(
        "--list-episodes",
        "List available episodes",
        "False",
        "--list-episodes"
    )
    optional_table.add_row(
        "--episode",
        "Load specific episode (name or index)",
        "None",
        "--episode 0"
    )
    optional_table.add_row(
        "--episodes",
        "Load multiple episodes (comma-separated)",
        "None",
        "--episodes 0,1,2"
    )
    optional_table.add_row(
        "--timestep",
        "Load specific timestep (requires --episode)",
        "None",
        "--timestep 100"
    )

    optional_panel = Panel(
        optional_table,
        title="[bold yellow]🟡 Optional Options[/bold yellow]",
        border_style="yellow",
        padding=(1, 2)
    )

    # Examples
    examples = Text()
    examples.append("🔹 ", style="cyan")
    examples.append("Show dataset information:\n", style="bold white")
    examples.append("  dataphy dataset load --dataset-path ./data --info\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("List all episodes:\n", style="bold white")
    examples.append("  dataphy dataset load --dataset-path ./data --list-episodes\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Load specific episode by index:\n", style="bold white")
    examples.append("  dataphy dataset load --dataset-path ./data --episode 0\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Load multiple episodes:\n", style="bold white")
    examples.append("  dataphy dataset load --dataset-path ./data --episodes 0,1,2\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Load episodes by name:\n", style="bold white")
    examples.append("  dataphy dataset load --dataset-path ./data --episodes episode_000000,episode_000001\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Load specific timestep:\n", style="bold white")
    examples.append("  dataphy dataset load --dataset-path ./data --episode 5 --timestep 100", style="yellow")

    examples_panel = Panel(
        examples,
        title="[bold cyan]🚀 Usage Examples[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(desc_panel)
    console.print()
    console.print(required_panel)
    console.print()
    console.print(optional_panel)
    console.print()
    console.print(examples_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy dataset --help' to see all dataset commands[/dim]", justify="center")
    console.print()

show_visualize_help()

Display fancy help for dataset visualize command.

Source code in src/dataphy/cli.py 
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
def show_visualize_help():
    """Display fancy help for dataset visualize command."""
    title = Text("🎬 Dataset Visualize", style="bold magenta")
    subtitle = Text("Interactive 2D visualization with rerun.io", style="dim")

    # Description panel
    desc = Text()
    desc.append("Visualize robotics datasets using interactive 2D viewers powered by rerun.io. ", style="white")
    desc.append("View camera feeds, robot actions, and state data in real-time.", style="white")

    desc_panel = Panel(
        desc,
        title="[bold blue]Description[/bold blue]",
        border_style="blue",
        padding=(1, 2)
    )

    # Required arguments
    required_table = Table(show_header=True, header_style="bold red", box=None)
    required_table.add_column("Option", style="cyan", width=15)
    required_table.add_column("Description", style="white", width=45)
    required_table.add_column("Example", style="dim yellow")

    required_table.add_row(
        "--format",
        "Dataset format (lerobot)",
        "--format lerobot"
    )

    required_panel = Panel(
        required_table,
        title="[bold red]🔴 Required Options[/bold red]",
        border_style="red",
        padding=(1, 2)
    )

    # Optional arguments
    optional_table = Table(show_header=True, header_style="bold yellow", box=None)
    optional_table.add_column("Option", style="cyan", width=15)
    optional_table.add_column("Description", style="white", width=35)
    optional_table.add_column("Default", style="green", width=15)
    optional_table.add_column("Example", style="dim yellow", width=20)

    optional_table.add_row(
        "--dataset-path",
        "Path to dataset directory",
        "None",
        "--dataset-path ./data"
    )
    optional_table.add_row(
        "--repo-id",
        "Hugging Face repository ID",
        "None",
        "--repo-id user/dataset"
    )
    optional_table.add_row(
        "--episode",
        "Specific episode ID to visualize",
        "None",
        "--episode episode_000000"
    )
    optional_table.add_row(
        "--episodes",
        "Multiple episodes to visualize (comma-separated)",
        "None",
        "--episodes 0,1,2"
    )
    optional_table.add_row(
        "--timestep-range",
        "Timestep range as 'start,end'",
        "all timesteps",
        "--timestep-range 0,100"
    )
    optional_table.add_row(
        "--camera",
        "Camera name to visualize",
        "all cameras",
        "--camera observation.images.laptop"
    )

    optional_panel = Panel(
        optional_table,
        title="[bold yellow]🟡 Optional Options[/bold yellow]",
        border_style="yellow",
        padding=(1, 2)
    )

    # Examples
    examples = Text()
    examples.append("🔹 ", style="cyan")
    examples.append("Visualize local dataset:\n", style="bold white")
    examples.append("  dataphy dataset visualize --format lerobot --dataset-path ./data\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Visualize from repository:\n", style="bold white")
    examples.append("  dataphy dataset visualize --format lerobot --repo-id carpit680/giraffe_clean_desk2\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Visualize specific episode:\n", style="bold white")
    examples.append("  dataphy dataset visualize --format lerobot --dataset-path ./data --episode episode_000000\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Visualize multiple episodes:\n", style="bold white")
    examples.append("  dataphy dataset visualize --format lerobot --dataset-path ./data --episodes 0,1,2\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Visualize timestep range:\n", style="bold white")
    examples.append("  dataphy dataset visualize --format lerobot --dataset-path ./data --timestep-range 0,100", style="yellow")

    examples_panel = Panel(
        examples,
        title="[bold cyan]🚀 Usage Examples[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(desc_panel)
    console.print()
    console.print(required_panel)
    console.print()
    console.print(optional_panel)
    console.print()
    console.print(examples_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy dataset --help' to see all dataset commands[/dim]", justify="center")
    console.print()

show_vision_help()

Display fancy help for augment vision command.

Source code in src/dataphy/cli.py 
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
def show_vision_help():
    """Display fancy help for augment vision command."""
    title = Text("🎨 Vision Augmentation", style="bold yellow")
    subtitle = Text("Apply image augmentations to batches of images", style="dim")

    # Description panel
    desc = Text()
    desc.append("Apply VisionPack augmentation pipelines to images with GPU acceleration. ", style="white")
    desc.append("Generate preview grids or process entire image datasets with configurable transforms.", style="white")

    desc_panel = Panel(
        desc,
        title="[bold blue]Description[/bold blue]",
        border_style="blue",
        padding=(1, 2)
    )

    # Required arguments
    required_table = Table(show_header=True, header_style="bold red", box=None)
    required_table.add_column("Option", style="cyan", width=15)
    required_table.add_column("Description", style="white", width=45)
    required_table.add_column("Example", style="dim yellow")

    required_table.add_row(
        "--config",
        "VisionPack YAML configuration file with augmentation pipeline",
        "--config examples/visionpack.yaml"
    )
    required_table.add_row(
        "--input",
        "Input source: directory, file",
        "--input ./images"
    )

    required_panel = Panel(
        required_table,
        title="[bold red]🔴 Required Options[/bold red]",
        border_style="red",
        padding=(1, 2)
    )

    # Optional arguments
    optional_table = Table(show_header=True, header_style="bold yellow", box=None)
    optional_table.add_column("Option", style="cyan", width=12)
    optional_table.add_column("Description", style="white", width=25)
    optional_table.add_column("Default", style="green", width=10)
    optional_table.add_column("Example", style="dim yellow", width=20)

    optional_table.add_row(
        "--output",
        "Output destination",
        "None",
        "--output ./augmented"
    )
    optional_table.add_row(
        "--preview",
        "Save preview grid image",
        "None",
        "--preview grid.jpg"
    )
    optional_table.add_row(
        "--seed",
        "Random seed",
        "1337",
        "--seed 42"
    )
    optional_table.add_row(
        "--device",
        "Processing device",
        "cuda",
        "--device cpu"
    )
    optional_table.add_row(
        "--batch-size",
        "Batch size for processing",
        "64",
        "--batch-size 32"
    )

    optional_panel = Panel(
        optional_table,
        title="[bold yellow]🟡 Optional Options[/bold yellow]",
        border_style="yellow",
        padding=(1, 2)
    )

    # Examples
    examples = Text()
    examples.append("🔹 ", style="cyan")
    examples.append("Generate preview grid:\n", style="bold white")
    examples.append("  dataphy augment vision --config aug.yaml --input ./images --preview grid.jpg\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Process images to output directory:\n", style="bold white")
    examples.append("  dataphy augment vision --config aug.yaml --input ./images --output ./augmented\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Custom settings:\n", style="bold white")
    examples.append("  dataphy augment vision --config aug.yaml --input ./images --device cpu --seed 42", style="yellow")

    examples_panel = Panel(
        examples,
        title="[bold cyan]🚀 Usage Examples[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(desc_panel)
    console.print()
    console.print(required_panel)
    console.print()
    console.print(optional_panel)
    console.print()
    console.print(examples_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy augment --help' to see all augment commands[/dim]", justify="center")
    console.print()

show_augment_dataset_help()

Display fancy help for augment dataset command.

Source code in src/dataphy/cli.py 
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
def show_augment_dataset_help():
    """Display fancy help for augment dataset command."""
    title = Text("🏭 Dataset Augmentation", style="bold magenta")
    subtitle = Text("Augment episodes or entire datasets with VisionPack transforms", style="dim")

    # Description panel
    desc = Text()
    desc.append("Apply VisionPack augmentation pipelines to robotics datasets with two modes: ", style="white")
    desc.append("Episode Mode (in-place) and Full Dataset Mode (new dataset). ", style="white")
    desc.append("Supports LeRobot format with automatic metadata updates.", style="white")

    desc_panel = Panel(
        desc,
        title="[bold blue]Description[/bold blue]",
        border_style="blue",
        padding=(1, 2)
    )

    # Modes table
    modes_table = Table(show_header=True, header_style="bold cyan", box=None)
    modes_table.add_column("Mode", style="cyan", width=15)
    modes_table.add_column("Trigger", style="yellow", width=20)
    modes_table.add_column("Description", style="white", width=50)

    modes_table.add_row(
        "Episode Mode",
        "--episode/--episodes",
        "Augment specific episodes in-place with backups"
    )
    modes_table.add_row(
        "Full Dataset Mode",
        "No episode selection",
        "Create new augmented dataset at --output-path"
    )

    modes_panel = Panel(
        modes_table,
        title="[bold cyan]🎯 Operation Modes[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    # Required arguments
    required_table = Table(show_header=True, header_style="bold red", box=None)
    required_table.add_column("Option", style="cyan", width=15)
    required_table.add_column("Description", style="white", width=45)
    required_table.add_column("Example", style="dim yellow")

    required_table.add_row(
        "--dataset-path",
        "Path to dataset directory",
        "--dataset-path ./my_dataset"
    )

    required_panel = Panel(
        required_table,
        title="[bold red]🔴 Required Options[/bold red]",
        border_style="red",
        padding=(1, 2)
    )

    # Episode selection options
    episode_table = Table(show_header=True, header_style="bold green", box=None)
    episode_table.add_column("Option", style="cyan", width=15)
    episode_table.add_column("Description", style="white", width=40)
    episode_table.add_column("Example", style="dim yellow")

    episode_table.add_row(
        "--episode",
        "Single episode (name or index)",
        "--episode 0 or --episode episode_000000"
    )
    episode_table.add_row(
        "--episodes",
        "Multiple episodes (comma-separated)",
        "--episodes 0,1,2 or --episodes episode_000000,episode_000001"
    )

    episode_panel = Panel(
        episode_table,
        title="[bold green]🎬 Episode Selection[/bold green]",
        border_style="green",
        padding=(1, 2)
    )

    # Output options
    output_table = Table(show_header=True, header_style="bold yellow", box=None)
    output_table.add_column("Option", style="cyan", width=15)
    output_table.add_column("Description", style="white", width=30)
    output_table.add_column("Default", style="green", width=15)
    output_table.add_column("Example", style="dim yellow")

    output_table.add_row(
        "--output-path",
        "Output directory (full dataset mode)",
        "./augmented",
        "--output-path ./new_dataset"
    )
    output_table.add_row(
        "--num-augmented",
        "Augmented versions per episode",
        "1",
        "--num-augmented 3"
    )
    output_table.add_row(
        "--preserve-original",
        "Include original episodes",
        "True",
        "--preserve-original"
    )

    output_panel = Panel(
        output_table,
        title="[bold yellow]📁 Output Options[/bold yellow]",
        border_style="yellow",
        padding=(1, 2)
    )

    # Examples
    examples = Text()
    examples.append("🔹 ", style="cyan")
    examples.append("Episode Mode - Augment single episode:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --episode 0 --config aug.yaml\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Episode Mode - Augment multiple episodes:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --episodes 0,1,2 --config aug.yaml\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("Full Dataset Mode - Create augmented dataset:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --config aug.yaml --num-augmented 3\n\n", style="yellow")

    examples.append("🔹 ", style="cyan")
    examples.append("With camera selection and sync:\n", style="bold white")
    examples.append("  dataphy augment dataset --dataset-path ./data --episode 0 --cameras observation.images.webcam --sync-views\n\n", style="yellow")

    examples_panel = Panel(
        examples,
        title="[bold cyan]🚀 Usage Examples[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(desc_panel)
    console.print()
    console.print(modes_panel)
    console.print()
    console.print(required_panel)
    console.print()
    console.print(episode_panel)
    console.print()
    console.print(output_panel)
    console.print()
    console.print(examples_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy augment dataset --help' for detailed command options[/dim]", justify="center")
    console.print()

show_list_formats_help()

Display fancy help for list-formats command.

Source code in src/dataphy/cli.py 
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
def show_list_formats_help():
    """Display fancy help for list-formats command."""
    title = Text("🗂️  Dataset Formats", style="bold blue")
    subtitle = Text("List all supported dataset formats and their descriptions", style="dim")

    # Description panel
    desc = Text()
    desc.append("Display all supported dataset formats with descriptions and example usage. ", style="white")
    desc.append("This helps you understand which formats are available for dataset operations.", style="white")

    desc_panel = Panel(
        desc,
        title="[bold blue]Description[/bold blue]",
        border_style="blue",
        padding=(1, 2)
    )

    # Usage
    usage = Text()
    usage.append("🔹 ", style="cyan")
    usage.append("List all formats:\n", style="bold white")
    usage.append("  dataphy dataset list-formats\n\n", style="yellow")

    usage.append("🔹 ", style="cyan")
    usage.append("Use with other commands:\n", style="bold white")
    usage.append("  dataphy dataset load --format lerobot --dataset-path ./data\n", style="yellow")
    usage.append("  dataphy dataset fetch --format lerobot --repo-id user/dataset\n", style="yellow")

    usage_panel = Panel(
        usage,
        title="[bold cyan]🚀 Usage[/bold cyan]",
        border_style="cyan",
        padding=(1, 2)
    )

    console.print()
    console.print(title, justify="center")
    console.print(subtitle, justify="center")
    console.print()
    console.print(desc_panel)
    console.print()
    console.print(usage_panel)
    console.print()
    console.print("[dim]💡 Use 'dataphy dataset list-formats --help' for detailed command options[/dim]", justify="center")
    console.print()

augment_vision(help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'), config: str = typer.Option(None, '--config', help='VisionPack YAML config'), input_path: str = typer.Option(None, '--input', help='Input source URI (dir, file)'), output_path: str = typer.Option(None, '--output', help='Output sink URI (dir)'), seed: int = typer.Option(1337, '--seed', help='Global seed'), batch_size: int = typer.Option(64, '--batch-size'), num_workers: int = typer.Option(8, '--num-workers'), device: str = typer.Option('cuda', '--device'), preview: str = typer.Option(None, '--preview', help='Write preview grid image to path'), limit: int = typer.Option(0, '--limit', help='Process first N batches only (0=all)'))

Source code in src/dataphy/cli.py 
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
@augment_app.command("vision")
def augment_vision(
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message"),
    config: str = typer.Option(None, "--config", help="VisionPack YAML config"),
    input_path: str = typer.Option(None, "--input", help="Input source URI (dir, file)"),
    output_path: str = typer.Option(None, "--output", help="Output sink URI (dir)"),
    seed: int = typer.Option(1337, "--seed", help="Global seed"),
    batch_size: int = typer.Option(64, "--batch-size"),
    num_workers: int = typer.Option(8, "--num-workers"),
    device: str = typer.Option("cuda", "--device"),
    preview: str = typer.Option(None, "--preview", help="Write preview grid image to path"),
    limit: int = typer.Option(0, "--limit", help="Process first N batches only (0=all)"),
):
    if help_flag:
        show_vision_help()
        raise typer.Exit()

    # Validate required parameters
    if not config:
        console.print("[red]❌ Error:[/red] --config is required")
        console.print("[dim]💡 Use 'dataphy augment vision --help' for help[/dim]")
        raise typer.Exit(code=1)

    if not input_path:
        console.print("[red]❌ Error:[/red] --input is required")
        console.print("[dim]💡 Use 'dataphy augment vision --help' for help[/dim]")
        raise typer.Exit(code=1)

    # Lazy imports for heavy dependencies
    from dataphy.visionpack.pipeline import build_pipeline
    from dataphy.io.loader import load_batches

    pipe = build_pipeline(config, device=device, seed=seed)
    batches = load_batches(input_path, batch_size=batch_size, num_workers=num_workers)

    if preview:
        # take one batch, run pipe, write grid
        import numpy as np
        from PIL import Image
        b = next(iter(batches))
        out = pipe(b)
        grid = _make_grid(out["images"])  # images: BxCxHxW [0..1]
        Image.fromarray((grid * 255).astype(np.uint8)).save(preview)

        # Fancy success message
        success_panel = Panel(
            f"[green]✅ Preview saved successfully![/green]\n[white]Location:[/white] [cyan]{preview}[/cyan]",
            title="[bold green]🎨 Vision Augmentation Preview[/bold green]",
            border_style="green"
        )
        console.print(success_panel)
        raise typer.Exit()

    if not output_path:
        ok = Confirm.ask("No --output provided. Stream to /dev/null?", default=False)
        if not ok:
            raise typer.Exit(code=1)

    # Lazy import for write_batches
    from dataphy.io.writer import write_batches

    write_batches(batches, pipe, output_path, limit=limit)
    console.print("[green]✅ Done[/green]")

dataset_fetch(help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'), dataset_format: str = typer.Option(None, '--format', help='Dataset format (lerobot)'), repo_id: str = typer.Option('carpit680/giraffe_clean_desk2', '--repo-id', help='Repository ID (for lerobot format)'), split: str = typer.Option('train', '--split', help='Dataset split (train, val, test)'), output: str = typer.Option(None, '--output', help='Local output directory'), revision: str = typer.Option('main', '--revision', help='Git revision'))

Fetch datasets from various sources.

Source code in src/dataphy/cli.py 
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
@dataset_app.command("fetch")
def dataset_fetch(
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message"),
    dataset_format: str = typer.Option(None, "--format", help="Dataset format (lerobot)"),
    repo_id: str = typer.Option("carpit680/giraffe_clean_desk2", "--repo-id", help="Repository ID (for lerobot format)"),
    split: str = typer.Option("train", "--split", help="Dataset split (train, val, test)"),
    output: str = typer.Option(None, "--output", help="Local output directory"),
    revision: str = typer.Option("main", "--revision", help="Git revision"),
):
    """Fetch datasets from various sources."""
    if help_flag:
        show_fetch_help()
        raise typer.Exit()

    # Validate required parameters
    if not dataset_format:
        console.print("[red]Error:[/red] --format is required")
        console.print("[dim]Use 'dataphy dataset fetch --help' for help[/dim]")
        raise typer.Exit(code=1)

    if not output:
        console.print("[red]Error:[/red] --output is required")
        console.print("[dim]Use 'dataphy dataset fetch --help' for help[/dim]")
        raise typer.Exit(code=1)

    if dataset_format.lower() == "lerobot":
        try:
            from dataphy.sources.lerobot import fetch, RepositoryNotFoundError, RevisionNotFoundError, NetworkError
            source = {
                "repo_id": repo_id,
                "split": split,
                "revision": revision,
            }
            result = fetch(source=source, output_dir=output, runner="DirectRunner")
            console.print(f"[green]LeRobot dataset fetched to[/green] {result}")
        except ImportError:
            console.print("[red]Error:[/red] huggingface_hub not installed. Install with: pip install huggingface_hub")
            raise typer.Exit(code=1)
        except RepositoryNotFoundError as e:
            console.print(f"[red]Repository not found:[/red] {e}")
            console.print("[yellow]Tip:[/yellow] Check that the repository ID is correct and the repository exists on Hugging Face Hub")
            console.print(f"[dim]Repository ID:[/dim] {repo_id}")
            console.print("[yellow]Common solutions:[/yellow]")
            console.print("  • Verify the repository ID format: 'username/repository-name'")
            console.print("  • Check if the repository is public or you have access to it")
            console.print("  • Try browsing to https://huggingface.co/{repo_id} in your browser")
            raise typer.Exit(code=1)
        except RevisionNotFoundError as e:
            console.print(f"[red]Revision not found:[/red] {e}")
            console.print("[yellow]Tip:[/yellow] Check that the revision exists in the repository")
            console.print(f"[dim]Repository ID:[/dim] {repo_id}")
            console.print(f"[dim]Revision:[/dim] {revision}")
            raise typer.Exit(code=1)
        except NetworkError as e:
            console.print(f"[red]Network error:[/red] {e}")
            console.print("[yellow]Tip:[/yellow] Check your internet connection and try again")
            raise typer.Exit(code=1)
        except PermissionError as e:
            console.print(f"[red]Permission denied:[/red] {e}")
            console.print("[yellow]Tip:[/yellow] The repository might be private. Check if you have access to it")
            raise typer.Exit(code=1)
        except Exception as e:
            console.print(f"[red]Unexpected error:[/red] {e}")
            console.print("[yellow]Tip:[/yellow] Check the repository ID and try again")
            raise typer.Exit(code=1)
    else:
        console.print(f"[red]Error:[/red] Unsupported format '{format}'. Supported formats: lerobot")
        raise typer.Exit(code=1)

dataset_info(help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'), format: str = typer.Option(None, '--format', help='Dataset format (lerobot)'), dataset_path: str = typer.Option(None, '--dataset-path', help='Path to dataset directory'), repo_id: str = typer.Option(None, '--repo-id', help='Hugging Face repository ID (for lerobot format)'))

Get information about datasets from various sources.

Source code in src/dataphy/cli.py 
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
@dataset_app.command("info")
def dataset_info(
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message"),
    format: str = typer.Option(None, "--format", help="Dataset format (lerobot)"),
    dataset_path: str = typer.Option(None, "--dataset-path", help="Path to dataset directory"),
    repo_id: str = typer.Option(None, "--repo-id", help="Hugging Face repository ID (for lerobot format)"),
):
    """Get information about datasets from various sources."""
    if help_flag:
        show_info_help()
        raise typer.Exit()

    if not format:
        console.print("[red]Error:[/red] --format is required")
        console.print("[dim]Use 'dataphy dataset info --help' for help[/dim]")
        raise typer.Exit(code=1)

    if not dataset_path and not repo_id:
        console.print("[red]Error:[/red] Either --dataset-path or --repo-id is required")
        console.print("[dim]Use 'dataphy dataset info --help' for help[/dim]")
        raise typer.Exit(code=1)

    if dataset_path and repo_id:
        console.print("[red]Error:[/red] Cannot specify both --dataset-path and --repo-id")
        console.print("[dim]Use 'dataphy dataset info --help' for help[/dim]")
        raise typer.Exit(code=1)

    if format.lower() == "lerobot":
        if repo_id:
            # Handle Hugging Face Hub dataset
            try:
                from dataphy.sources.lerobot import get_dataset_info, RepositoryNotFoundError, RevisionNotFoundError, NetworkError
                # Extract dataset name from repo_id (e.g., "lerobot/lerobot-100k" -> "lerobot-100k")
                dataset_name = repo_id.split("/")[-1]
                info = get_dataset_info(repo_id, dataset_name)
                if info:
                    console.print(f"[green]Dataset info for {repo_id}:[/green]")
                    print(f"  Available splits: {', '.join(info['available_splits'])}")
                    print(f"  File types: {', '.join(info['file_types'])}")
                    print(f"  Total files: {info['total_files']}")

                    # Display detailed information if available
                    if info.get('detailed_info'):
                        detailed = info['detailed_info']
                        console.print("\n[blue]Detailed Information:[/blue]")
                        print(f"  Robot type: {detailed.get('robot_type', 'N/A')}")
                        print(f"  Total episodes: {detailed.get('total_episodes', 'N/A')}")
                        print(f"  Total frames: {detailed.get('total_frames', 'N/A')}")
                        print(f"  Total videos: {detailed.get('total_videos', 'N/A')}")
                        print(f"  FPS: {detailed.get('fps', 'N/A')}")
                        print(f"  Codebase version: {detailed.get('codebase_version', 'N/A')}")

                        # Show available features
                        if detailed.get('features'):
                            print(f"  Available features: {', '.join(detailed['features'].keys())}")
                else:
                    console.print(f"[red]Error:[/red] Could not retrieve dataset info for {repo_id}")
                    raise typer.Exit(code=1)
            except ImportError:
                console.print("[red]Error:[/red] huggingface_hub not installed. Install with: pip install huggingface_hub")
                raise typer.Exit(code=1)
            except RepositoryNotFoundError as e:
                console.print(f"[red]Repository not found:[/red] {e}")
                console.print("[yellow]Tip:[/yellow] Check that the repository ID is correct and the repository exists on Hugging Face Hub")
                console.print(f"[dim]Repository ID:[/dim] {repo_id}")
                console.print("[yellow]Common solutions:[/yellow]")
                console.print("  • Verify the repository ID format: 'username/repository-name'")
                console.print("  • Check if the repository is public or you have access to it")
                console.print("  • Try browsing to https://huggingface.co/{repo_id} in your browser")
                raise typer.Exit(code=1)
            except NetworkError as e:
                console.print(f"[red]Network error:[/red] {e}")
                console.print("[yellow]Tip:[/yellow] Check your internet connection and try again")
                raise typer.Exit(code=1)
            except PermissionError as e:
                console.print(f"[red]Permission denied:[/red] {e}")
                console.print("[yellow]Tip:[/yellow] The repository might be private. Check if you have access to it")
                raise typer.Exit(code=1)
            except Exception as e:
                console.print(f"[red]Unexpected error:[/red] {e}")
                console.print("[yellow]Tip:[/yellow] Check the repository ID and try again")
                raise typer.Exit(code=1)
        else:
            # Handle local dataset
            try:
                from dataphy.dataset.registry import DatasetFormat, create_dataset_loader
                from pathlib import Path

                # Validate dataset path exists
                if not Path(dataset_path).exists():
                    console.print(f"[red]Error:[/red] Dataset path not found: {dataset_path}")
                    raise typer.Exit(code=1)

                # Create dataset loader
                loader = create_dataset_loader(dataset_path, format_type=DatasetFormat.LEROBOT)

                # Get dataset information
                dataset_info = loader.get_dataset_info()
                episodes = loader.get_episode_ids()

                console.print(f"[green]Dataset info for {dataset_path}:[/green]")
                print(f"  Format: {dataset_info.get('format', 'Unknown')}")
                print(f"  Total episodes: {len(episodes)}")
                print(f"  Total timesteps: {dataset_info.get('total_timesteps', 'Unknown')}")

                if dataset_info.get('features'):
                    print(f"  Features: {', '.join(dataset_info['features'])}")

                # Show sample episodes
                if episodes:
                    sample_episodes = episodes[:5]
                    print(f"  Sample episodes: {', '.join(sample_episodes)}")
                    if len(episodes) > 5:
                        print(f"  ... and {len(episodes) - 5} more episodes")

                # Show detailed information if available
                if hasattr(dataset_info, 'metadata') and dataset_info.metadata:
                    console.print("\n[blue]Detailed Information:[/blue]")
                    metadata = dataset_info.metadata
                    print(f"  Robot type: {metadata.get('robot_type', 'N/A')}")
                    print(f"  Codebase version: {metadata.get('codebase_version', 'N/A')}")
                    print(f"  FPS: {metadata.get('fps', 'N/A')}")

                    # Show available features
                    if metadata.get('features'):
                        print(f"  Available features: {', '.join(metadata['features'].keys())}")

            except Exception as e:
                console.print(f"[red]Error:[/red] Could not load dataset info: {e}")
                console.print("[yellow]Tip:[/yellow] Check that the dataset path is valid and contains a LeRobot dataset")
                raise typer.Exit(code=1)
    else:
        console.print(f"[red]❌ Error:[/red] Unsupported format '{format}'. Supported formats: lerobot")
        raise typer.Exit(code=1)

dataset_load(help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'), dataset_path: str = typer.Option(None, '--dataset-path', help='Path to dataset directory'), format: str = typer.Option(None, '--format', help='Dataset format (auto-detected if not specified)'), info: bool = typer.Option(False, '--info', help='Show dataset information'), list_episodes: bool = typer.Option(False, '--list-episodes', help='List available episodes'), episode: str = typer.Option(None, '--episode', help="Load specific episode (name: 'episode_000000' or index: '0', '1', '2'...)"), episodes: str = typer.Option(None, '--episodes', help="Load multiple episodes (comma-separated, e.g., '0,1,2' or 'episode_000000,episode_000001')"), timestep: int = typer.Option(None, '--timestep', help='Load specific timestep (requires single --episode)'))

Load and inspect datasets.

Source code in src/dataphy/cli.py 
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
@dataset_app.command("load")
def dataset_load(
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message"),
    dataset_path: str = typer.Option(None, "--dataset-path", help="Path to dataset directory"),
    format: str = typer.Option(None, "--format", help="Dataset format (auto-detected if not specified)"),
    info: bool = typer.Option(False, "--info", help="Show dataset information"),
    list_episodes: bool = typer.Option(False, "--list-episodes", help="List available episodes"),
    episode: str = typer.Option(None, "--episode", help="Load specific episode (name: 'episode_000000' or index: '0', '1', '2'...)"),
    episodes: str = typer.Option(None, "--episodes", help="Load multiple episodes (comma-separated, e.g., '0,1,2' or 'episode_000000,episode_000001')"),
    timestep: int = typer.Option(None, "--timestep", help="Load specific timestep (requires single --episode)"),
):
    """Load and inspect datasets."""
    if help_flag:
        show_load_help()
        raise typer.Exit()

    if not dataset_path:
        console.print("[red]Error:[/red] --dataset-path is required")
        console.print("[dim]Use 'dataphy dataset load --help' for help[/dim]")
        raise typer.Exit(code=1)
    try:
        from dataphy.dataset.registry import DatasetFormat, create_dataset_loader

        # Parse format if provided
        format_enum = None
        if format:
            try:
                format_enum = DatasetFormat(format.lower())
            except ValueError:
                console.print(f"[red]❌ Error:[/red] Unknown format '{format}'. Supported formats: {[f.value for f in DatasetFormat]}")
                raise typer.Exit(code=1)

        # Create dataset loader
        loader = create_dataset_loader(dataset_path, format_type=format_enum)

        if info:
            # Show dataset information
            dataset_info = loader.get_dataset_info()
            console.print("[green]📊 Dataset Information:[/green]")
            print(f"  Format: {dataset_info.get('format', 'Unknown')}")
            print(f"  Total episodes: {dataset_info.get('total_episodes', 'Unknown')}")
            print(f"  Total timesteps: {dataset_info.get('total_timesteps', 'Unknown')}")
            if dataset_info.get('features'):
                print(f"  Features: {', '.join(dataset_info['features'])}")

        elif list_episodes:
            # List available episodes
            episodes = loader.list_episodes()
            console.print("[green]📋 Available episodes:[/green]")
            for ep_id in episodes:
                print(f"  - {ep_id}")

        elif episode or episodes:
            # Handle episode/episodes parameter - support single and multiple episodes
            if episode and episodes:
                console.print("[red]❌ Error:[/red] Cannot specify both --episode and --episodes")
                raise typer.Exit(code=1)

            if timestep is not None and episodes:
                console.print("[red]❌ Error:[/red] --timestep can only be used with single --episode")
                raise typer.Exit(code=1)

            # Get all episodes for index conversion
            all_episodes = loader.list_episodes()

            # Determine target episodes
            target_episodes = []
            if episode:
                target_episodes = [episode]
            elif episodes:
                target_episodes = [ep.strip() for ep in episodes.split(",")]

            # Convert episode indices to names and validate
            final_episodes = []
            for ep in target_episodes:
                episode_id = ep

                # Check if episode is a numeric index and convert to episode name
                try:
                    episode_index = int(ep)
                    if episode_index < 0 or episode_index >= len(all_episodes):
                        console.print(f"[red]❌ Error:[/red] Episode index {episode_index} out of range. Available episodes: 0-{len(all_episodes)-1}")
                        raise typer.Exit(code=1)
                    episode_id = all_episodes[episode_index]
                    console.print(f"[green]📋 Using episode index {episode_index}:[/green] {episode_id}")
                except ValueError:
                    # ep is already a name, use as-is
                    pass

                # Validate episode exists
                if episode_id not in all_episodes:
                    console.print(f"[red]❌ Error:[/red] Episode '{episode_id}' not found")
                    console.print(f"[dim]Available episodes: {all_episodes[:5]}...[/dim]")
                    raise typer.Exit(code=1)

                final_episodes.append(episode_id)

            # Load episodes
            for i, episode_id in enumerate(final_episodes):
                if len(final_episodes) > 1:
                    console.print(f"\n[cyan]📁 Episode {i+1}/{len(final_episodes)}:[/cyan] {episode_id}")

                if timestep is not None:
                    # Load specific timestep (only for single episode)
                    data = loader.get_timestep(episode_id, timestep)
                    console.print(f"[green]⏱️  Loaded timestep {timestep} from episode {episode_id}:[/green]")
                    print(f"  Keys: {list(data.keys())}")
                    for key, value in data.items():
                        if hasattr(value, 'shape'):
                            print(f"  {key}: shape {value.shape}, dtype {value.dtype}")
                        else:
                            print(f"  {key}: {type(value).__name__}")
                else:
                    # Load entire episode
                    episode_data = loader.get_episode(episode_id)
                    data = episode_data.data
                    console.print(f"[green]📁 Loaded episode {episode_id}:[/green]")
                    console.print(f"  Episode length: {episode_data.length} timesteps")
                    console.print(f"  Available data keys: {list(data.keys())}")

                    # Show sample data for each key
                    for key, value in data.items():
                        if isinstance(value, list) and len(value) > 0:
                            sample_value = value[0]
                            if hasattr(sample_value, 'shape'):
                                console.print(f"  {key}: {len(value)} items, sample shape {sample_value.shape}, dtype {sample_value.dtype}")
                            else:
                                console.print(f"  {key}: {len(value)} items, sample type {type(sample_value).__name__}")
                        else:
                            console.print(f"  {key}: {type(value).__name__}")

            if len(final_episodes) > 1:
                console.print(f"\n[green]✅ Loaded {len(final_episodes)} episodes successfully[/green]")
        else:
            console.print("[yellow]⚠️  No action specified. Use --info, --list-episodes, or --episode to interact with the dataset.[/yellow]")

    except Exception as e:
        console.print(f"[red]❌ Error loading dataset:[/red] {e}")
        raise typer.Exit(code=1)

dataset_list_formats(help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'))

List supported dataset formats.

Source code in src/dataphy/cli.py 
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
@dataset_app.command("list-formats")
def dataset_list_formats(
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message")
):
    """List supported dataset formats."""
    if help_flag:
        show_list_formats_help()
        raise typer.Exit()

    try:
        from dataphy.dataset.registry import list_supported_formats
        formats = list_supported_formats()

        # Create a fancy table for formats
        formats_table = Table(title="🗂️  Supported Dataset Formats", show_header=True, header_style="bold magenta")
        formats_table.add_column("Format", style="cyan", width=15)
        formats_table.add_column("Description", style="white")
        formats_table.add_column("Example Usage", style="dim yellow")

        format_descriptions = {
            "lerobot": ("LeRobot robotics datasets", "dataphy dataset load --format lerobot"),

        }

        for format_type in formats:
            desc, example = format_descriptions.get(format_type.value, ("General format", "dataphy dataset load"))
            formats_table.add_row(format_type.value, desc, example)

        console.print()
        console.print(formats_table)
        console.print()

    except Exception as e:
        console.print(f"[red]❌ Error listing formats:[/red] {e}")
        raise typer.Exit(code=1)

dataset_visualize(help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'), format: str = typer.Option(None, '--format', help='Dataset format (lerobot)'), dataset_path: str = typer.Option(None, '--dataset-path', help='Path to dataset directory'), repo_id: str = typer.Option(None, '--repo-id', help='Hugging Face repository ID (for lerobot format)'), episode: str = typer.Option(None, '--episode', help="Specific episode ID to visualize (name: 'episode_000000' or index: '0', '1', '2'...)"), episodes: str = typer.Option(None, '--episodes', help="Multiple episodes to visualize (comma-separated, e.g., '0,1,2' or 'episode_000000,episode_000001')"), timestep_range: str = typer.Option(None, '--timestep-range', help="Timestep range as 'start,end' (default: all timesteps)"), camera: str = typer.Option(None, '--camera', help='Camera name to visualize (for multi-camera datasets)'))

Visualize datasets using format-specific viewers.

Source code in src/dataphy/cli.py 
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
@dataset_app.command("visualize")
def dataset_visualize(
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message"),
    format: str = typer.Option(None, "--format", help="Dataset format (lerobot)"),
    dataset_path: str = typer.Option(None, "--dataset-path", help="Path to dataset directory"),
    repo_id: str = typer.Option(None, "--repo-id", help="Hugging Face repository ID (for lerobot format)"),
    episode: str = typer.Option(None, "--episode", help="Specific episode ID to visualize (name: 'episode_000000' or index: '0', '1', '2'...)"),
    episodes: str = typer.Option(None, "--episodes", help="Multiple episodes to visualize (comma-separated, e.g., '0,1,2' or 'episode_000000,episode_000001')"),
    timestep_range: str = typer.Option(None, "--timestep-range", help="Timestep range as 'start,end' (default: all timesteps)"),
    camera: str = typer.Option(None, "--camera", help="Camera name to visualize (for multi-camera datasets)"),
):
    """Visualize datasets using format-specific viewers."""
    if help_flag:
        show_visualize_help()
        raise typer.Exit()

    if not format:
        console.print("[red]Error:[/red] --format is required")
        console.print("[dim]Use 'dataphy dataset visualize --help' for help[/dim]")
        raise typer.Exit(code=1)
    if format.lower() == "lerobot":
        try:
            from dataphy.visualization.lerobot import visualize_lerobot_dataset
            from dataphy.dataset.registry import create_dataset_loader

            # Handle repo-id by fetching dataset first if needed
            actual_dataset_path = dataset_path
            if repo_id and not dataset_path:
                # Auto-fetch dataset to temporary location for visualization
                import tempfile
                import os
                from dataphy.sources.lerobot import fetch, RepositoryNotFoundError, RevisionNotFoundError, NetworkError

                console.print(f"[green]📥 Fetching dataset from HuggingFace Hub:[/green] {repo_id}")
                temp_dir = tempfile.mkdtemp(prefix="dataphy_viz_")
                try:
                    source = {
                        "repo_id": repo_id,
                        "split": "train",
                        "revision": "main",
                    }
                    actual_dataset_path = fetch(source=source, output_dir=temp_dir, runner="DirectRunner")
                    console.print(f"[green]✅ Dataset cached at:[/green] {actual_dataset_path}")
                except RepositoryNotFoundError as e:
                    console.print(f"[red]❌ Repository not found:[/red] {e}")
                    console.print(f"[yellow]Tip:[/yellow] Check that {repo_id} exists on Hugging Face Hub")
                    raise typer.Exit(code=1)
                except (NetworkError, Exception) as e:
                    console.print(f"[red]❌ Error fetching dataset:[/red] {e}")
                    raise typer.Exit(code=1)

            # Handle episode selection - support both single and multiple episodes
            target_episodes = []

            if episode or episodes:
                # Create loader to get episode list for index conversion
                loader = create_dataset_loader(actual_dataset_path)
                all_episodes = loader.get_episode_ids()

                if episode and episodes:
                    console.print("[red]❌ Error:[/red] Cannot specify both --episode and --episodes")
                    raise typer.Exit(code=1)

                if episode:
                    target_episodes = [episode]
                elif episodes:
                    target_episodes = [ep.strip() for ep in episodes.split(",")]

                # Convert episode indices to names
                final_episodes = []
                for ep in target_episodes:
                    episode_id = ep

                    # Check if episode is a numeric index and convert to episode name
                    try:
                        episode_index = int(ep)
                        if episode_index < 0 or episode_index >= len(all_episodes):
                            console.print(f"[red]❌ Error:[/red] Episode index {episode_index} out of range. Available episodes: 0-{len(all_episodes)-1}")
                            raise typer.Exit(code=1)
                        episode_id = all_episodes[episode_index]
                        console.print(f"[green]📋 Using episode index {episode_index}:[/green] {episode_id}")
                    except ValueError:
                        # ep is already a name, use as-is
                        pass

                    # Validate episode exists
                    if episode_id not in all_episodes:
                        console.print(f"[red]❌ Error:[/red] Episode '{episode_id}' not found")
                        console.print(f"[dim]Available episodes: {all_episodes[:5]}...[/dim]")
                        raise typer.Exit(code=1)

                    final_episodes.append(episode_id)

                # Visualize episodes
                if len(final_episodes) == 1:
                    console.print(f"[green]🔍 Visualizing episode:[/green] {final_episodes[0]}")
                    visualize_lerobot_dataset(
                        dataset_path=actual_dataset_path,
                        repo_id=None,  # Use local path now
                        episode_id=final_episodes[0],
                        timestep_range=timestep_range,
                        camera=camera
                    )
                else:
                    console.print(f"[green]🔍 Visualizing {len(final_episodes)} episodes:[/green] {final_episodes}")
                    console.print("[dim]💡 Tip: Each episode will open in a separate viewer[/dim]")
                    for i, ep_id in enumerate(final_episodes):
                        console.print(f"[cyan]Opening episode {i+1}/{len(final_episodes)}:[/cyan] {ep_id}")
                        visualize_lerobot_dataset(
                            dataset_path=actual_dataset_path,
                            repo_id=None,  # Use local path now
                            episode_id=ep_id,
                            timestep_range=timestep_range,
                            camera=camera
                        )
            else:
                # No specific episodes - visualize all
                visualize_lerobot_dataset(
                    dataset_path=actual_dataset_path,
                    repo_id=None if actual_dataset_path != dataset_path else repo_id,  # Use local path if we fetched it
                    episode_id=None,
                    timestep_range=timestep_range,
                    camera=camera
                )
        except ImportError:
            console.print("[red]❌ Error:[/red] Missing dependencies for LeRobot visualization. Install with: pip install rerun-sdk")
            raise typer.Exit(code=1)
        except Exception as e:
            console.print(f"[red]❌ Error visualizing LeRobot dataset:[/red] {e}")
            raise typer.Exit(code=1)
    else:
        console.print(f"[red]❌ Error:[/red] Unsupported format '{format}' for visualization. Supported formats: lerobot")
        raise typer.Exit(code=1)

augment_dataset(help_flag: bool = typer.Option(False, '--help', '-h', help='Show help message'), dataset_path: str = typer.Option(None, '--dataset-path', help='Path to dataset directory'), config: str = typer.Option(None, '--config', help='VisionPack pipeline YAML config'), episode: str = typer.Option(None, '--episode', help="Single episode to augment (name: 'episode_000000' or index: '0', '1', '2'...)"), episodes: str = typer.Option(None, '--episodes', help="Multiple episodes to augment (comma-separated, e.g., '0,1,2' or 'episode_000000,episode_000001')"), output_path: str = typer.Option('./augmented', '--output-path', help='Output path for new dataset (full dataset mode only, default: ./augmented)'), num_augmented: int = typer.Option(1, '--num-augmented', help='Number of augmented versions per episode (default: 1)'), cameras: str = typer.Option(None, '--cameras', help="Camera streams to augment (comma-separated, e.g., 'observation.images.webcam')"), preserve_original: bool = typer.Option(True, '--preserve-original/--no-preserve-original', help='Include original episodes in output dataset (full dataset mode)'), sync_views: bool = typer.Option(False, '--sync-views', help='Use synchronized augmentation across cameras'), random_seed: int = typer.Option(None, '--seed', help='Random seed for reproducible augmentation'), no_backup: bool = typer.Option(False, '--no-backup', help='Skip creating backup of original files (episode mode only)'), restore: str = typer.Option(None, '--restore', help='Restore episode from backup (provide episode ID)'), format: str = typer.Option(None, '--format', help='Dataset format (auto-detected if not specified)'), list_episodes: bool = typer.Option(False, '--list-episodes', help='List available episodes and cameras'), dry_run: bool = typer.Option(False, '--dry-run', help='Show what would be augmented without actually doing it'))

Augment episodes or entire datasets with VisionPack transforms.

🎯 MODES: • Episode Mode: Specify --episode or --episodes to augment specific episodes in-place • Full Dataset Mode: No episode selection creates a new augmented dataset

🔧 EPISODE MODE (--episode or --episodes provided): • Modifies original dataset with backups • Camera stream selection and synchronized views • Automatic backup and restore functionality • In-place video repackaging in original format

🏭 FULL DATASET MODE (no episode selection): • Creates entirely new dataset at --output-path (default: ./augmented) • Multiple augmented versions per episode (--num-augmented) • Preserves original episodes alongside augmented ones • Automatic LeRobot version detection and metadata updates

The augmentation uses VisionPack transforms including spatial, photometric, texture, and occlusion variations optimized for robotics applications.

Source code in src/dataphy/cli.py 
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
@augment_app.command("dataset")
def augment_dataset(
    help_flag: bool = typer.Option(False, "--help", "-h", help="Show help message"),
    dataset_path: str = typer.Option(None, "--dataset-path", help="Path to dataset directory"),
    config: str = typer.Option(None, "--config", help="VisionPack pipeline YAML config"),

    # Episode selection (determines mode)
    episode: str = typer.Option(None, "--episode", help="Single episode to augment (name: 'episode_000000' or index: '0', '1', '2'...)"),
    episodes: str = typer.Option(None, "--episodes", help="Multiple episodes to augment (comma-separated, e.g., '0,1,2' or 'episode_000000,episode_000001')"),

    # Output control
    output_path: str = typer.Option("./augmented", "--output-path", help="Output path for new dataset (full dataset mode only, default: ./augmented)"),
    num_augmented: int = typer.Option(1, "--num-augmented", help="Number of augmented versions per episode (default: 1)"),

    # Camera and processing options
    cameras: str = typer.Option(None, "--cameras", help="Camera streams to augment (comma-separated, e.g., 'observation.images.webcam')"),
    preserve_original: bool = typer.Option(True, "--preserve-original/--no-preserve-original", help="Include original episodes in output dataset (full dataset mode)"),
    sync_views: bool = typer.Option(False, "--sync-views", help="Use synchronized augmentation across cameras"),
    random_seed: int = typer.Option(None, "--seed", help="Random seed for reproducible augmentation"),

    # Legacy episode-mode options
    no_backup: bool = typer.Option(False, "--no-backup", help="Skip creating backup of original files (episode mode only)"),
    restore: str = typer.Option(None, "--restore", help="Restore episode from backup (provide episode ID)"),

    # General options
    format: str = typer.Option(None, "--format", help="Dataset format (auto-detected if not specified)"),
    list_episodes: bool = typer.Option(False, "--list-episodes", help="List available episodes and cameras"),
    dry_run: bool = typer.Option(False, "--dry-run", help="Show what would be augmented without actually doing it"),
):
    """
    Augment episodes or entire datasets with VisionPack transforms.

    🎯 MODES:
    • Episode Mode: Specify --episode or --episodes to augment specific episodes in-place
    • Full Dataset Mode: No episode selection creates a new augmented dataset

    🔧 EPISODE MODE (--episode or --episodes provided):
    • Modifies original dataset with backups
    • Camera stream selection and synchronized views
    • Automatic backup and restore functionality
    • In-place video repackaging in original format

    🏭 FULL DATASET MODE (no episode selection):
    • Creates entirely new dataset at --output-path (default: ./augmented)
    • Multiple augmented versions per episode (--num-augmented)
    • Preserves original episodes alongside augmented ones
    • Automatic LeRobot version detection and metadata updates

    The augmentation uses VisionPack transforms including spatial, photometric,
    texture, and occlusion variations optimized for robotics applications.
    """
    if help_flag:
        show_augment_dataset_help()
        raise typer.Exit()

    # Validate required parameters
    if not dataset_path:
        console.print("[red]Error:[/red] --dataset-path is required")
        console.print("[dim]Use 'dataphy augment dataset --help' for help[/dim]")
        raise typer.Exit(code=1)

    try:
        from dataphy.dataset.episode_augmentor import EpisodeAugmentor
        from dataphy.dataset.augmentor import DatasetAugmentor, AugmentationConfig
        from dataphy.dataset.registry import DatasetFormat, create_dataset_loader

        # Parse format if provided
        format_enum = None
        if format:
            try:
                format_enum = DatasetFormat(format.lower())
            except ValueError:
                console.print(f"[red]❌ Error:[/red] Unknown format '{format}'. Supported formats: {[f.value for f in DatasetFormat]}")
                raise typer.Exit(code=1)

        # Create dataset loader
        loader = create_dataset_loader(dataset_path, format_type=format_enum)

        # Determine mode based on episode parameters
        episode_mode = episode is not None or episodes is not None
        full_dataset_mode = not episode_mode

        # Handle special operations first
        if restore:
            augmentor = EpisodeAugmentor(loader)
            all_episodes = augmentor.list_episodes()

            # Convert episode index to name if needed
            restore_episode = restore
            try:
                episode_index = int(restore)
                # Convert index to episode name
                if episode_index < 0 or episode_index >= len(all_episodes):
                    console.print(f"[red]❌ Error:[/red] Episode index {episode_index} out of range. Available episodes: 0-{len(all_episodes)-1}")
                    raise typer.Exit(code=1)
                restore_episode = all_episodes[episode_index]
                console.print(f"[green]📋 Using episode index {episode_index}:[/green] {restore_episode}")
            except ValueError:
                # restore is already a name, use as-is
                pass

            console.print(f"[yellow]🔄 Restoring episode:[/yellow] {restore_episode}")
            augmentor.restore_episode(restore_episode)
            console.print(f"[green]✅ Episode {restore_episode} restored from backup[/green]")
            return

        if list_episodes:
            augmentor = EpisodeAugmentor(loader)
            all_episodes = augmentor.list_episodes()
            backups = augmentor.list_backups()

            console.print(f"[green]📊 Dataset Information:[/green]")
            print(f"  Total episodes: {len(all_episodes)}")
            print(f"  Episodes with backups: {len(backups)}")

            console.print(f"\n[green]📋 Available Episodes:[/green]")
            for i, ep in enumerate(all_episodes[:10]):  # Show first 10
                backup_status = " [dim](backed up)[/dim]" if ep in backups else ""
                console.print(f"  {i:2d}. {ep}{backup_status}")

            if len(all_episodes) > 10:
                console.print(f"  ... and {len(all_episodes) - 10} more episodes")

            # Show cameras for first episode
            if all_episodes:
                first_episode = all_episodes[0]
                cameras_list = augmentor.get_available_cameras(first_episode)
                console.print(f"\n[green]📹 Available Cameras ({first_episode}):[/green]")
                for cam in cameras_list:
                    console.print(f"  • {cam}")

            return

        # Validate config is provided (required for both modes)
        if not config:
            console.print("[red]❌ Error:[/red] --config is required for augmentation")
            if episode_mode:
                console.print("[dim]Use --list-episodes to see available episodes[/dim]")
            raise typer.Exit(code=1)

        # Route to appropriate mode
        if episode_mode:
            # EPISODE MODE: Single or multiple specific episodes
            return _handle_episode_mode(
                loader, dataset_path, config, episode, episodes, cameras, 
                no_backup, sync_views, num_augmented, dry_run
            )
        else:
            # FULL DATASET MODE: Create new augmented dataset
            return _handle_full_dataset_mode(
                loader, dataset_path, output_path, config, num_augmented, 
                cameras, preserve_original, sync_views, random_seed, dry_run
            )

    except Exception as e:
        console.print(f"[red]❌ Error augmenting dataset:[/red] {e}")
        raise typer.Exit(code=1)