1 vin.diagnostics.experimental_plotting

vin.diagnostics.experimental_plotting

Plotly diagnostics for legacy and experimental VIN encodings.

The active VIN v3 plotting helpers live in aria_nbv.vin.diagnostics.plotting. This module contains app-facing figures for legacy shell/LFF experiments and therefore remains under the canonical diagnostics package rather than aria_nbv.vin.experimental.

1.1 Functions

Name Description
build_alignment_figures Plot alignment histograms between candidates and voxel frame.
build_candidate_encoding_figures Build Plotly figures for actual candidate encodings.
build_field_token_histograms Overlay histograms of field values and sampled token values.
build_frustum_samples_figure Plot frustum sample points colored by token validity (world frame).
build_lff_response_figures Visualize LFF Fourier features and MLP output along one input dimension.
build_prediction_alignment_figure Scatter of predicted score vs view alignment.
build_vin_encoding_figures Build Plotly figures from VIN forward diagnostics.
plot_vin_encodings_from_debug Generate VIN encoding plots using Plotly and persist them as HTML.

1.1.1 build_alignment_figures

vin.diagnostics.experimental_plotting.build_alignment_figures(
    debug,
    *,
    log1p_counts=False,
)

Plot alignment histograms between candidates and voxel frame.

1.1.2 build_candidate_encoding_figures

vin.diagnostics.experimental_plotting.build_candidate_encoding_figures(
    debug,
    *,
    lmax,
    sh_normalization,
    radius_freqs,
    pose_encoder_lff=None,
    include_legacy_sh=True,
    max_candidates=512,
    max_sh_components=64,
    max_pose_dims=128,
)

Build Plotly figures for actual candidate encodings.

1.1.3 build_field_token_histograms

vin.diagnostics.experimental_plotting.build_field_token_histograms(
    debug,
    *,
    channel_names,
    max_channels=4,
    max_samples=200000,
    log1p_counts=False,
)

Overlay histograms of field values and sampled token values.

1.1.4 build_frustum_samples_figure

vin.diagnostics.experimental_plotting.build_frustum_samples_figure(
    debug,
    *,
    p3d_cameras,
    candidate_index,
    grid_size,
    depths_m,
)

Plot frustum sample points colored by token validity (world frame).

1.1.5 build_lff_response_figures

vin.diagnostics.experimental_plotting.build_lff_response_figures(
    pose_encoder,
    *,
    input_dim,
    input_range,
    num_samples=200,
    max_features=96,
)

Visualize LFF Fourier features and MLP output along one input dimension.

1.1.6 build_prediction_alignment_figure

vin.diagnostics.experimental_plotting.build_prediction_alignment_figure(
    debug,
    *,
    expected_normalized,
)

Scatter of predicted score vs view alignment.

1.1.7 build_vin_encoding_figures

vin.diagnostics.experimental_plotting.build_vin_encoding_figures(
    debug,
    *,
    lmax,
    sh_normalization,
    radius_freqs,
    pose_encoder_lff=None,
    include_legacy_sh=True,
    log1p_counts=False,
)

Build Plotly figures from VIN forward diagnostics.

1.1.8 plot_vin_encodings_from_debug

vin.diagnostics.experimental_plotting.plot_vin_encodings_from_debug(
    debug,
    *,
    out_dir,
    lmax,
    sh_normalization,
    radius_freqs,
    file_stem_prefix,
    pose_encoder_lff=None,
    include_legacy_sh=True,
)

Generate VIN encoding plots using Plotly and persist them as HTML.

1.1.8.1 Parameters

Name Type Description Default
debug VinForwardDiagnostics Diagnostics from VinModel.forward_with_debug. required
out_dir Path Output directory for saved figures. required
lmax int Maximum SH degree to visualize (legacy plots only). required
sh_normalization str Spherical harmonics normalization mode (legacy plots only). required
radius_freqs Iterable[float] Frequencies for the legacy radius Fourier feature plot. required
file_stem_prefix str Prefix used for output filenames. required
pose_encoder_lff LearnableFourierFeatures | None Optional LFF encoder used for weight visualizations. None
include_legacy_sh bool Whether to include legacy SH/Fourier plots. True

1.1.8.2 Returns

Name Type Description
dict[str, Path] Mapping of figure labels to saved HTML paths.
Back to top