ONNX Model Zoo

colour-science/learning-munsell

By colour-science · ↓ 0 · ♥ 0 · Updated 2026-02-14

What's in this repo

This page lists the files in colour-science/learning-munsell, including deep_wide.onnx, ft_transformer.onnx, mixture_of_experts.onnx and more.

  • 45 ONNX models (.onnx files)
  • 257 files, including 82 .py, 45 .onnx, 44 .data, 44 .pth, 32 .npz, 2 .md
  • Last updated 2026-02-14

ONNX files

File Size Download
models/from_xyY/deep_wide.onnx — Download
models/from_xyY/ft_transformer.onnx — Download
models/from_xyY/mixture_of_experts.onnx — Download
models/from_xyY/mlp.onnx — Download
models/from_xyY/mlp_attention.onnx — Download
models/from_xyY/mlp_error_predictor.onnx — Download
models/from_xyY/mlp_gamma.onnx — Download
models/from_xyY/multi_head.onnx — Download
models/from_xyY/multi_head_3stage_error_predictor.onnx — Download
models/from_xyY/multi_head_circular.onnx — Download

Showing 10 of 45 .onnx files — see the full file list on the right.

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

Learning Munsell - Machine Learning for Munsell Color Conversions

A project implementing machine learning-based methods for bidirectional conversion between CIE xyY colourspace values and Munsell specifications.

Two Conversion Directions:

  • from_xyY: CIE xyY to Munsell specification
  • to_xyY: Munsell specification to CIE xyY

Project Overview

Objective

Provide 100-1000x speedup for batch Munsell conversions compared to colour-science routines while maintaining high accuracy.

Results

from_xyY (CIE xyY to Munsell) — 33 models evaluated on all 2,734 REAL Munsell colors:

Model Delta-E Speed (ms)
Colour Library (Baseline) 0.00 116.3
Multi-MLP + Multi-Error Predictor 0.51 0.061
Multi-ResNet + Multi-Error Predictor (Large Dataset) 0.52 0.096
Transformer + Error Predictor (Large Dataset) 0.52 0.163
Multi-MLP (Classification Code) + Code-Aware Multi-Error Predictor (Large Dataset) 0.53 0.118
Multi-Head + Multi-Error Predictor (Large Dataset) 0.53 0.046
Multi-MLP (Classification Code) + Code-Aware Multi-Error Predictor 0.53 0.052
Multi-MLP (Classification Code) + Multi-Error Predictor 0.53 0.050
MLP + Error Predictor 0.53 0.036
Multi-Head + Multi-Error Predictor 0.54 0.057
Multi-ResNet (Large Dataset) 0.56 0.047
Multi-Head (Large Dataset) 0.57 0.012
FT-Transformer 0.70 0.067
Unified MLP 0.71 0.074
Transformer (Large Dataset) 0.73 0.120
Mixture of Experts 0.74 0.021
Multi-MLP 0.91 0.027
Multi-MLP (Classification Code) 0.92 0.026
Multi-MLP (Classification Code) (Large Dataset) 0.89 0.066
MLP + Self-Attention 0.88 0.185
Deep + Wide 1.18 0.078
MLP (Base Only) 1.30 0.009
Multi-MLP (Hue Angle sin/cos) 1.78 0.021
  • Best Accuracy: Multi-MLP + Multi-Error Predictor — Delta-E 0.51, 1,905x faster
  • Fastest: MLP Base Only (0.009 ms/sample) — 13,365x faster than Colour library
  • Best Balance: MLP + Error Predictor — 3,196x faster with Delta-E 0.53

to_xyY (Munsell to CIE xyY) — 6 models evaluated on all 2,734 REAL Munsell colors:

Model Delta-E Speed (ms)
Colour Library (Baseline) 0.00 1.40
Multi-MLP + Multi-Error Predictor 0.48 0.066
Multi-Head + Multi-Error Predictor 0.51 0.054
Simple MLP 0.52 0.002
Multi-MLP 0.57 0.028
Multi-Head 0.60 0.013
Multi-MLP + Error Predictor 0.61 0.060
  • Best Accuracy: Multi-MLP + Multi-Error Predictor — Delta-E 0.48, 21x faster
  • Fastest: Simple MLP (0.002 ms/sample) — 669x faster than Colour library

Approach

  • 33 models tested for from_xyY (MLP, Multi-Head, Multi-MLP, Multi-ResNet, Transformers, FT-Transformer, Mixture of Experts)
  • 6 models tested for to_xyY (Simple MLP, Multi-Head, Multi-MLP with error predictors)
  • Two-stage models (base + error predictor) proved most effective
  • Best model: Multi-MLP + Multi-Error Predictor with Delta-E 0.51
  • Training data: ~1.4M samples from dense xyY grid with boundary refinement and forward Munsell sampling
  • Deployment: ONNX format with ONNX Runtime

For detailed architecture comparisons, model benchmarks, training pipeline details, and experimental results, see docs/learning_munsell.md.

Installation

Dependencies (Runtime):

  • numpy >= 2.0
  • onnxruntime >= 1.16

Dependencies (Training):

  • torch >= 2.0
  • scikit-learn >= 1.3
  • matplotlib >= 3.9
  • mlflow >= 2.10
  • optuna >= 3.0
  • colour-science >= 0.4.7
  • click >= 8.0
  • onnx >= 1.15
  • onnxscript >= 0.5.6
  • tqdm >= 4.66
  • jax >= 0.4.20
  • jaxlib >= 0.4.20
  • flax >= 0.10.7
  • optax >= 0.2.6
  • scipy >= 1.12
  • tensorboard >= 2.20

From the project root:

cd learning-munsell

# Install all dependencies (creates virtual environment automatically)
uv sync

Usage

Generate Training Data

uv run python learning_munsell/data_generation/generate_training_data.py

Note: This step is computationally expensive (uses iterative algorithm for ground truth).

Train Models

xyY to Munsell (from_xyY)

Best performing model (Multi-MLP + Multi-Error Predictor):

# Train base Multi-MLP
uv run python learning_munsell/training/from_xyY/train_multi_mlp.py

# Train multi-error predictor
uv run python learning_munsell/training/from_xyY/train_multi_mlp_multi_error_predictor.py

Alternative architectures:

uv run python learning_munsell/training/from_xyY/train_multi_resnet_large.py
uv run python learning_munsell/training/from_xyY/train_multi_head_large.py
uv run python learning_munsell/training/from_xyY/train_ft_transformer.py
uv run python learning_munsell/training/from_xyY/train_unified_mlp.py
uv run python learning_munsell/training/from_xyY/train_deep_wide.py
uv run python learning_munsell/training/from_xyY/train_mlp_attention.py

Munsell to xyY (to_xyY)

Best performing model (Multi-MLP + Multi-Error Predictor):

# Train base Multi-MLP
uv run python learning_munsell/training/to_xyY/train_multi_mlp.py

# Train multi-error predictor
uv run python learning_munsell/training/to_xyY/train_multi_mlp_multi_error_predictor.py

Other architectures:

uv run python learning_munsell/training/to_xyY/train_multi_head.py
uv run python learning_munsell/training/to_xyY/train_multi_mlp_error_predictor.py
uv run python learning_munsell/training/to_xyY/train_multi_head_multi_error_predictor.py

Train the differentiable approximator for use in Delta-E loss:

uv run python learning_munsell/training/to_xyY/train_munsell_to_xyY_approximator.py

Hyperparameter Search

uv run python learning_munsell/training/from_xyY/hyperparameter_search_multi_head.py
uv run python learning_munsell/training/from_xyY/hyperparameter_search_multi_head_error_predictor.py

Compare All Models

uv run python learning_munsell/comparison/from_xyY/compare_all_models.py
uv run python learning_munsell/comparison/to_xyY/compare_all_models.py

Generates comprehensive HTML reports at reports/from_xyY/model_comparison.html and reports/to_xyY/model_comparison.html.

Monitor Training

MLflow:

uv run mlflow ui --backend-store-uri "sqlite:///mlruns.db" --port=5000

Open in your browser.

Directory Structure

learning-munsell/
+-- data/                          # Training data
|   +-- training_data.npz          # Generated training samples
|   +-- training_data_large.npz    # Large dataset (~1.4M samples)
|   +-- training_data_params.json  # Generation parameters
|   +-- training_data_large_params.json
+-- models/                        # Trained models (ONNX + PyTorch)
|   +-- from_xyY/                  # xyY to Munsell models (38 ONNX models)
|   |   +-- multi_mlp_multi_error_predictor.onnx  # BEST
|   |   +-- ... (additional model variants)
|   +-- to_xyY/                    # Munsell to xyY models (6 ONNX models)
|       +-- multi_mlp_multi_error_predictor.onnx  # BEST
|       +-- ... (additional model variants)
+-- learning_munsell/              # Source code
|   +-- analysis/                  # Analysis scripts
|   +-- comparison/                # Model comparison scripts
|   +-- data_generation/           # Data generation scripts
|   +-- interpolation/             # Classical interpolation methods
|   +-- losses/                    # Loss functions (JAX Delta-E)
|   +-- models/                    # Model architecture definitions
|   +-- training/                  # Model training scripts
|   +-- utilities/                 # Shared utilities
+-- docs/                          # Documentation
+-- reports/                       # HTML comparison reports
+-- logs/                          # Script output logs
+-- mlruns.db                      # MLflow experiment tracking database

About

Learning Munsell by Colour Developers Research project for the Colour library

Model info

tabular-regression onnxruntime
onnxruntime onnx python colour color colour-science color-science colour-spaces color-spaces colourspace colorspace tabular-regression
↓ 0 ♥ 0

Created: 2026-02-14

Updated: 2026-02-14

View on Hugging Face

Files (257)

.gitattributes
.gitignore
.pre-commit-config.yaml
LICENSE
README.md
docs/_static/gamma_sweep_plot.pdf
docs/_static/gamma_sweep_plot.png
docs/learning_munsell.md
docs/training_data_large_hue_density.png
learning_munsell/__init__.py
learning_munsell/analysis/__init__.py
learning_munsell/analysis/error_analysis.py
learning_munsell/analysis/hue_density_plot.py
learning_munsell/comparison/from_xyY/__init__.py
learning_munsell/comparison/from_xyY/compare_all_models.py
learning_munsell/comparison/from_xyY/compare_gamma_model.py
learning_munsell/comparison/to_xyY/__init__.py
learning_munsell/comparison/to_xyY/compare_all_models.py
learning_munsell/data_generation/generate_training_data.py
learning_munsell/data_generation/generate_training_data_uniform.py
learning_munsell/interpolation/__init__.py
learning_munsell/interpolation/from_xyY/__init__.py
learning_munsell/interpolation/from_xyY/compare_methods.py
learning_munsell/interpolation/from_xyY/delaunay_interpolator.py
learning_munsell/interpolation/from_xyY/kdtree_interpolator.py
learning_munsell/interpolation/from_xyY/rbf_interpolator.py
learning_munsell/losses/__init__.py
learning_munsell/losses/jax_delta_e.py
learning_munsell/models/__init__.py
learning_munsell/models/networks.py
learning_munsell/training/from_xyY/__init__.py
learning_munsell/training/from_xyY/hyperparameter_search_error_predictor.py
learning_munsell/training/from_xyY/hyperparameter_search_multi_head.py
learning_munsell/training/from_xyY/hyperparameter_search_multi_head_error_predictor.py
learning_munsell/training/from_xyY/hyperparameter_search_multi_mlp.py
learning_munsell/training/from_xyY/refine_multi_head_real.py
learning_munsell/training/from_xyY/train_deep_wide.py
learning_munsell/training/from_xyY/train_ft_transformer.py
learning_munsell/training/from_xyY/train_mixture_of_experts.py
learning_munsell/training/from_xyY/train_mlp.py
learning_munsell/training/from_xyY/train_mlp_attention.py
learning_munsell/training/from_xyY/train_mlp_error_predictor.py
learning_munsell/training/from_xyY/train_mlp_gamma.py
learning_munsell/training/from_xyY/train_multi_head_3stage_error_predictor.py
learning_munsell/training/from_xyY/train_multi_head_circular.py
learning_munsell/training/from_xyY/train_multi_head_cross_attention_error_predictor.py
learning_munsell/training/from_xyY/train_multi_head_gamma.py
learning_munsell/training/from_xyY/train_multi_head_gamma_sweep.py
learning_munsell/training/from_xyY/train_multi_head_large.py
learning_munsell/training/from_xyY/train_multi_head_mlp.py
learning_munsell/training/from_xyY/train_multi_head_multi_error_predictor.py
learning_munsell/training/from_xyY/train_multi_head_multi_error_predictor_large.py
learning_munsell/training/from_xyY/train_multi_head_st2084.py
learning_munsell/training/from_xyY/train_multi_head_weighted_boundary.py
learning_munsell/training/from_xyY/train_multi_head_weighted_boundary_multi_error_predictor.py
learning_munsell/training/from_xyY/train_multi_mlp.py
learning_munsell/training/from_xyY/train_multi_mlp_class_code.py
learning_munsell/training/from_xyY/train_multi_mlp_class_code_aware_multi_error_predictor.py
learning_munsell/training/from_xyY/train_multi_mlp_class_code_aware_multi_error_predictor_large.py
learning_munsell/training/from_xyY/train_multi_mlp_class_code_aware_multi_error_predictor_uniform.py
learning_munsell/training/from_xyY/train_multi_mlp_class_code_large.py
learning_munsell/training/from_xyY/train_multi_mlp_class_code_multi_error_predictor.py
learning_munsell/training/from_xyY/train_multi_mlp_class_code_uniform.py
learning_munsell/training/from_xyY/train_multi_mlp_hue_angle.py
learning_munsell/training/from_xyY/train_multi_mlp_jax.py
learning_munsell/training/from_xyY/train_multi_mlp_large.py
learning_munsell/training/from_xyY/train_multi_mlp_multi_error_predictor.py
learning_munsell/training/from_xyY/train_multi_mlp_multi_error_predictor_large.py
learning_munsell/training/from_xyY/train_multi_mlp_weighted_boundary.py
learning_munsell/training/from_xyY/train_multi_mlp_weighted_boundary_multi_error_predictor.py
learning_munsell/training/from_xyY/train_multi_resnet_error_predictor_large.py
learning_munsell/training/from_xyY/train_multi_resnet_large.py
learning_munsell/training/from_xyY/train_transformer_large.py
learning_munsell/training/from_xyY/train_transformer_multi_error_predictor_large.py
learning_munsell/training/from_xyY/train_unified_mlp.py
learning_munsell/training/to_xyY/__init__.py
learning_munsell/training/to_xyY/hyperparameter_search_multi_error_predictor.py
learning_munsell/training/to_xyY/hyperparameter_search_multi_head.py
learning_munsell/training/to_xyY/hyperparameter_search_multi_mlp.py
learning_munsell/training/to_xyY/train_multi_head.py
learning_munsell/training/to_xyY/train_multi_head_multi_error_predictor.py
learning_munsell/training/to_xyY/train_multi_mlp.py
learning_munsell/training/to_xyY/train_multi_mlp_error_predictor.py
learning_munsell/training/to_xyY/train_multi_mlp_multi_error_predictor.py
learning_munsell/training/to_xyY/train_munsell_to_xyY_approximator.py
learning_munsell/utilities/__init__.py
learning_munsell/utilities/common.py
learning_munsell/utilities/data.py
learning_munsell/utilities/export.py
learning_munsell/utilities/losses.py
learning_munsell/utilities/training.py
models/from_xyY/deep_wide.onnx ONNX
models/from_xyY/deep_wide.onnx.data
models/from_xyY/deep_wide_best.pth
models/from_xyY/deep_wide_normalization_parameters.npz
models/from_xyY/ft_transformer.onnx ONNX
models/from_xyY/ft_transformer.onnx.data
models/from_xyY/ft_transformer_best.pth
models/from_xyY/ft_transformer_normalization_parameters.npz
models/from_xyY/mixture_of_experts.onnx ONNX
models/from_xyY/mixture_of_experts.onnx.data
models/from_xyY/mixture_of_experts_best.pth
models/from_xyY/mixture_of_experts_normalization_parameters.npz
models/from_xyY/mlp.onnx ONNX
models/from_xyY/mlp.onnx.data
models/from_xyY/mlp_attention.onnx ONNX
models/from_xyY/mlp_attention.onnx.data
models/from_xyY/mlp_attention_best.pth
models/from_xyY/mlp_attention_normalization_parameters.npz
models/from_xyY/mlp_best.pth
models/from_xyY/mlp_error_predictor.onnx ONNX
models/from_xyY/mlp_error_predictor.onnx.data
models/from_xyY/mlp_error_predictor_best.pth
models/from_xyY/mlp_gamma.onnx ONNX
models/from_xyY/mlp_gamma.onnx.data
models/from_xyY/mlp_gamma_best.pth
models/from_xyY/mlp_gamma_normalization_parameters.npz
models/from_xyY/mlp_normalization_parameters.npz
models/from_xyY/multi_head.onnx ONNX
models/from_xyY/multi_head.onnx.data
models/from_xyY/multi_head_3stage_error_predictor.onnx ONNX
models/from_xyY/multi_head_3stage_error_predictor.onnx.data
models/from_xyY/multi_head_3stage_error_predictor_best.pth
models/from_xyY/multi_head_best.pth
models/from_xyY/multi_head_circular.onnx ONNX
models/from_xyY/multi_head_circular.onnx.data
models/from_xyY/multi_head_circular.pth
models/from_xyY/multi_head_circular_normalization_parameters.npz
models/from_xyY/multi_head_cross_attention_error_predictor.onnx ONNX
models/from_xyY/multi_head_cross_attention_error_predictor.onnx.data
models/from_xyY/multi_head_cross_attention_error_predictor.pth
models/from_xyY/multi_head_gamma.onnx ONNX
models/from_xyY/multi_head_gamma.onnx.data
models/from_xyY/multi_head_gamma_best.pth
models/from_xyY/multi_head_gamma_normalization_parameters.npz
models/from_xyY/multi_head_large.onnx ONNX
models/from_xyY/multi_head_large.onnx.data
models/from_xyY/multi_head_large_best.pth
models/from_xyY/multi_head_large_normalization_parameters.npz
models/from_xyY/multi_head_multi_error_predictor.onnx ONNX
models/from_xyY/multi_head_multi_error_predictor.onnx.data
models/from_xyY/multi_head_multi_error_predictor_best.pth
models/from_xyY/multi_head_multi_error_predictor_large.onnx ONNX
models/from_xyY/multi_head_multi_error_predictor_large.onnx.data
models/from_xyY/multi_head_multi_error_predictor_large_best.pth
models/from_xyY/multi_head_normalization_parameters.npz
models/from_xyY/multi_head_refined_real.onnx ONNX
models/from_xyY/multi_head_refined_real.onnx.data
models/from_xyY/multi_head_refined_real_best.pth
models/from_xyY/multi_head_refined_real_normalization_parameters.npz
models/from_xyY/multi_head_st2084.onnx ONNX
models/from_xyY/multi_head_st2084.onnx.data
models/from_xyY/multi_head_st2084_best.pth
models/from_xyY/multi_head_st2084_normalization_parameters.npz
models/from_xyY/multi_head_weighted_boundary.onnx ONNX
models/from_xyY/multi_head_weighted_boundary.onnx.data
models/from_xyY/multi_head_weighted_boundary_best.pth
models/from_xyY/multi_head_weighted_boundary_multi_error_predictor_weighted_boundary.onnx ONNX
models/from_xyY/multi_head_weighted_boundary_multi_error_predictor_weighted_boundary.onnx.data
models/from_xyY/multi_head_weighted_boundary_multi_error_predictor_weighted_boundary_best.pth
models/from_xyY/multi_head_weighted_boundary_normalization_parameters.npz
models/from_xyY/multi_mlp.onnx ONNX
models/from_xyY/multi_mlp.onnx.data
models/from_xyY/multi_mlp_best.pth
models/from_xyY/multi_mlp_class_code.onnx ONNX
models/from_xyY/multi_mlp_class_code.onnx.data
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor.onnx ONNX
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor.onnx.data
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor_best.pth
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor_large.onnx ONNX
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor_large.onnx.data
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor_large_best.pth
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor_uniform.onnx ONNX
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor_uniform.onnx.data
models/from_xyY/multi_mlp_class_code_aware_multi_error_predictor_uniform_best.pth
models/from_xyY/multi_mlp_class_code_best.pth
models/from_xyY/multi_mlp_class_code_large.onnx ONNX
models/from_xyY/multi_mlp_class_code_large.onnx.data
models/from_xyY/multi_mlp_class_code_large_best.pth
models/from_xyY/multi_mlp_class_code_large_normalization_parameters.npz
models/from_xyY/multi_mlp_class_code_multi_error_predictor.onnx ONNX
models/from_xyY/multi_mlp_class_code_multi_error_predictor.onnx.data
models/from_xyY/multi_mlp_class_code_multi_error_predictor_best.pth
models/from_xyY/multi_mlp_class_code_normalization_parameters.npz
models/from_xyY/multi_mlp_class_code_uniform.onnx ONNX
models/from_xyY/multi_mlp_class_code_uniform.onnx.data
models/from_xyY/multi_mlp_class_code_uniform_best.pth
models/from_xyY/multi_mlp_class_code_uniform_normalization_parameters.npz
models/from_xyY/multi_mlp_hue_angle.onnx ONNX
models/from_xyY/multi_mlp_hue_angle.onnx.data
models/from_xyY/multi_mlp_hue_angle_best.pth
models/from_xyY/multi_mlp_hue_angle_normalization_parameters.npz
models/from_xyY/multi_mlp_jax_delta_e.npz
models/from_xyY/multi_mlp_jax_delta_e.onnx ONNX
models/from_xyY/multi_mlp_jax_delta_e.onnx.data
models/from_xyY/multi_mlp_jax_delta_e_normalization_parameters.npz
models/from_xyY/multi_mlp_large.onnx ONNX
models/from_xyY/multi_mlp_large.onnx.data
models/from_xyY/multi_mlp_large_best.pth
models/from_xyY/multi_mlp_large_normalization_parameters.npz
models/from_xyY/multi_mlp_multi_error_predictor.onnx ONNX
models/from_xyY/multi_mlp_multi_error_predictor.onnx.data
models/from_xyY/multi_mlp_multi_error_predictor_best.pth
models/from_xyY/multi_mlp_multi_error_predictor_large.onnx ONNX
models/from_xyY/multi_mlp_multi_error_predictor_large.onnx.data
models/from_xyY/multi_mlp_multi_error_predictor_large_best.pth
models/from_xyY/multi_mlp_normalization_parameters.npz
models/from_xyY/multi_mlp_weighted_boundary.onnx ONNX
models/from_xyY/multi_mlp_weighted_boundary.onnx.data
models/from_xyY/multi_mlp_weighted_boundary_best.pth
models/from_xyY/multi_mlp_weighted_boundary_multi_error_predictor.onnx ONNX
models/from_xyY/multi_mlp_weighted_boundary_multi_error_predictor.onnx.data
models/from_xyY/multi_mlp_weighted_boundary_multi_error_predictor_best.pth
models/from_xyY/multi_mlp_weighted_boundary_normalization_parameters.npz
models/from_xyY/multi_resnet_error_predictor_large.onnx ONNX
models/from_xyY/multi_resnet_error_predictor_large.onnx.data
models/from_xyY/multi_resnet_error_predictor_large_best.pth
models/from_xyY/multi_resnet_large.onnx ONNX
models/from_xyY/multi_resnet_large.onnx.data
models/from_xyY/multi_resnet_large_best.pth
models/from_xyY/multi_resnet_large_normalization_parameters.npz
models/from_xyY/transformer_error_predictor_large_best.pth
models/from_xyY/transformer_large.onnx ONNX
models/from_xyY/transformer_large_best.pth
models/from_xyY/transformer_large_normalization_parameters.npz
models/from_xyY/transformer_multi_error_predictor_large.onnx ONNX
models/from_xyY/transformer_multi_error_predictor_large.onnx.data
models/from_xyY/unified_mlp.onnx ONNX
models/from_xyY/unified_mlp.onnx.data
models/from_xyY/unified_mlp_best.pth
models/from_xyY/unified_mlp_normalization_parameters.npz
models/to_xyY/multi_head.onnx ONNX
models/to_xyY/multi_head.onnx.data
models/to_xyY/multi_head.pth
models/to_xyY/multi_head_multi_error_predictor.onnx ONNX
models/to_xyY/multi_head_multi_error_predictor.onnx.data
models/to_xyY/multi_head_multi_error_predictor.pth
models/to_xyY/multi_head_multi_error_predictor_normalization_parameters.npz
models/to_xyY/multi_head_normalization_parameters.npz
models/to_xyY/multi_mlp.onnx ONNX
models/to_xyY/multi_mlp.onnx.data
models/to_xyY/multi_mlp.pth
models/to_xyY/multi_mlp_error_predictor.onnx ONNX
models/to_xyY/multi_mlp_error_predictor.onnx.data
models/to_xyY/multi_mlp_error_predictor.pth
models/to_xyY/multi_mlp_error_predictor_normalization_parameters.npz
models/to_xyY/multi_mlp_multi_error_predictor.onnx ONNX
models/to_xyY/multi_mlp_multi_error_predictor.onnx.data
models/to_xyY/multi_mlp_multi_error_predictor.pth
models/to_xyY/multi_mlp_multi_error_predictor_normalization_parameters.npz
models/to_xyY/multi_mlp_normalization_parameters.npz
models/to_xyY/munsell_to_xyY_approximator.onnx ONNX
models/to_xyY/munsell_to_xyY_approximator.onnx.data
models/to_xyY/munsell_to_xyY_approximator.pth
models/to_xyY/munsell_to_xyY_approximator_normalization_parameters.npz
models/to_xyY/munsell_to_xyY_approximator_weights.npz
pyproject.toml

Related models

More from colour-science

No other models by this author.

More tabular-regression models

Browse all tabular-regression models

Popular models