Downloads · 30 days
0
arnorsig/danish-food-classification
danish-food-classification is a text classification model from arnorsig. Use it when you need a label for a piece of text. The card lists the license as mit.
This repository contains pre-trained models for classifying Danish food text descriptions into standard food categories. These models are designed to be used with the EIR prediction framework.
Downloads · 30 days
0
Access
Public
Updated Feb 3, 2026
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.pt1.1 GB · 100%
From the Hugging Face model README
This repository contains pre-trained models for classifying Danish food text descriptions into standard food categories. These models are designed to be used with the EIR prediction framework.
Major Category Model (majorcateg_run3jseq)
Subcategory Model (subcateg_run3jseq)
These models require the eirpredict tool.
Install the tool
uv pip install git+https://github.com/arnor-sigurdsson/[email protected]
Download the models
from huggingface_hub import snapshot_download
model_path = snapshot_download(
repo_id="arnorsig/danish-food-classification",
allow_patterns="majorcateg_run3jseq/*"
)
print(f"Model downloaded to: {model_path}")
model_path = snapshot_download(
repo_id="arnorsig/danish-food-classification",
allow_patterns="subcateg_run3jseq/*"
)
print(f"Model downloaded to: {model_path}")
Run prediction (example for subcategory model):
eirpredict \
--global_configs predict_global_config.yaml \
--input_configs predict_input_config.yaml \
--output_configs predict_output_config.yaml \
--model_path subcateg_run3jseq/training_output/saved_models/output_model_6300_perf-average=0.9312.pt \
--output_folder my_predictions
For full documentation and configuration files, please visit the GitHub Repository.