Aller au contenu
ModelPrésentéExterne
Browse files

GelGenie Universal Dec 2023

This model consists of an SMP-UNet trained on the GelGenie training dataset in December 2023. It is highly robust and should produce good results for a wide variety of gel types and resolutions. This is the primary...

Sourcehuggingface.co/cykavodka/GelGenie-Universal-Dec-2023/tree/1845c27ab1ede277e23c8f3b284b16b50a5201c7
TypeOtherVersionRevision 1845c27CClasse

Source du modèle

Type
Other
Taille du fichier
54,6–164 MB
Version
vRevision 1845c27
Mis à jour
16 sept. 2026
Téléchargements
0
Source
Hugging Face

Description de la source

This model consists of an SMP-UNet trained on the GelGenie training dataset in December 2023. It is highly robust and should produce good results for a wide variety of gel types and resolutions. This is the primary model that should be the first point of reference for any new gel analysis.

The model was trained on the training set (420 images) for 600 epochs and the best checkpoint extracted based on the validation dice score.

For more details on the configuration used for training, please visit https://huggingface.co/mattaq/GelGenie-Universal-Dec-2023 and check the config.toml file. Our codebase is fully open-sourced and is available here: https://github.com/mattaq31/GelGenie.

A BioImage.IO version of this model is also available for download here.

Sources

1 source
Hugging FacePrincipalVersion 1845c27ab1ede277e23c8f3b284b16b50a5201c7
huggingface.co/cykavodka/GelGenie-Universal-Dec-2023/tree/1845c27ab1ede277e23c8f3b284b16b50a5201c7

Vérifié 1 sept.

Download files

Artefacts du modèle

4 artefacts

checkpoints/checkpoint_epoch_579.pth

pth · 164 MB · SHA-256 44a2d223c908…c329 · Hugging Face

Download file

onnx_checkpoints/unet_dec_21_epoch_579_fixed_dim_1024.onnx

onnx · 54,6 MB · SHA-256 56e335e59e85…ed29 · Hugging Face

Download file

onnx_checkpoints/unet_dec_21_epoch_579.onnx

onnx · 54,6 MB · SHA-256 10ea972a4062…9c48 · Hugging Face

Download file

torchscript_checkpoints/unet_dec_21_epoch_579.pt

pt · 54,9 MB · SHA-256 fcdca2fc286b…dfeb · Hugging Face

Download file

Extraits de sources

2 extraits
Readme1 sept.huggingface.co/cykavodka/GelGenie-Universal-Dec-2023

--- license: apache-2.0 pipeline_tag: image-segmentation library_name: pytorch --- This model consists of an SMP-UNet trained on the GelGenie training dataset in December 2023. It is highly robust and should produce good results for a wide variety of gel types and resolutions. This is the primary model that should be the first point of reference for any new gel analysis. The model was trained on the training set (420 images) for 600 epochs and the best checkpoint extracted based on the validation dice score. For more details on the configuration used for training, please visit https://huggingface.co/mattaq/GelGenie-Universal-Dec-2023 and check the config.toml file. Our codebase is fully open-sourced and is available here: https://github.com/mattaq31/GelGenie. A [BioImage.IO](https://bioimage.io/#/) version of this model is also available for download [here](https://huggingface.co/mattaq/GelGenie-Universal-Dec-2023/resolve/main/gelgenie_universal_model_bioimageio.zip).

Note1 sept.huggingface.co/cykavodka/GelGenie-Universal-Dec-2023

Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Library pytorch · Repo cykavodka/GelGenie-Universal-Dec-2023