Skip to page content
SAVRN
Search Plan a project

Open-weight model · Image segmentation

gap-efficient-sam

by Truong KhangTruong/gap-efficient-sam

gap-efficient-sam is an open-weight model for image segmentation from Truong, released under Apache License 2.0. Its published files total 1.7 GB. It draws 38 downloads a month.

Official repository for gap-efficient-sam checkpoints, evaluated on AI-generated image detection and segmentation tasks. To download the latest checkpoint directly to your local workspace

Parameters—
Context—
Weights1.7 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads38

Model Card

By Truong, published under apache-2.0, revision c2fc2b3921e8.

Official repository for gap-efficient-sam checkpoints, evaluated on AI-generated image detection and segmentation tasks. To download the latest checkpoint directly to your local workspace

Read Truong's full model card

Official repository for gap-efficient-sam checkpoints, evaluated on AI-generated image detection and segmentation tasks.

Available Versions

Version Best Metric Score Best Epoch Updated
v1 0.5743321430499237 -1 2026-10-12
  • Active Version: v1
  • Best Validation Score: 0.5743321430499237 (Epoch -1)
  • Total Training Epochs: 1

Quickstart & Checkpoint Usage

1. Pull checkpoints using sid-pull

To download the latest checkpoint directly to your local workspace:

sid-pull --name KhangTruong/gap-efficient-sam

To pull a specific version:

sid-pull --name KhangTruong/gap-efficient-sam --version v1

2. Resume or Fine-tune with sid-train

Once downloaded, resume training seamlessly:

sid-train --config configs/experiments/diffusion_diff_minimized/default.yaml --override training.epochs=40

Or specify explicit checkpoint path:

sid-train --resume checkpoints/checkpoint_latest.pt

3. Push new checkpoints using sid-push

sid-push --name KhangTruong/gap-efficient-sam --version v2

Repository Layout

KhangTruong/gap-efficient-sam/
├── README.md               # Model Card & Documentation
├── config.yaml             # Model & Training Configuration
├── manifest.json           # Catalog of all versions & metrics
├── checkpoints/            # Active / Latest Checkpoints
│   ├── checkpoint_best.pt
│   ├── checkpoint_latest.pt
│   └── checkpoint_periodic.pt
├── reports/                # Evaluation reports & plots
│   ├── training_curves.png
│   └── test_evaluation_report.json
└── versions/               # Version Archive
    └── v1/
        ├── checkpoints/
        └── reports/

Identity and Version

Repository
KhangTruong/gap-efficient-sam
Publisher
Truong
Task
Image segmentation
Modality
Image
Library
sid-unet
Parameters
Not stated by the source
Languages
sid-unet
Revision
c2fc2b3921e83c4c9c89dd3791b24afc9bc0c0cd
First published
2026-10-09
Last updated
2026-10-12

Files and Weights

27 files, 1.7 GB in total. The weights are 6 files totalling 1.7 GB in pt.

Weights6 files · 1.7 GB
Configuration15 files · 51.9 KB
Documentation5 files · 13.4 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
checkpoints/checkpoint_best.ptWeights1.2 KB cd31e5a0a7f8
checkpoints/checkpoint_latest.ptWeights432.2 MB 5a83766f8a4f
checkpoints/checkpoint_periodic.ptWeights432.2 MB c827c64888aa
versions/v1/checkpoints/checkpoint_best.ptWeights1.2 KB cd31e5a0a7f8
versions/v1/checkpoints/checkpoint_latest.ptWeights432.2 MB 5a83766f8a4f
versions/v1/checkpoints/checkpoint_periodic.ptWeights432.2 MB c827c64888aa
checkpoints/checkpoint_latest_config.yamlConfiguration3.3 KB —
checkpoints/checkpoint_periodic_config.yamlConfiguration3.3 KB —
checkpoints/effective_config.yamlConfiguration3.2 KB —
config.yamlConfiguration3.3 KB —
manifest.jsonConfiguration390 B —
reports/test_evaluation_report.jsonConfiguration7.0 KB —
reports/training_final_report.jsonConfiguration7.1 KB —
reports/training_history.jsonConfiguration2 B —
versions/v1/checkpoint_latest_config.yamlConfiguration3.3 KB —
versions/v1/checkpoint_periodic_config.yamlConfiguration3.3 KB —
versions/v1/effective_config.yamlConfiguration3.2 KB —
versions/v1/manifest.jsonConfiguration390 B —
versions/v1/reports/test_evaluation_report.jsonConfiguration7.0 KB —
versions/v1/reports/training_final_report.jsonConfiguration7.1 KB —
versions/v1/reports/training_history.jsonConfiguration2 B —
README.mdDocumentation2.1 KB —
reports/test_evaluation_report.mdDocumentation2.8 KB —
reports/training_final_report.mdDocumentation2.9 KB —
versions/v1/reports/test_evaluation_report.mdDocumentation2.8 KB —
versions/v1/reports/training_final_report.mdDocumentation2.9 KB —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
1.7 GB
Download from Truong

Released by Truong through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published1.7 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About gap-efficient-sam

Can I use gap-efficient-sam commercially?

Yes. gap-efficient-sam is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Image segmentation

segformer-b2-finetuned-ade-512-512

NVIDIA

SegFormer model fine-tuned on ADE20k at resolution 512x512. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository. Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team. SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is first pre-trained on ImageNet-1k, after which a decode head is added and fine-tuned altogether on a…

Open weights other transformers
View model

Model · Image segmentation

segformer-b3-finetuned-ade-512-512

NVIDIA

SegFormer model fine-tuned on ADE20k at resolution 512x512. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository. Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team. SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is first pre-trained on ImageNet-1k, after which a decode head is added and fine-tuned altogether on a…

Open weights other transformers
View model

Model · Image segmentation

oneformer_ade20k_swin_large

SHI Labs

OneFormer model trained on the ADE20k dataset (large-sized version, Swin backbone). It was introduced in the paper OneFormer: One Transformer to Rule Universal Image Segmentation by Jain et al. and first released in this repository. OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing specialized models across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task-guided for training, and task-dynamic for inference, all with a single…

Open weights mit transformers
View model

Model · Image segmentation

segformer-b1-finetuned-ade-512-512

NVIDIA

SegFormer model fine-tuned on ADE20k at resolution 512x512. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository. Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team. SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is first pre-trained on ImageNet-1k, after which a decode head is added and fine-tuned altogether on a…

Open weights other transformers
View model

Model · Image segmentation

segformer-b0-finetuned-ade-512-512

Joshua

https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Example: Image segmentation with Xenova/segformer-b0-finetuned-ade-512-512. You can visualize the outputs with: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Open weights transformers.js
View model

Model · Image segmentation

DelineateAnything

Mykola Lavreniuk

Delineate Anything v2 extends Delineate Anything into a globally representative, resolution-agnostic foundation model that scales agricultural field boundary detection to a planetary level from any imagery source. Trained on FBIS-73M, a massive 73-million-instance dataset spanning 61 countries with diverse imagery sources ranging from 0.25m to 10m resolution, built through a resolution-specific curation pipeline that solves the parcel-versus-field mismatch, Delineate Anything v2 sets a new state-of-the-art in global zero-shot delineation. It delivers a +103.3% relative gain in [email protected] over Delineate Anything while maintaining extreme efficiency, mapping all of Ukraine (603,000 km²) in 5.4…

Open weights agpl-3.0 ultralytics
View model