NGIML performs single-image forgery localization from a pretrained checkpoint and an input RGB image.
Fuente del modelo
Descripción de la fuente
NGIML performs single-image forgery localization from a pretrained checkpoint and an input RGB image.
Pretrained checkpoints are hosted on Hugging Face:
Fuentes
1 fuenteVerificado 8 sept
Artefactos del modelo
11 artefactosExtractos de fuentes
2 extractosCASIA2-EffNet-42.pt (110 MB)CASIA2-EffNet+Noise-42.pt (172 MB)CASIA2-EffNet+Swin-42.pt (593 MB)CASIA2-Full-42.pt (618 MB)CASIA2-Full-4.pt (618 MB)CASIA2-Full-420.pt (618 MB)CASIA2-Full(mbconv)-42.pt (611 MB)CASIA2-Swin-42.pt (495 MB)CASIA2-Swin+Noise-42.pt (556 MB)CCC-Full-42.pt (618 MB)TampCOCO-Full-42.pt (618 MB)The easiest way to test the model is through Colab:
infer.ipynb in ColabThis is the recommended path for quick testing because the notebook is already set up for checkpoint-based inference.
If you want to run the project locally, use the repository files here:
Install the dependencies:
pip install -r requirements.txt
CASIA2-EffNet+Swin-42.pt
pt · 565 MB · SHA-256 643d37b2d452…a59a · Hugging Face
--- license: apache-2.0 language: - en pipeline_tag: image-segmentation tags: - manipulation - forgery - image - cnn - transformer - residual-noise - efficientnet - swin - localization --- # NGIML Model Card ## Inference NGIML performs single-image forgery localization from a pretrained checkpoint and an input RGB image. --- ## Checkpoints Pretrained checkpoints are hosted on Hugging Face: [juhenes/ngiml](https://huggingface.co/juhenes/ngiml) ### CASIA2 / Extended Models - `CASIA2-EffNet-42.pt` (110 MB) - `CASIA2-EffNet+Noise-42.pt` (172 MB) - `CASIA2-EffNet+Swin-42.pt` (593 MB) - `CASIA2-Full-42.pt` (618 MB) - `CASIA2-Full-4.pt` (618 MB) - `CASIA2-Full-420.pt` (618 MB) - `CASIA2-Full(mbconv)-42.pt` (611 MB) - `CASIA2-Swin-42.pt` (495 MB) - `CASIA2-Swin+Noise-42.pt` (556 MB) ### Additional Datasets / Models - `CCC-Full-42.pt` (618 MB) - `TampCOCO-Full-42.pt (618 MB)` ## Run Inference ### Recommended: Google Colab The easiest way to test the model is through Colab: - Google Colab: [Open `infer.ipynb` in Colab](https://colab.research.google.com/github/juhenes/ngiml-infer/blob/main/infer.ipynb) This is the recommended path for quick testing because the notebook is already set up for checkpoint-based inference. --- ### Local CLI If you want to run the project locally, use the repository files here: - GitHub: [juhenes/ngiml-infer](https://github.com/juhenes/ngiml-infer) Install the dependencies: ```bash pip install -r requirements.txt
Source context: 0 downloads · 0 likes · Pipeline image-segmentation · Repo juhenes/ngiml