# segformer_b2_clothes by Mateusz Dziemian: Open-Weight Model Source: https://savrn.com/models/segformer-b2-clothes Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve segformer_b2_clothes (27M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [segformer_b2_clothes on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/segformer-b2-clothes/gpus) ## SAVRN's Notes on segformer_b2_clothes This SegFormer model labels clothing and body parts pixel by pixel: hat, hair, sunglasses, upper clothes, skirt, pants, shoes, bags and more. It was trained on the ATR human parsing dataset and has 27M parameters. The license is listed as other, so check the terms and the terms of the NVIDIA SegFormer base before commercial use. It is popular for virtual try-on and fashion tools, with more than 500 likes. SAVRN Research, 2026-09-18 ## Model Card SegFormer model fine-tuned on ATR dataset for clothes segmentation but can also be used for human segmentation. The dataset on hugging face is called "mattmdjaga/humanparsingdataset". Labels: 0: "Background", 1: "Hat", 2: "Hair", 3: "Sunglasses", 4: "Upper-clothes", 5: "Skirt", 6: "Pants", 7: "Dress", 8: "Belt", 9: "Left-shoe", 10: "Right-shoe", 11: "Face", 12: "Left-leg", 13: "Right-leg", 14: "Left-arm", 15: "Right-arm", 16: "Bag", 17: "Scarf" The license for this model can be found here. Excerpt from the card by Mateusz Dziemian, licensed other. ## Configuration Architecture SegformerForSemanticSegmentation Stored precision float32 Model type segformer ## Identity and Version Repository mattmdjaga/segformer_b2_clothes Publisher Mateusz Dziemian Task Image segmentation Modality Image Library transformers Parameters 27M parameters Languages Not stated by the source Revision 584abc1e1d260e23c0fc627c5217a09b2b461046 First published 2022-11-24 Last updated 2025-09-19 ## Files and Weights 17 files, 548.5 MB in total. The weights are 7 files totalling 548.2 MB in bin, onnx, pt, pth, safetensors. Weights7 files · 548.2 MB Configuration7 files · 301.9 KB Documentation1 file · 4.4 KB Repository2 files · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 109.5 MB | 8f86fd90c567 | | onnx/model.onnx | Weights | 110.0 MB | a93a8dac171b | | optimizer.pt | Weights | 219.1 MB | 4f642f5c29cb | | pytorch_model.bin | Weights | 109.6 MB | 934543143c97 | | rng_state.pth | Weights | 14.6 KB | a7c38376dfee | | scheduler.pt | Weights | 627 B | 7a9a297dec0f | | training_args.bin | Weights | 3.3 KB | 210f58c34439 | | config.json | Configuration | 1.7 KB | — | | handler.py | Configuration | 1.5 KB | — | | mattmdjaga_segformer_b2_clothes.json | Configuration | 4.9 KB | — | | onnx/config.json | Configuration | 1.7 KB | — | | onnx/preprocessor_config.json | Configuration | 431 B | — | | preprocessor_config.json | Configuration | 271 B | — | | trainer_state.json | Configuration | 291.3 KB | — | | README.md | Documentation | 4.4 KB | — | | .gitattributes | Repository | 1.5 KB | — | | .gitignore | Repository | 29 B | — | ## License and Download License other Access Open weights, no gate Download size 548.2 MB [Download from Mateusz Dziemian](https://huggingface.co/mattmdjaga/segformer_b2_clothes) Released by Mateusz Dziemian through its official repository on Hugging Face. ## Built From - Described by [arXiv:2105.15203](https://savrn.com/papers/segformer-simple-and-efficient-design-for-semantic-segmentation-with-transformers) - Trained on (disclosed) mattmdjaga/human_parsing_dataset ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 548.2 MB | | 16-bit | 0.1 GB | | 8-bit | 0.0 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About segformer_b2_clothes ### How much GPU memory does segformer_b2_clothes need? About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (27M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run segformer_b2_clothes on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### What license is segformer_b2_clothes released under? other, as its publisher declares it. Read the license text before commercial use. ## Similar Models Model · Image segmentation ### [car-damage-photo-integrity-v9](https://savrn.com/models/car-damage-photo-integrity-v9) [Sai Charan Obuladinne](https://savrn.com/model-publishers/obuladinnesai) A PyTorch research model for detecting and localizing AI-edited regions in car-damage photos. It focuses on localized inpainting that adds, removes or exaggerates vehicle damage, and returns a tamper heatmap, an image-level suspicion score and a threshold-based flag. Use it to explore image manipulation detection, diffusion inpainting detection and vehicle-photo integrity with the supplied local inference code. It does not assess damage severity, estimate repair costs or prove fraud. Fully AI-generated scenes are a documented weak case. Author: Sai Charan Obuladinne · Framework: PyTorch · Weights: Safetensors · Declared repository license: Apache-2.0; see the upstream-data caveat below.… Open weights apache-2.0 29M parameters pytorch [View model](https://savrn.com/models/car-damage-photo-integrity-v9) Model · Image segmentation ### [videomt-dinov2-small-ytvis2019](https://savrn.com/models/videomt-dinov2-small-ytvis2019) [Mobile Perception Systems Lab](https://savrn.com/model-publishers/tue-mps) This repository contains the Hugging Face Transformers conversion of the official VidEoMT checkpoint yt2019vitsmall52.8.pth from tue-mps/VidEoMT. The metrics above are the numbers reported by the authors in the official model zoo. Use processor.postprocessinstancesegmentation, processor.postprocesspanopticsegmentation, or processor.postprocesssemanticsegmentation depending on the target task. Open weights 24M parameters transformers [View model](https://savrn.com/models/videomt-dinov2-small-ytvis2019) Model · Image segmentation ### [rf-detr-seg-nano](https://savrn.com/models/rf-detr-seg-nano) [Roboflow](https://savrn.com/model-publishers/roboflow) RF-DETR is a real-time detection transformer family introduced in RF-DETR: Neural Architecture Search for Real-Time Detection Transformers by Robinson et al. and integrated in Transformers via PR #36895. RF-DETR is an end-to-end instance segmentation model that combines ideas from LW-DETR and Deformable DETR: a DINOv2-with-registers style ViT backbone (with an RF-DETR windowing pattern for efficient attention), a multi-scale projector between encoder and decoder, and a multi-scale deformable DETR decoder extended with an instance-segmentation head. You can use the raw model for instance segmentation; it predicts per-instance masks together with bounding boxes and class scores. See the model… Open weights apache-2.0 34M parameters transformers [View model](https://savrn.com/models/rf-detr-seg-nano) Model · Image segmentation ### [DART-Seg](https://savrn.com/models/dart-seg) [Swarna](https://savrn.com/model-publishers/koushik45048545309) Text-prompted 3D CT segmentation. Name a structure, get its mask. 286 anatomical structures and lesions, 39M parameters, trained from scratch. ONLY PROMPT FOR THE STRUCTURES YOU NEED. Prompting for unnecessary or anatomically absent structures may cause hallucinations and false-positive segmentations. After inference, DART-Seg may produce fragments. Use the below postprocessing to fix that. Quote prompts and paths that contain spaces, e.g. --prompts "left kidney" or --image "my scan.nii.gz". Python API (run from inside the downloaded folder so dartseg.py is importable): - Residual 3D U-Net; each prompt's text embedding attends to image features and produces its mask. All prompts share one… Open weights cc-by-nc-sa-4.0 39M parameters pytorch [View model](https://savrn.com/models/dart-seg) Model · Image segmentation ### [maskformer-swin-tiny-coco](https://savrn.com/models/maskformer-swin-tiny-coco) [AI at Meta](https://savrn.com/model-publishers/facebook) MaskFormer model trained on COCO panoptic segmentation (tiny-sized version, Swin backbone). It was introduced in the paper Per-Pixel Classification is Not All You Need for Semantic Segmentation and first released in this repository. Disclaimer: The team releasing MaskFormer did not write a model card for this model so this model card has been written by the Hugging Face team. MaskFormer addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. You can use this particular checkpoint for semantic segmentation. See the model hub to look for other… Open weights other 42M parameters transformers [View model](https://savrn.com/models/maskformer-swin-tiny-coco) Model · Image segmentation ### [RMBG-1.4](https://savrn.com/models/rmbg-1-4) [BRIA AI](https://savrn.com/model-publishers/briaai) RMBG v1.4 is our state-of-the-art background removal model, designed to effectively separate foreground from background in a range of categories and image types. This model has been trained on a carefully selected dataset, which includes: general stock images, e-commerce, gaming, and advertising content, making it suitable for commercial use cases powering enterprise content creation at scale. The accuracy, efficiency, and versatility currently rival leading source-available models. It is ideal where content safety, legally licensed datasets, and bias mitigation are paramount. Developed by BRIA AI, RMBG v1.4 is available as a source-available model for non-commercial use. To purchase a… Open weights other 44M parameters transformers [View model](https://savrn.com/models/rmbg-1-4) ## Mateusz Dziemian [All models and datasets](https://savrn.com/model-publishers/mattmdjaga) ## Versions - [584abc1e1d26](https://savrn.com/models/segformer-b2-clothes/versions/584abc1e1d26) · current 2026-09-18 ## Explore More - [All image segmentation models](https://savrn.com/models/tasks/image-segmentation) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/mattmdjaga/segformer_b2_clothes) - [How the hub is built](https://savrn.com/model-hub/methodology)