%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Segformer B0 Finetuned Floorplan
Lightweight image segmentation model based on MIT-B0 architecture, fine-tuned specifically for floor plan segmentation tasks
Downloads 133
Release Time : 1/8/2025
Model Overview
This model is the B0 version of the SegFormer architecture, fine-tuned on the floorplan dataset based on the nvidia/mit-b0 foundation model, suitable for spatial segmentation tasks in architectural floor plans
Model Features
Lightweight Architecture
Lightweight design based on MIT-B0, suitable for deployment in resource-constrained environments
Floor Plan Specialization
Optimized for architectural floor plan data, effectively identifying room areas and background
Efficient Training
Achieves low validation loss (0.0034) with just 50 training epochs
Model Capabilities
Image semantic segmentation
Architectural floor plan analysis
Room area identification
Use Cases
Architectural Design
Automatic Floor Plan Parsing
Automatically identifies room areas and functional zones from scanned floor plans
Real Estate
Floor Plan Digitization
Converts paper floor plans into digital spatial structure data
đ segformer-b0-finetuned-floorplan
This model is a fine - tuned version of [nvidia/mit - b0](https://huggingface.co/nvidia/mit - b0) on the patnev71/floorplan dataset. It is designed for image segmentation tasks in the vision field, aiming to provide accurate segmentation results for floorplan images.
đ Quick Start
This fine - tuned model can be used for floorplan image segmentation tasks. You can load the model through relevant deep - learning frameworks and use it for inference on new floorplan images.
đ Documentation
Model description
This model is a fine - tuned version of [nvidia/mit - b0](https://huggingface.co/nvidia/mit - b0) on the patnev71/floorplan dataset. It achieves the following results on the evaluation set:
- Loss: 0.0034
- Mean Iou: 0.0
- Mean Accuracy: nan
- Overall Accuracy: nan
- Accuracy Background: nan
- Accuracy Room: nan
- Iou Background: 0.0
- Iou Room: 0.0
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 6e - 05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon = 1e - 08 and optimizer_args = No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Room | Iou Background | Iou Room |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.4537 | 0.4651 | 20 | 0.5128 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.2352 | 0.9302 | 40 | 0.3004 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.215 | 1.3953 | 60 | 0.1865 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.149 | 1.8605 | 80 | 0.1596 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.1142 | 2.3256 | 100 | 0.1121 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0981 | 2.7907 | 120 | 0.0978 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.09 | 3.2558 | 140 | 0.0726 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0631 | 3.7209 | 160 | 0.0562 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0558 | 4.1860 | 180 | 0.0542 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0446 | 4.6512 | 200 | 0.0439 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0481 | 5.1163 | 220 | 0.0397 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0323 | 5.5814 | 240 | 0.0398 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0323 | 6.0465 | 260 | 0.0302 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0235 | 6.5116 | 280 | 0.0352 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.024 | 6.9767 | 300 | 0.0331 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0211 | 7.4419 | 320 | 0.0258 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0193 | 7.9070 | 340 | 0.0202 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0198 | 8.3721 | 360 | 0.0194 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0185 | 8.8372 | 380 | 0.0219 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0209 | 9.3023 | 400 | 0.0188 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.014 | 9.7674 | 420 | 0.0187 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0124 | 10.2326 | 440 | 0.0165 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0125 | 10.6977 | 460 | 0.0141 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0117 | 11.1628 | 480 | 0.0157 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0139 | 11.6279 | 500 | 0.0124 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0111 | 12.0930 | 520 | 0.0151 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0121 | 12.5581 | 540 | 0.0132 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.008 | 13.0233 | 560 | 0.0116 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0097 | 13.4884 | 580 | 0.0127 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0122 | 13.9535 | 600 | 0.0116 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0063 | 14.4186 | 620 | 0.0118 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0096 | 14.8837 | 640 | 0.0102 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0094 | 15.3488 | 660 | 0.0111 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0073 | 15.8140 | 680 | 0.0100 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0062 | 16.2791 | 700 | 0.0103 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0051 | 16.7442 | 720 | 0.0085 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0055 | 17.2093 | 740 | 0.0097 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0074 | 17.6744 | 760 | 0.0107 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0067 | 18.1395 | 780 | 0.0073 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.005 | 18.6047 | 800 | 0.0076 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0049 | 19.0698 | 820 | 0.0086 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0044 | 19.5349 | 840 | 0.0064 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0052 | 20.0 | 860 | 0.0076 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0055 | 20.4651 | 880 | 0.0072 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0075 | 20.9302 | 900 | 0.0089 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0049 | 21.3953 | 920 | 0.0061 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0057 | 21.8605 | 940 | 0.0074 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0042 | 22.3256 | 960 | 0.0066 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0038 | 22.7907 | 980 | 0.0073 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0049 | 23.2558 | 1000 | 0.0061 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0039 | 23.7209 | 1020 | 0.0042 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0037 | 24.1860 | 1040 | 0.0053 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0032 | 24.6512 | 1060 | 0.0063 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0034 | 25.1163 | 1080 | 0.0060 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0032 | 25.5814 | 1100 | 0.0063 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0047 | 26.0465 | 1120 | 0.0061 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.003 | 26.5116 | 1140 | 0.0061 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0027 | 26.9767 | 1160 | 0.0058 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0025 | 27.4419 | 1180 | 0.0061 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0053 | 27.9070 | 1200 | 0.0054 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0039 | 28.3721 | 1220 | 0.0069 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0025 | 28.8372 | 1240 | 0.0062 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0026 | 29.3023 | 1260 | 0.0044 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0028 | 29.7674 | 1280 | 0.0063 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0022 | 30.2326 | 1300 | 0.0061 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0028 | 30.6977 | 1320 | 0.0054 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0025 | 31.1628 | 1340 | 0.0052 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0034 | 31.6279 | 1360 | 0.0056 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0029 | 32.0930 | 1380 | 0.0054 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0024 | 32.5581 | 1400 | 0.0050 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0028 | 33.0233 | 1420 | 0.0051 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0022 | 33.4884 | 1440 | 0.0054 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0022 | 33.9535 | 1460 | 0.0033 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0032 | 34.4186 | 1480 | 0.0038 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0029 | 34.8837 | 1500 | 0.0042 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0019 | 35.3488 | 1520 | 0.0042 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0025 | 35.8140 | 1540 | 0.0042 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.003 | 36.2791 | 1560 | 0.0035 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0023 | 36.7442 | 1580 | 0.0041 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.002 | 37.2093 | 1600 | 0.0038 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0022 | 37.6744 | 1620 | 0.0043 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0027 | 38.1395 | 1640 | 0.0034 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0019 | 38.6047 | 1660 | 0.0034 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0025 | 39.0698 | 1680 | 0.0033 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0019 | 39.5349 | 1700 | 0.0039 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0022 | 40.0 | 1720 | 0.0036 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0015 | 40.4651 | 1740 | 0.0037 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0025 | 40.9302 | 1760 | 0.0039 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0022 | 41.3953 | 1780 | 0.0040 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0018 | 41.8605 | 1800 | 0.0036 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0019 | 42.3256 | 1820 | 0.0031 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0028 | 42.7907 | 1840 | 0.0035 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0022 | 43.2558 | 1860 | 0.0035 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0015 | 43.7209 | 1880 | 0.0030 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.002 | 44.1860 | 1900 | 0.0030 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0018 | 44.6512 | 1920 | 0.0031 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0017 | 45.1163 | 1940 | 0.0034 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0025 | 45.5814 | 1960 | 0.0037 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0019 | 46.0465 | 1980 | 0.0039 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0016 | 46.5116 | 2000 | 0.0035 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0024 | 46.9767 | 2020 | 0.0037 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0018 | 47.4419 | 2040 | 0.0034 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0032 | 47.9070 | 2060 | 0.0035 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.002 | 48.3721 | 2080 | 0.0034 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0018 | 48.8372 | 2100 | 0.0037 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.002 | 49.3023 | 2120 | 0.0035 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
| 0.0019 | 49.7674 | 2140 | 0.0034 | 0.0 | nan | nan | nan | nan | 0.0 | 0.0 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
đ License
This model is under the other license.
Clipseg Rd64 Refined
Apache-2.0
CLIPSeg is an image segmentation model based on text and image prompts, supporting zero-shot and one-shot image segmentation tasks.
Image Segmentation
Transformers
TransformersC
CIDAS
10.0M
122
RMBG 1.4
Other
BRIA RMBG v1.4 is an advanced background removal model designed for efficiently separating foreground and background in various types of images, suitable for non-commercial use.
Image Segmentation Transformers
TransformersR
briaai
874.12k
1,771
RMBG 2.0
Other
The latest background removal model developed by BRIA AI, capable of effectively separating foreground and background in various images, suitable for large-scale commercial content creation scenarios.
Image Segmentation Transformers
TransformersR
briaai
703.33k
741
Segformer B2 Clothes
MIT
SegFormer model fine-tuned on ATR dataset for clothing and human segmentation
Image Segmentation Transformers
TransformersS
mattmdjaga
666.39k
410
Sam Vit Base
Apache-2.0
SAM is a vision model capable of generating high-quality object masks from input prompts (such as points or boxes), supporting zero-shot segmentation tasks
Image Segmentation Transformers Other
Transformers OtherS
facebook
635.09k
137
Birefnet
MIT
BiRefNet is a deep learning model for high-resolution binary image segmentation, which achieves accurate image segmentation through a bilateral reference network.
Image Segmentation Transformers
TransformersB
ZhengPeng7
626.54k
365
Segformer B1 Finetuned Ade 512 512
Other
SegFormer is a Transformer-based semantic segmentation model fine-tuned on the ADE20K dataset, suitable for image segmentation tasks.
Image Segmentation Transformers
TransformersS
nvidia
560.79k
6
Sam Vit Large
Apache-2.0
SAM is a visual model capable of generating high-quality object masks from input points or bounding boxes, with zero-shot transfer capability.
Image Segmentation Transformers Other
Transformers OtherS
facebook
455.43k
28
Face Parsing
Semantic segmentation model fine-tuned from nvidia/mit-b5 for face parsing tasks
Image Segmentation Transformers English
Transformers EnglishF
jonathandinu
398.59k
157
Sam Vit Huge
Apache-2.0
SAM is a vision model capable of generating high-quality object masks based on input prompts, supporting zero-shot transfer to new tasks
Image Segmentation Transformers Other
Transformers OtherS
facebook
324.78k
163
Featured Recommended AI Models
Š 2025AIbase