segformer-homux-interior

Davidts/segformer-homux-interior

segformer-homux-interior is a image segmentation model from Davidts. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

14% of all-time downloads

All-time downloads

153

Public

Parameters

27.4M

657 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors109 MB · 100%

At a glance

Task: Image Segmentation
Library: transformers
License: other
Model type: segformer
Access: Public
Created: Mar 12, 2026
Updated: Mar 13, 2026
SHA: 02bd4759

Base models

nvidia/segformer-b2-finetuned-ade-512-512

Spaces

umang2191/room-surface-studio

Model card

From the Hugging Face model README

segformer-homux-interior

This model is a fine-tuned version of nvidia/segformer-b2-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3125
Mean Iou: 0.7710
Mean Accuracy: 0.8686
Overall Accuracy: 0.8805
Per Category Iou: [0.8225759368873339, 0.7214708108904201, 0.7689017068739673]
Per Category Accuracy: [0.9046095590958206, 0.8360629339483715, 0.8650707644388027]

Model description

More information needed

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 200
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Per Category Iou	Per Category Accuracy
0.3281	0.5	334	0.3519	0.7379	0.8415	0.8614	[0.796996078509595, 0.6861837251111725, 0.7306086868771977]	[0.8923095435453426, 0.8139671019147643, 0.818195333470989]
0.2731	1.0	668	0.3177	0.7580	0.8559	0.8743	[0.8168826352930761, 0.7010385023155785, 0.7561036197652337]	[0.9165844481398346, 0.7912322773333116, 0.8599388168566798]
0.243	1.5	1002	0.3105	0.7626	0.8562	0.8776	[0.8208011914809089, 0.7133892465362764, 0.7537049097215778]	[0.9152797105709557, 0.8141868156990059, 0.8391208523276643]
0.2326	2.0	1336	0.3113	0.7691	0.8634	0.8802	[0.8235077706490904, 0.7166765608276489, 0.7670094438911704]	[0.9148524604655109, 0.815721400291319, 0.8595021383622881]
0.2185	2.5	1670	0.3127	0.7684	0.8613	0.8805	[0.8243368214294293, 0.7181819386653856, 0.7627792135543665]	[0.9176388931848591, 0.8141817909046856, 0.85198095474657]
0.2049	3.0	2004	0.3125	0.7710	0.8686	0.8805	[0.8225759368873339, 0.7214708108904201, 0.7689017068739673]	[0.9046095590958206, 0.8360629339483715, 0.8650707644388027]

Framework versions

Transformers 4.44.2
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.19.1

Task: Image Segmentation
Library: transformers
Type: segformer
License: other
Created: Mar 12, 2026
Updated: Mar 13, 2026