segformer-b0-finetuned-net-4Sep

PushkarA07/segformer-b0-finetuned-net-4Sep

segformer-b0-finetuned-net-4Sep is a image segmentation model from PushkarA07. 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

3% of all-time downloads

All-time downloads

271

Public

Parameters

3.7M

149 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors14.9 MB · 100%

At a glance

Task: Image Segmentation
Library: transformers
License: other
Model type: segformer
Access: Public
Created: Sep 4, 2025
Updated: Oct 17, 2025
SHA: bfc76b1b

Model card

From the Hugging Face model README

segformer-b0-finetuned-net-4Sep

This model is a fine-tuned version of PushkarA07/segformer-b0-finetuned-net-4Sep on the PushkarA07/batch2-tiles_W5 dataset. It achieves the following results on the evaluation set:

Loss: 0.0035
Mean Iou: 0.8702
Mean Accuracy: 0.9096
Overall Accuracy: 0.9987
Accuracy Abnormality: 0.8196
Iou Abnormality: 0.7417

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: 1e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Abnormality	Iou Abnormality
0.0025	0.4348	10	0.0035	0.8709	0.9118	0.9987	0.8241	0.7432
0.0044	0.8696	20	0.0035	0.8703	0.9105	0.9987	0.8215	0.7420
0.0128	1.3043	30	0.0035	0.8701	0.9090	0.9987	0.8185	0.7415
0.0056	1.7391	40	0.0035	0.8700	0.9087	0.9987	0.8180	0.7413
0.0083	2.1739	50	0.0035	0.8702	0.9100	0.9987	0.8205	0.7418
0.0051	2.6087	60	0.0035	0.8703	0.9101	0.9987	0.8207	0.7420
0.0075	3.0435	70	0.0036	0.8704	0.9111	0.9987	0.8227	0.7422
0.0078	3.4783	80	0.0035	0.8704	0.9105	0.9987	0.8214	0.7421
0.0033	3.9130	90	0.0035	0.8706	0.9118	0.9987	0.8241	0.7426
0.0062	4.3478	100	0.0035	0.8702	0.9111	0.9987	0.8227	0.7418
0.003	4.7826	110	0.0036	0.8699	0.9088	0.9987	0.8181	0.7412
0.0114	5.2174	120	0.0035	0.8699	0.9087	0.9987	0.8178	0.7412
0.014	5.6522	130	0.0036	0.8699	0.9086	0.9987	0.8177	0.7412
0.0118	6.0870	140	0.0035	0.8700	0.9086	0.9987	0.8176	0.7413
0.0058	6.5217	150	0.0036	0.8701	0.9098	0.9987	0.8201	0.7416
0.0109	6.9565	160	0.0035	0.8701	0.9096	0.9987	0.8197	0.7416
0.0044	7.3913	170	0.0036	0.8708	0.9126	0.9987	0.8257	0.7429
0.0036	7.8261	180	0.0035	0.8704	0.9104	0.9987	0.8213	0.7422
0.0143	8.2609	190	0.0035	0.8701	0.9089	0.9987	0.8183	0.7415
0.0083	8.6957	200	0.0035	0.8705	0.9110	0.9987	0.8224	0.7424
0.0039	9.1304	210	0.0035	0.8704	0.9108	0.9987	0.8220	0.7421
0.0053	9.5652	220	0.0036	0.8704	0.9108	0.9987	0.8222	0.7421
0.0045	10.0	230	0.0035	0.8702	0.9096	0.9987	0.8196	0.7417

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu126
Datasets 4.2.0
Tokenizers 0.22.1

Task: Image Segmentation
Library: transformers
Type: segformer
License: other
Created: Sep 4, 2025
Updated: Oct 17, 2025