model2

giuseppemartino/model2

model2 is a image segmentation model from giuseppemartino. 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

2% of all-time downloads

All-time downloads

600

Public

Repo size

1.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin110 MB · 100%

At a glance

Task: Image Segmentation
Library: transformers
License: other
Model type: segformer
Access: Public
Created: Oct 15, 2023
Updated: Oct 15, 2023
SHA: 6ed63112

Base models

nvidia/mit-b2

Model card

From the Hugging Face model README

model2

This model is a fine-tuned version of nvidia/mit-b2 on the giuseppemartino/isaid_sam_predicted dataset. It achieves the following results on the evaluation set:

Loss: 0.2318
Mean Iou: 0.2504
Mean Accuracy: 0.3019
Overall Accuracy: 0.4542
Accuracy Background: nan
Accuracy Ship: 0.6330
Accuracy Small-vehicle: 0.4644
Accuracy Tennis-court: 0.0280
Accuracy Helicopter: nan
Accuracy Basketball-court: 0.0
Accuracy Ground-track-field: 0.6010
Accuracy Swimming-pool: nan
Accuracy Harbor: 0.4575
Accuracy Soccer-ball-field: 0.7776
Accuracy Plane: nan
Accuracy Storage-tank: 0.0
Accuracy Baseball-diamond: nan
Accuracy Large-vehicle: 0.3594
Accuracy Bridge: 0.0
Accuracy Roundabout: 0.0
Iou Background: 0.0
Iou Ship: 0.5194
Iou Small-vehicle: 0.4368
Iou Tennis-court: 0.0280
Iou Helicopter: nan
Iou Basketball-court: 0.0
Iou Ground-track-field: 0.5492
Iou Swimming-pool: nan
Iou Harbor: 0.3611
Iou Soccer-ball-field: 0.7592
Iou Plane: nan
Iou Storage-tank: 0.0
Iou Baseball-diamond: nan
Iou Large-vehicle: 0.3508
Iou Bridge: 0.0
Iou Roundabout: 0.0

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: 8
eval_batch_size: 8
seed: 1337
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: polynomial
training_steps: 1345

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Background	Accuracy Ship	Accuracy Small-vehicle	Accuracy Tennis-court	Accuracy Helicopter	Accuracy Ground-track-field	Accuracy Swimming-pool	Accuracy Harbor	Accuracy Soccer-ball-field	Accuracy Plane	Accuracy Baseball-diamond	Accuracy Large-vehicle	Iou Ship	Iou Small-vehicle	Iou Tennis-court	Iou Helicopter	Iou Ground-track-field	Iou Swimming-pool	Iou Harbor	Iou Soccer-ball-field	Iou Plane	Iou Baseball-diamond	Iou Large-vehicle
1.1413	1.0	113	0.5054	0.0431	0.0841	0.0445	nan	0.0611	0.0179	0.0079	nan	0.0	nan	0.8374	0.0	nan	nan	0.0010	0.0592	0.0178	0.0079	nan	0.0	nan	0.4319	0.0	nan	nan	0.0010
0.326	2.0	226	0.3240	0.0756	0.1192	0.2144	nan	0.0433	0.1690	0.0	nan	0.0	nan	0.8062	0.0	nan	nan	0.2926	0.0430	0.1614	0.0	nan	0.0	nan	0.4129	0.0	nan	nan	0.2904
0.1849	3.0	339	0.2807	0.1589	0.2164	0.3238	nan	0.3520	0.3125	0.0	nan	0.3563	nan	0.6252	0.4509	nan	nan	0.2835	0.3236	0.2894	0.0	nan	0.3265	0.0	0.3954	0.4506	nan	nan	0.2807
0.1341	4.0	452	0.2694	0.1618	0.2309	0.3055	nan	0.2089	0.3628	0.0188	nan	0.4866	nan	0.7552	0.5206	nan	nan	0.1866	0.2004	0.3303	0.0188	nan	0.4268	0.0	0.4221	0.5205	nan	nan	0.1840
0.1282	5.0	565	0.2631	0.2057	0.2726	0.3396	nan	0.4061	0.3347	0.0292	nan	0.6126	nan	0.6152	0.8252	nan	nan	0.1751	0.3667	0.3169	0.0292	nan	0.4767	nan	0.3995	0.7049	nan	nan	0.1745
0.1138	6.0	678	0.2418	0.1949	0.2558	0.3865	nan	0.2362	0.3709	0.0122	nan	0.6128	nan	0.6627	0.5823	nan	nan	0.3365	0.2249	0.3444	0.0122	nan	0.4625	nan	0.3921	0.5725	nan	nan	0.3301
0.1049	7.0	791	0.2345	0.2013	0.2623	0.4725	nan	0.3186	0.4071	0.0827	nan	0.1697	nan	0.7809	0.6140	nan	nan	0.5118	0.2927	0.3851	0.0827	nan	0.1679	nan	0.4702	0.5212	nan	nan	0.4961
0.0829	8.0	904	0.2351	0.2194	0.2818	0.4348	nan	0.1689	0.4289	0.0980	nan	0.5547	nan	0.7050	0.7860	nan	nan	0.3580	0.1619	0.4048	0.0980	nan	0.5205	nan	0.3967	0.7023	nan	nan	0.3490
0.0922	9.0	1017	0.2350	0.2549	0.3103	0.5060	nan	0.4729	0.4726	0.0572	nan	0.5679	nan	0.5794	0.7942	nan	nan	0.4690	0.4143	0.4398	0.0572	nan	0.5293	nan	0.4010	0.7613	nan	nan	0.4563
0.0717	10.0	1130	0.2399	0.2344	0.2871	0.4150	nan	0.4512	0.4155	0.0169	nan	0.5706	nan	0.6279	0.7676	nan	nan	0.3089	0.3995	0.3949	0.0169	nan	0.5351	nan	0.4246	0.7393	nan	nan	0.3023
0.0787	11.0	1243	0.2228	0.2578	0.3105	0.4726	nan	0.6679	0.4378	0.0666	nan	0.5865	nan	0.4684	0.7796	nan	nan	0.4087	0.5359	0.4172	0.0666	nan	0.5456	nan	0.3785	0.7528	nan	nan	0.3975
0.0787	11.9	1345	0.2318	0.2504	0.3019	0.4542	nan	0.6330	0.4644	0.0280	nan	0.6010	nan	0.4575	0.7776	nan	nan	0.3594	0.5194	0.4368	0.0280	nan	0.5492	nan	0.3611	0.7592	nan	nan	0.3508

Framework versions

Transformers 4.35.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1

Task: Image Segmentation
Library: transformers
Type: segformer
License: other
Created: Oct 15, 2023
Updated: Oct 15, 2023