SegForCoral-b2-2025_06_24_45583-bs16_refine is a fine-tuned version of nvidia/mit-b2.

Model description

SegForCoral-b2-2025_06_24_45583-bs16_refine is a model built on top of nvidia/mit-b2 model for underwater multilabel image classification.The classification head is a combination of linear, ReLU, batch normalization, and dropout layers.

The source code for training the model can be found in this Git repository.

Developed by: lombardata, credits to César Leblanc and Victor Illien

Intended uses & limitations

You can use the raw model for classify diverse marine species, encompassing coral morphotypes classes taken from the Global Coral Reef Monitoring Network (GCRMN), habitats classes and seagrass species.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Number of Epochs: 22.0
Learning Rate: 1e-05
Train Batch Size: 16
Eval Batch Size: 16
Optimizer: Adam
LR Scheduler Type: ReduceLROnPlateau with a patience of 5 epochs and a factor of 0.1
Freeze Encoder: No
Data Augmentation: No

Training results

Epoch	Validation Loss	Learning Rate
1	0.653289794921875	1e-05
2	0.609367311000824	1e-05
3	0.582149088382721	1e-05
4	0.5670394897460938	1e-05
5	0.554327666759491	1e-05
6	0.5497708320617676	1e-05
7	0.5440376400947571	1e-05
8	0.5385246276855469	1e-05
9	0.5357204079627991	1e-05
10	0.531782865524292	1e-05
11	0.5508688688278198	1e-05
12	0.5295144319534302	1e-05
13	0.5301058292388916	1e-05
14	0.5334520936012268	1e-05
15	0.5511576533317566	1e-05
16	0.5356723666191101	1e-05
17	0.5746968984603882	1e-05
18	0.5447458028793335	1e-05
19	0.5349059700965881	1.0000000000000002e-06
20	0.5344632863998413	1.0000000000000002e-06
21	0.5357407331466675	1.0000000000000002e-06
22	0.5339811444282532	1.0000000000000002e-06

Framework Versions

Transformers: 4.51.3
Pytorch: 2.6.0+cu124
Datasets: 3.6.0
Tokenizers: 0.21.1