BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze

BeitEAU is a fine-tuned version of BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze. It achieves the following results on the test set:

• Loss: 0.1647
• F1 Micro: 0.7446
• F1 Macro: 0.6015
• Accuracy: 0.2171

---

Model description

BeitEAU is a model built on top of BeitEAU-base-patch16-384-2025_11_07_78282-bs32_freeze 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 and evaluation data

Details on the number of images for each class are given in the following table:

---

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• Number of Epochs: 61.0
• Learning Rate: 0.001
• Train Batch Size: 32
• Eval Batch Size: 32
• Optimizer: Adam
• LR Scheduler Type: ReduceLROnPlateau with a patience of 5 epochs and a factor of 0.1
• Freeze Encoder: Yes
• Data Augmentation: Yes

Data Augmentation

Data were augmented using the following transformations :

Train Transforms

• PreProcess: No additional parameters
• Resize: probability=1.00
• RandomHorizontalFlip: probability=0.25
• RandomVerticalFlip: probability=0.25
• ColorJiggle: probability=0.25
• RandomPerspective: probability=0.25
• Normalize: probability=1.00

Val Transforms

• PreProcess: No additional parameters
• Resize: probability=1.00
• Normalize: probability=1.00

Training results

---

Framework Versions

• Transformers: 4.56.0.dev0
• Pytorch: 2.6.0+cu124
• Datasets: 3.0.2
• Tokenizers: 0.21.0