segformer-b0-finetuned-fish-almogm
This model is a fine-tuned version of nvidia/mit-b0 on the None dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.0068
- eval_mean_iou: 0.4831
- eval_mean_accuracy: 1.0000
- eval_overall_accuracy: 1.0000
- eval_accuracy_background: 1.0000
- eval_accuracy_fish: nan
- eval_iou_background: 0.9662
- eval_iou_fish: 0.0
- eval_runtime: 62.449
- eval_samples_per_second: 0.801
- eval_steps_per_second: 0.4
- epoch: 6.46
- step: 640
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2