metadata
license: other
base_model: nvidia/mit-b0
tags:
- image-segmentation
- vision
- generated_from_trainer
model-index:
- name: baseline_plantorgans_model
results: []
baseline_plantorgans_model
This model is a fine-tuned version of nvidia/mit-b0 on the jpodivin/plantorgans dataset. It achieves the following results on the evaluation set:
- Loss: 0.5639
- Mean Iou: 0.1095
- Mean Accuracy: 0.1373
- Overall Accuracy: 0.1858
- Accuracy Void: nan
- Accuracy Fruit: 0.5208
- Accuracy Leaf: 0.0197
- Accuracy Flower: 0.0
- Accuracy Stem: 0.0087
- Iou Void: 0.0
- Iou Fruit: 0.5192
- Iou Leaf: 0.0197
- Iou Flower: 0.0
- Iou Stem: 0.0087
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Void | Accuracy Fruit | Accuracy Leaf | Accuracy Flower | Accuracy Stem | Iou Void | Iou Fruit | Iou Leaf | Iou Flower | Iou Stem |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.8673 | 1.0 | 719 | 0.4827 | 0.1301 | 0.1639 | 0.2227 | nan | 0.6188 | 0.0271 | 0.0 | 0.0098 | 0.0 | 0.6135 | 0.0271 | 0.0 | 0.0098 |
| 0.4457 | 2.0 | 1438 | 0.5555 | 0.1130 | 0.1416 | 0.1927 | nan | 0.5224 | 0.0305 | 0.0 | 0.0135 | 0.0 | 0.5209 | 0.0305 | 0.0 | 0.0135 |
| 0.3272 | 3.0 | 2157 | 0.5639 | 0.1095 | 0.1373 | 0.1858 | nan | 0.5208 | 0.0197 | 0.0 | 0.0087 | 0.0 | 0.5192 | 0.0197 | 0.0 | 0.0087 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0