metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
model-index:
- name: fish_classification
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9969230769230769
- name: F1
type: f1
value: 0.9970182569296375
fish_classification
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2213
- Accuracy: 0.9969
- F1: 0.9970
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.5189 | 1.0 | 71 | 1.0828 | 0.9969 | 0.9970 |
| 0.7083 | 2.0 | 142 | 0.5398 | 0.9954 | 0.9955 |
| 0.3727 | 3.0 | 213 | 0.3473 | 0.9954 | 0.9955 |
| 0.2624 | 4.0 | 284 | 0.2734 | 0.9985 | 0.9985 |
| 0.2184 | 5.0 | 355 | 0.2401 | 0.9985 | 0.9985 |
| 0.1972 | 6.0 | 426 | 0.2238 | 0.9985 | 0.9985 |
| 0.1879 | 7.0 | 497 | 0.2213 | 0.9969 | 0.9970 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2