metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-Landscape_Recognition
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.866
vit-base-patch16-224-in21k-Landscape_Recognition
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: 0.5122
- Accuracy: 0.866
- Weighted f1: 0.8678
- Micro f1: 0.866
- Macro f1: 0.8678
- Weighted recall: 0.866
- Micro recall: 0.866
- Macro recall: 0.866
- Weighted precision: 0.8710
- Micro precision: 0.866
- Macro precision: 0.8710
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted f1 | Micro f1 | Macro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2866 | 1.0 | 625 | 0.4308 | 0.8487 | 0.8538 | 0.8487 | 0.8538 | 0.8487 | 0.8487 | 0.8487 | 0.8700 | 0.8487 | 0.8700 |
| 0.1522 | 2.0 | 1250 | 0.4648 | 0.8687 | 0.8694 | 0.8687 | 0.8694 | 0.8687 | 0.8687 | 0.8687 | 0.8714 | 0.8687 | 0.8714 |
| 0.0609 | 3.0 | 1875 | 0.5122 | 0.866 | 0.8678 | 0.866 | 0.8678 | 0.866 | 0.866 | 0.866 | 0.8710 | 0.866 | 0.8710 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3