metadata
license: apache-2.0
base_model: microsoft/resnet-50
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: resnet-50-finetuned-eurosat
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: 0.9648304120191213
resnet-50-finetuned-eurosat
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1363
- Accuracy: 0.9648
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7502 | 1.0 | 549 | 1.3285 | 0.7954 |
| 0.6126 | 2.0 | 1098 | 0.3205 | 0.9301 |
| 0.4063 | 3.0 | 1647 | 0.1893 | 0.9551 |
| 0.3333 | 4.0 | 2197 | 0.1515 | 0.9624 |
| 0.3365 | 5.0 | 2745 | 0.1363 | 0.9648 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1