metadata
license: apache-2.0
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: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.5026722090261283
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: 1.5983
- Accuracy: 0.5027
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: 0.0001
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.89 | 6 | 1.7745 | 0.2838 |
| 1.9066 | 1.89 | 12 | 1.7447 | 0.3895 |
| 1.9066 | 2.89 | 18 | 1.7216 | 0.4154 |
| 1.9875 | 3.89 | 24 | 1.6914 | 0.4311 |
| 1.8094 | 4.89 | 30 | 1.6659 | 0.4629 |
| 1.8094 | 5.89 | 36 | 1.6485 | 0.4852 |
| 1.8906 | 6.89 | 42 | 1.6278 | 0.4869 |
| 1.8906 | 7.89 | 48 | 1.6098 | 0.5021 |
| 1.8516 | 8.89 | 54 | 1.6131 | 0.5175 |
| 1.718 | 9.89 | 60 | 1.5983 | 0.5027 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1