metadata
license: other
base_model: google/mobilenet_v2_0.75_160
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: day-night
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: 0.9988452655889145
day-night
This model is a fine-tuned version of google/mobilenet_v2_0.75_160 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0030
- Accuracy: 0.9988
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: 10
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1021 | 0.6 | 200 | 0.0679 | 0.9734 |
0.0199 | 1.19 | 400 | 0.0184 | 0.9919 |
0.0723 | 1.79 | 600 | 0.6625 | 0.7852 |
0.0247 | 2.38 | 800 | 0.0030 | 0.9988 |
0.0273 | 2.98 | 1000 | 0.0254 | 0.9885 |
0.012 | 3.57 | 1200 | 0.0177 | 0.9965 |
0.0142 | 4.17 | 1400 | 0.0282 | 0.9908 |
0.009 | 4.76 | 1600 | 0.0189 | 0.9977 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3