metadata
license: apache-2.0
base_model: google/vit-large-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: fashion-images-perspectives-vit-large-patch16-224-in21k-v4
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: touchtech/fashion-images-perspectives
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9434482758620689
fashion-images-perspectives-vit-large-patch16-224-in21k-v4
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the touchtech/fashion-images-perspectives dataset. It achieves the following results on the evaluation set:
- Loss: 0.2203
- Accuracy: 0.9434
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: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4275 | 1.0 | 3081 | 0.3064 | 0.9011 |
| 0.3555 | 2.0 | 6162 | 0.3097 | 0.9103 |
| 0.3069 | 3.0 | 9243 | 0.3036 | 0.9106 |
| 0.2449 | 4.0 | 12324 | 0.2268 | 0.9377 |
| 0.2339 | 5.0 | 15405 | 0.2203 | 0.9434 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3