Hugging Face's logo

autoevaluate
/
image-multi-class-classification-not-evaluated

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
2
image-multi-class-classification-not-evaluated / README.md
lewtun's picture
lewtun HF staff
Update README.md
e47c849
preview code
|
raw
history blame contribute delete
1.52 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - mnist
  - autoevaluate/mnist-sample
metrics:
  - accuracy
duplicated_from: autoevaluate/image-multi-class-classification

image-classification

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the mnist dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0556
  • Accuracy: 0.9833

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: 1

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3743 1.0 422 0.0556 0.9833

Framework versions

  • Transformers 4.20.0
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1