Hugging Face's logo

nandyc
/
swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2

Image Classification
Transformers
PyTorch
swin
Generated from Trainer
Inference Endpoints
Model card Files Community
swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2 / README.md
nandyc's picture
nandyc
🍻 cheers
f36e2b5
preview code
|
raw
history blame
4.35 kB
metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - image-classification
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2
    results: []

swin-tiny-patch4-window7-224-finetuned_ASL_Isolated_Swin_dataset2

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

  • Loss: 0.0439
  • Accuracy: 0.9846

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: 0.0002
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.5603 1.09 100 1.0931 0.6423
0.9055 2.17 200 0.5069 0.8615
0.4254 3.26 300 0.5634 0.8154
0.5814 4.35 400 0.2883 0.9154
0.4953 5.43 500 0.2710 0.9154
0.4456 6.52 600 0.2451 0.9346
0.4524 7.61 700 0.2625 0.9308
0.3095 8.7 800 0.2397 0.9462
0.3224 9.78 900 0.1787 0.9385
0.4069 10.87 1000 0.3376 0.9231
0.3467 11.96 1100 0.1603 0.9538
0.469 13.04 1200 0.2247 0.9423
0.4523 14.13 1300 0.1552 0.9538
0.2923 15.22 1400 0.3376 0.9346
0.3139 16.3 1500 0.1449 0.9577
0.3873 17.39 1600 0.1495 0.9654
0.2994 18.48 1700 0.1821 0.9654
0.2611 19.57 1800 0.1294 0.9769
0.1883 20.65 1900 0.0879 0.9731
0.2076 21.74 2000 0.1969 0.95
0.3531 22.83 2100 0.2135 0.9538
0.4339 23.91 2200 0.1030 0.9615
0.2959 25.0 2300 0.1579 0.9731
0.1546 26.09 2400 0.1648 0.9692
0.1315 27.17 2500 0.1514 0.9577
0.2191 28.26 2600 0.1257 0.9538
0.16 29.35 2700 0.1162 0.9692
0.1567 30.43 2800 0.1252 0.9731
0.1147 31.52 2900 0.2642 0.9577
0.1434 32.61 3000 0.1371 0.9769
0.2488 33.7 3100 0.1161 0.9769
0.1646 34.78 3200 0.2052 0.9615
0.1326 35.87 3300 0.1995 0.9769
0.137 36.96 3400 0.1124 0.9731
0.1633 38.04 3500 0.1620 0.9692
0.1593 39.13 3600 0.1838 0.9731
0.2192 40.22 3700 0.1331 0.9769
0.1495 41.3 3800 0.1291 0.9731
0.226 42.39 3900 0.1090 0.9692
0.1383 43.48 4000 0.0994 0.9654
0.0491 44.57 4100 0.0660 0.9769
0.1034 45.65 4200 0.0698 0.9808
0.0893 46.74 4300 0.0439 0.9846
0.1789 47.83 4400 0.0577 0.9808
0.0569 48.91 4500 0.0547 0.9846
0.1113 50.0 4600 0.0605 0.9846

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1