<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
pose-estimation-crop-uncrop
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1513
- Accuracy: 0.9649
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 0.8 | 3 | 0.6639 | 0.7193 |
No log | 1.87 | 7 | 0.5238 | 0.8421 |
0.6164 | 2.93 | 11 | 0.4318 | 0.8246 |
0.6164 | 4.0 | 15 | 0.3080 | 0.9474 |
0.6164 | 4.8 | 18 | 0.3269 | 0.9123 |
0.3439 | 5.87 | 22 | 0.2105 | 0.9649 |
0.3439 | 6.93 | 26 | 0.1825 | 0.9649 |
0.2371 | 8.0 | 30 | 0.1349 | 0.9649 |
0.2371 | 8.8 | 33 | 0.1607 | 0.9649 |
0.2371 | 9.87 | 37 | 0.1251 | 0.9825 |
0.2196 | 10.93 | 41 | 0.1570 | 0.9825 |
0.2196 | 12.0 | 45 | 0.1602 | 0.9649 |
0.2196 | 12.8 | 48 | 0.1101 | 0.9825 |
0.1576 | 13.87 | 52 | 0.1103 | 1.0 |
0.1576 | 14.93 | 56 | 0.1405 | 0.9649 |
0.1634 | 16.0 | 60 | 0.1513 | 0.9649 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3