metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: pose-estimation-crop-uncrop
results: []
Crop vs Full Body
Model description
This model predicts whether the person in the image is cropped or full body. It is trained on Lucy in the Sky images.
This model is a fine-tuned version of google/vit-base-patch16-224-in21k.
Training and evaluation data
It achieves the following results on the evaluation set:
- Loss: 0.1513
- Accuracy: 0.9649
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
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3