metadata
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swinv2-tiny-patch4-window8-256-finetuned-gardner-exp-max
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8154362416107382
swinv2-tiny-patch4-window8-256-finetuned-gardner-exp-max
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6445
- Accuracy: 0.8154
Model description
Predict Expansion Grade - Gardner Score from an embryo image
Intended uses & limitations
More information will be provided
Training and evaluation data
More information will be provided
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6002 | 0.97 | 14 | 1.4558 | 0.5024 |
| 1.4093 | 2.0 | 29 | 1.2320 | 0.5024 |
| 1.1068 | 2.97 | 43 | 1.0740 | 0.5951 |
| 0.9988 | 4.0 | 58 | 0.9967 | 0.6049 |
| 0.9099 | 4.97 | 72 | 0.9248 | 0.6 |
| 0.8674 | 6.0 | 87 | 0.8766 | 0.6780 |
| 0.8638 | 6.97 | 101 | 0.8656 | 0.6732 |
| 0.833 | 8.0 | 116 | 0.8395 | 0.6732 |
| 0.8211 | 8.97 | 130 | 0.8204 | 0.6927 |
| 0.8236 | 9.66 | 140 | 0.8204 | 0.6780 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.15.0