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-icm-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: 0.6428571428571429

swinv2-tiny-patch4-window8-256-finetuned-gardner-icm-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: 1.0741
Accuracy: 0.6429

Model description

Predict Inner Cell Mass Grade - Gardner Score from an embryo image

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0925	0.94	11	1.0631	0.7952
0.9552	1.96	23	0.6336	0.7952
0.6566	2.98	35	0.5356	0.7952
0.5686	4.0	47	0.5150	0.7952
0.5703	4.94	58	0.5129	0.7952
0.5726	5.96	70	0.5154	0.7952
0.5482	6.98	82	0.5142	0.7952
0.568	8.0	94	0.5109	0.7952
0.5245	8.94	105	0.5134	0.7952
0.5979	9.96	117	0.5238	0.7952
0.5442	10.98	129	0.5076	0.7952
0.545	12.0	141	0.5062	0.7952
0.5514	12.94	152	0.5013	0.7952
0.5377	13.96	164	0.5045	0.7952
0.5282	14.98	176	0.5038	0.7952
0.5389	16.0	188	0.4994	0.7952
0.5039	16.94	199	0.4996	0.7952
0.5348	17.96	211	0.4940	0.7952
0.5426	18.72	220	0.4947	0.7952

Framework versions

Transformers 4.36.2
Pytorch 2.1.2
Datasets 2.16.0
Tokenizers 0.15.0