metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - precision
model-index:
  - name: swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_08
    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: 0.9591516103692066
          - name: Precision
            type: precision
            value: 0.9627515459909033

swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_08

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.1210
Accuracy: 0.9592
F1 Score: 0.9600
Precision: 0.9628

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: 100
eval_batch_size: 100
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 400
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	F1 Score	Precision
1.2882	0.99	19	0.5469	0.7962	0.7863	0.8077
0.3491	1.97	38	0.3030	0.8861	0.8878	0.8981
0.1791	2.96	57	0.2077	0.9211	0.9229	0.9307
0.122	4.0	77	0.2007	0.9254	0.9272	0.9369
0.0671	4.99	96	0.2073	0.9269	0.9294	0.9401
0.0474	5.97	115	0.1384	0.9482	0.9494	0.9547
0.032	6.96	134	0.1683	0.9430	0.9447	0.9511
0.0225	8.0	154	0.1101	0.9650	0.9657	0.9671
0.0193	8.99	173	0.1372	0.9533	0.9544	0.9585
0.0193	9.87	190	0.1210	0.9592	0.9600	0.9628

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3