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
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: 0.9265375854214123
- name: Precision
type: precision
value: 0.9269521372101541
swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final
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: 0.1925
- Accuracy: 0.9265
- F1 Score: 0.9252
- Precision: 0.9270
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 |
---|---|---|---|---|---|---|
1.2212 | 0.96 | 20 | 1.1407 | 0.6429 | 0.6225 | 0.6601 |
0.565 | 1.98 | 41 | 0.5162 | 0.8326 | 0.8311 | 0.8428 |
0.3245 | 2.99 | 62 | 0.3265 | 0.8804 | 0.8784 | 0.8843 |
0.2618 | 4.0 | 83 | 0.2713 | 0.9066 | 0.9054 | 0.9105 |
0.2164 | 4.96 | 103 | 0.2812 | 0.8946 | 0.8929 | 0.8994 |
0.1814 | 5.98 | 124 | 0.2411 | 0.9060 | 0.9043 | 0.9091 |
0.1481 | 6.99 | 145 | 0.2345 | 0.9100 | 0.9084 | 0.9130 |
0.1468 | 8.0 | 166 | 0.2340 | 0.9072 | 0.9055 | 0.9108 |
0.1336 | 8.96 | 186 | 0.1925 | 0.9265 | 0.9252 | 0.9270 |
0.133 | 9.64 | 200 | 0.2021 | 0.9220 | 0.9207 | 0.9235 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3