metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224-in22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-base-patch4-window7-224-in22k-MM_Classification_base_V10
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8729338842975206
swin-base-patch4-window7-224-in22k-MM_Classification_base_V10
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: 0.3427
- Accuracy: 0.8729
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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7948 | 0.9836 | 15 | 0.4498 | 0.8352 |
| 0.4439 | 1.9672 | 30 | 0.3836 | 0.8590 |
| 0.4024 | 2.9508 | 45 | 0.3652 | 0.8600 |
| 0.3562 | 4.0 | 61 | 0.3474 | 0.8642 |
| 0.345 | 4.9836 | 76 | 0.3429 | 0.8688 |
| 0.3379 | 5.9672 | 91 | 0.3427 | 0.8729 |
| 0.3213 | 6.8852 | 105 | 0.3443 | 0.8709 |
Framework versions
- Transformers 4.44.2
- Pytorch 1.13.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1