metadata
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_V2
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: 0.882202304737516
swin-base-patch4-window7-224-in22k-MM_Classification_base_V2
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: 0.3018
- Accuracy: 0.8822
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 |
|---|---|---|---|---|
| 1.0086 | 1.0 | 19 | 0.4613 | 0.8105 |
| 0.4528 | 2.0 | 38 | 0.3454 | 0.8592 |
| 0.3556 | 3.0 | 57 | 0.3289 | 0.8604 |
| 0.3404 | 4.0 | 76 | 0.3197 | 0.8784 |
| 0.3175 | 5.0 | 95 | 0.3018 | 0.8822 |
| 0.3007 | 6.0 | 114 | 0.3007 | 0.8809 |
| 0.2968 | 7.0 | 133 | 0.2967 | 0.8758 |
Framework versions
- Transformers 4.43.3
- Pytorch 1.13.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1