|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swinv2-tiny-patch4-window8-256 |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: microsoft_swinv2-tiny-patch4-window8-256-batch_16_epoch_4_classes_24_final_withAug |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: bengali_food_images |
|
type: imagefolder |
|
config: default |
|
split: train |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9456521739130435 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# microsoft_swinv2-tiny-patch4-window8-256-batch_16_epoch_4_classes_24_final_withAug |
|
|
|
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the bengali_food_images dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2321 |
|
- Accuracy: 0.9457 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.7162 | 0.09 | 100 | 1.4225 | 0.7079 | |
|
| 1.2286 | 0.17 | 200 | 0.9461 | 0.7935 | |
|
| 1.0323 | 0.26 | 300 | 0.7366 | 0.8356 | |
|
| 0.8678 | 0.34 | 400 | 0.6211 | 0.8628 | |
|
| 0.7849 | 0.43 | 500 | 0.5354 | 0.8655 | |
|
| 0.7105 | 0.51 | 600 | 0.4793 | 0.8899 | |
|
| 0.6198 | 0.6 | 700 | 0.4319 | 0.9090 | |
|
| 0.6276 | 0.68 | 800 | 0.4022 | 0.8981 | |
|
| 0.5411 | 0.77 | 900 | 0.3816 | 0.9117 | |
|
| 0.4984 | 0.85 | 1000 | 0.3824 | 0.9022 | |
|
| 0.5665 | 0.94 | 1100 | 0.3460 | 0.9212 | |
|
| 0.5741 | 1.02 | 1200 | 0.3336 | 0.9158 | |
|
| 0.4039 | 1.11 | 1300 | 0.3204 | 0.9130 | |
|
| 0.4347 | 1.19 | 1400 | 0.3038 | 0.9307 | |
|
| 0.3639 | 1.28 | 1500 | 0.2955 | 0.9253 | |
|
| 0.4282 | 1.36 | 1600 | 0.2948 | 0.9293 | |
|
| 0.4375 | 1.45 | 1700 | 0.2868 | 0.9212 | |
|
| 0.3063 | 1.53 | 1800 | 0.2861 | 0.9334 | |
|
| 0.3549 | 1.62 | 1900 | 0.2826 | 0.9293 | |
|
| 0.4326 | 1.71 | 2000 | 0.2698 | 0.9348 | |
|
| 0.3697 | 1.79 | 2100 | 0.2602 | 0.9280 | |
|
| 0.3155 | 1.88 | 2200 | 0.2523 | 0.9361 | |
|
| 0.3348 | 1.96 | 2300 | 0.2506 | 0.9470 | |
|
| 0.3854 | 2.05 | 2400 | 0.2565 | 0.9321 | |
|
| 0.3951 | 2.13 | 2500 | 0.2482 | 0.9402 | |
|
| 0.3531 | 2.22 | 2600 | 0.2455 | 0.9402 | |
|
| 0.3643 | 2.3 | 2700 | 0.2513 | 0.9375 | |
|
| 0.3393 | 2.39 | 2800 | 0.2492 | 0.9429 | |
|
| 0.3635 | 2.47 | 2900 | 0.2394 | 0.9402 | |
|
| 0.3624 | 2.56 | 3000 | 0.2425 | 0.9389 | |
|
| 0.3608 | 2.64 | 3100 | 0.2390 | 0.9457 | |
|
| 0.3215 | 2.73 | 3200 | 0.2483 | 0.9321 | |
|
| 0.2971 | 2.81 | 3300 | 0.2455 | 0.9402 | |
|
| 0.3838 | 2.9 | 3400 | 0.2363 | 0.9470 | |
|
| 0.3036 | 2.98 | 3500 | 0.2422 | 0.9402 | |
|
| 0.401 | 3.07 | 3600 | 0.2398 | 0.9429 | |
|
| 0.3458 | 3.15 | 3700 | 0.2517 | 0.9429 | |
|
| 0.2908 | 3.24 | 3800 | 0.2423 | 0.9457 | |
|
| 0.3016 | 3.32 | 3900 | 0.2402 | 0.9443 | |
|
| 0.2961 | 3.41 | 4000 | 0.2414 | 0.9457 | |
|
| 0.3822 | 3.5 | 4100 | 0.2413 | 0.9416 | |
|
| 0.2596 | 3.58 | 4200 | 0.2356 | 0.9457 | |
|
| 0.3064 | 3.67 | 4300 | 0.2324 | 0.9497 | |
|
| 0.3059 | 3.75 | 4400 | 0.2321 | 0.9457 | |
|
| 0.42 | 3.84 | 4500 | 0.2556 | 0.9402 | |
|
| 0.2959 | 3.92 | 4600 | 0.2491 | 0.9416 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|