|
--- |
|
license: apache-2.0 |
|
base_model: facebook/convnextv2-base-22k-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: convnextv2-base-22k-224-finetuned-cassava-leaf-disease |
|
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: 0.8827102803738318 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# convnextv2-base-22k-224-finetuned-cassava-leaf-disease |
|
|
|
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3524 |
|
- Accuracy: 0.8827 |
|
|
|
## 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: 360 |
|
- eval_batch_size: 360 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 1440 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 16 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.504 | 0.96 | 13 | 0.9739 | 0.6159 | |
|
| 0.9073 | 2.0 | 27 | 0.5204 | 0.8187 | |
|
| 0.4289 | 2.96 | 40 | 0.4312 | 0.85 | |
|
| 0.3901 | 4.0 | 54 | 0.3916 | 0.8645 | |
|
| 0.34 | 4.96 | 67 | 0.3755 | 0.8715 | |
|
| 0.3326 | 6.0 | 81 | 0.3746 | 0.8710 | |
|
| 0.3153 | 6.96 | 94 | 0.3684 | 0.8771 | |
|
| 0.3103 | 8.0 | 108 | 0.3543 | 0.8780 | |
|
| 0.292 | 8.96 | 121 | 0.3620 | 0.8804 | |
|
| 0.2953 | 10.0 | 135 | 0.3545 | 0.8794 | |
|
| 0.2879 | 10.96 | 148 | 0.3550 | 0.8808 | |
|
| 0.2779 | 12.0 | 162 | 0.3504 | 0.8799 | |
|
| 0.2736 | 12.96 | 175 | 0.3554 | 0.8818 | |
|
| 0.2769 | 14.0 | 189 | 0.3526 | 0.8846 | |
|
| 0.2625 | 14.96 | 202 | 0.3527 | 0.8813 | |
|
| 0.2625 | 15.41 | 208 | 0.3524 | 0.8827 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.1 |
|
|
