metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
- recall
- precision
model-index:
- name: Armature_Defect_Detection_Resin
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: 0.76
- name: F1
type: f1
value: 0.76
- name: Recall
type: recall
value: 0.76
- name: Precision
type: precision
value: 0.76
Armature_Defect_Detection_Resin
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: 0.4978
- Accuracy: 0.76
- F1: 0.76
- Recall: 0.76
- Precision: 0.76
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|---|---|---|---|---|---|---|---|
| No log | 0.57 | 1 | 0.7205 | 0.44 | 0.44 | 0.44 | 0.44 |
| No log | 1.57 | 2 | 0.5926 | 0.6 | 0.6 | 0.6 | 0.6 |
| No log | 2.57 | 3 | 0.4978 | 0.76 | 0.76 | 0.76 | 0.76 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1