<!-- 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. -->

PE_fb_convnext_OD_v2

This model is a fine-tuned version of facebook/convnext-tiny-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Accuracy: 0.9444

• F1: 0.4857

• Precision: 0.5

• Recall: 0.9722

• Loss: 0.1103

• Classification Report: precision recall f1-score support

       6       0.00      0.00      0.00         0
       7       1.00      0.94      0.97        18
  

  accuracy 0.94 18 macro avg 0.50 0.47 0.49 18 weighted avg 1.00 0.94 0.97 18

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: 0.0005
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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

       0       0.00      0.00      0.00         0
       6       0.00      0.00      0.00         0
       7       1.00      0.83      0.91        18

accuracy                           0.83        18

macro avg 0.33 0.28 0.30 18 weighted avg 1.00 0.83 0.91 18 | | 0.0159 | 2.0 | 226 | 0.8889 | 0.4706 | 0.5 | 0.9444 | 0.2652 | precision recall f1-score support

       6       0.00      0.00      0.00         0
       7       1.00      0.89      0.94        18

accuracy                           0.89        18

macro avg 0.50 0.44 0.47 18 weighted avg 1.00 0.89 0.94 18 | | 0.0267 | 3.0 | 339 | 0.9444 | 0.4857 | 0.5 | 0.9722 | 0.1103 | precision recall f1-score support

       6       0.00      0.00      0.00         0
       7       1.00      0.94      0.97        18

accuracy                           0.94        18

macro avg 0.50 0.47 0.49 18 weighted avg 1.00 0.94 0.97 18 |

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1