SibiTransExperiment exp_tl_001
Config
json
{
"model_id": "MNv3l",
"img_size": 224,
"batch_size": 64,
"optimizer": "adamw",
"lr_head": 0.001,
"lr_ft": 7e-05,
"weight_decay": 1e-05,
"label_smoothing": 0.05,
"dropout": 0.4,
"head_epochs": 12,
"ft_epochs": 35,
"finetune": true,
"unfreeze_pct": 0.5,
"lr_schedule": "reduce",
"patience": 9
}
Results
- Accuracy: 0.9964
- Macro F1: 0.9964
- Weighted F1: 0.9964
- Best Val Acc: 0.9933
Dataset (EDA)
- Jumlah kelas: 26
- Jumlah sampel: 15921
- Min per kelas: 601, Max per kelas: 619
- Imbalance ratio (max/min): 1.03
Plots
- train_acc:
- train_loss:
- cm_counts:
- cm_normalized:
Artifacts
- Models: keras:
D:\Dhika\(KULIAH)\'Skripsi\Github\Fix_TA_Project\Fix_TA_Project\1. Workspace\3. Transferlearning\runs\exp_tl_001\artifacts\best_ft.keras, h5:D:\Dhika\(KULIAH)\'Skripsi\Github\Fix_TA_Project\Fix_TA_Project\1. Workspace\3. Transferlearning\runs\exp_tl_001\artifacts\final_model.h5, tflite:D:\Dhika\(KULIAH)\'Skripsi\Github\Fix_TA_Project\Fix_TA_Project\1. Workspace\3. Transferlearning\runs\exp_tl_001\artifacts\model_fp16.tflite
Sumber Data
- Direktori:
D:\Dhika\(KULIAH)\'Skripsi\Github\Fix_TA_Project\Fix_TA_Project\1. Workspace\3. Transferlearning\runs\exp_tl_001 - README: ada