SibiTransExperiment exp_002
Config
json
{
"model_id": "B",
"img_size": 192,
"batch_size": 96,
"optimizer": "adam",
"lr": 0.0005,
"weight_decay": 0.0001,
"dropout": 0.3,
"patience": 10,
"lr_schedule": "reduce"
}
Results
- Accuracy: 0.8144
- Macro F1: 0.8173
- Weighted F1: 0.8173
- Best Val Acc: 0.82
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\2. CNN\1.Workplace\Custom_model\runs\exp_002\artifacts\best.keras, h5:D:\Dhika\(KULIAH)\'Skripsi\Github\Fix_TA_Project\Fix_TA_Project\1. Workspace\2. CNN\1.Workplace\Custom_model\runs\exp_002\artifacts\final_model.h5, tflite:D:\Dhika\(KULIAH)\'Skripsi\Github\Fix_TA_Project\Fix_TA_Project\1. Workspace\2. CNN\1.Workplace\Custom_model\runs\exp_002\artifacts\model.tflite
Sumber Data
- Direktori:
D:\Dhika\(KULIAH)\'Skripsi\Github\Fix_TA_Project\Fix_TA_Project\1. Workspace\2. CNN\1.Workplace\Custom_model\runs\exp_002 - README: ada