機器學習程式是透過不斷實驗、調整模型以訓練出一個理想模型為開發目標。為了使模型盡可能地符合期望，開發者需不斷執行超參數調整的過程，既存作法雖可達到在訓練期間調整超參數的功能，但仍有其不足之處。為了對比調整前後的差異，常見使用表格的方式去記錄實驗過程，然而此法較不易直觀地看出實驗之間的關連性。 對此，本研究提出一個輔助超參數調整工具：RETUNE，利用回呼函式和checkpoint機制，讓使用者可在訓練期間對優化器超參數進行調整，結合視覺化方式即時反饋模型評估指標給使用者，並自動記錄調整時的模型配置等相關訓練數據。同時，提供回溯功能使模型得以回復至先前的訓練狀態，以進行模型比較。最後，以樹狀圖的方式呈現先前調整歷程，協助使用者歸納過去的實驗，進而理解超參數對訓練產生的影響，更有效的進行優化器超參數調整與模型優化的過程。;Building machine learning model is an experiment-driven process. Tuning hyperparamters iteratively to meet the acceptance criteria usually results in tremendous trial models. There are some related research for tuning hyperparameters during training, but still have constraints for building a model. Moreover, most of the developers tend to manage these artifacts in tableau way, and extra effort must be spent with it. However, tables can not reveal the correlation between experiments. In this paper, we implement a tool: RETUNE with callback function and checkpoint operation. It allows users to tune optimizer′s hyperparameters based on the visualized feedback of the model metrics during training, and automatically extracts model configuration from the experiment. With the feature to restore model from the previous training state, users would be able to compare from multiple potential models. Finally, the tuning process would be plotted as a tree graph which aimed at helping users understand the historical experiments and realize the relation between hyperparameters setting and training process, in order to effectively manipulate hyperparameter tuning and model optimization.
