We propose Semi-Decision-Focused Learning, a practical adaptation of Decision-Focused Learning for portfolio optimization. Rather than directly optimizing complex financial metrics, we employ simple target portfolios (Max-Sortino or One-Hot) and train models with a convex, cross-entropy loss. We further incorporate Deep Ensemble methods to reduce variance and stabilize performance. Experiments on two universes (one upward-trending and another range-bound) show consistent outperformance over baseline portfolios, demonstrating the effectiveness and robustness of our approach. Code is available at https://github.com/sDFLwDE/sDFLwDE