Metric comparison between the used dataset and the closest values reported in evaluation, both for the MuseGAN baseline and PowGAN.

Values in the ‘Model’ row are better the closer to the ‘Dataset’ row. Notice that both datasets show different metrics due to random sampling, track trimming, and sample rejection, but the error still shows a similar scale, which suggests correct training. For the columns, ‘D’, ‘B’, and ‘G’ correspond to Drums, Bass, and Guitar.「模型」行中的数值越接近「数据集」行，表现越优异。请注意，受随机采样、音轨裁剪与样本剔除操作影响，两个数据集的评估指标存在差异，但误差尺度仍保持一致，这表明训练过程正确无误。列标识「D」、「B」与「G」分别对应鼓组（Drums）、贝斯（Bass）与吉他（Guitar）。