翻译：Loading the raw data and processing by Rawpy takes significant more time than the backpropagation. By default, the code will load all the groundtruth data processed by Rawpy into memory without 8-bit or 16-bit quantization. This requires at least 64 GB RAM for training the Sony model and 128 GB RAM for the Fuji model. If you need to train it on a machine with less RAM, you may need to revise the code and use the groundtruth data on the disk. We provide the 16-bit groundtruth images processed by Rawpy: Sony (12 GB) and Fuji (22 GB).

使用Rawpy加载原始数据并进行处理比反向传播所需的时间要长得多。默认情况下，该代码将加载由Rawpy处理的所有groundtruth数据到内存中，而不进行8位或16位量化。这需要至少64 GB的RAM来训练Sony模型，以及128 GB的RAM来训练Fuji模型。如果您需要在RAM较少的机器上进行训练，则可能需要修改代码并使用磁盘上的groundtruth数据。我们提供了由Rawpy处理的16位groundtruth图像：Sony（12 GB）和Fuji（22 GB）。