Deep learning based Image Compression for Microscopy Images: An Empirical Study

This dataset supports the manuscript titled "Deep Learning Based Image Compression for Microscopy Images: An Empirical Study." The materials provided are essential for replicating the experiments in the study. The dataset is divided into three main parts: Config: train and test yaml config files for both 2D and 3D mmv_im2im labelfree task Sample_data: sample data to test the compression and the downstream labelfree code, in both 2D and 3D case. Model: fine-tuned 2D/3D labelfree model and 3D compression model. We use pre-trained 2D compression models from CompressAI本数据集支持题为《基于深度学习的显微镜图像压缩：一项实证研究》的学术手稿。所提供的材料对于复现该研究中的实验至关重要。本数据集主要分为三个部分： 配置文件（Config）：包含针对2D与3D场景下mmv_im2im无标记（labelfree）任务的训练与测试yaml配置文件。 示例数据（Sample_data）：涵盖2D与3D两种场景的示例数据，用于测试图像压缩以及下游无标记任务代码。 模型（Model）：包含微调后的2D/3D无标记模型与3D压缩模型。本研究使用了来自CompressAI的预训练2D压缩模型。