[ILSVRC] Data for "Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations"

This repository contains data collected under the following study:P.Kharyuk, S.Matveev, I.Oseledets. Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations, arXiv:2503.03283. Corresponding source code repository: https://github.com/kharyuk/activation_sa Places365-based part: 10.5281/zenodo.18098133 0_models.7z: copy of the CNN models used in the research (reference: https://docs.pytorch.org/vision/main/models.html) 1_sensitivity_values.7z: sensitivity values (Sobol indices, Shapley values) computed for the first experimental series. In addition, logs and npz-files containing the sampled parameters were packed. To be used within the jupyter notebooks, all .hdf5 files should be placed into the 'results' directory of the source code repository. 2_guided_masking_predictions.7z: these files include the top-5 class predictions and corresponding classifying layer's outputs computed for the second experimental series. Every .hdf5 file should be placed into the 'results' directory of the source code repository. Logs and pkl files with sampling parameters are also included in the archive. 3_single_channelled_segments.7z: sensitivity values (Sobol indices, Shapley values) computed for the third experimental series (for the standalone segments). As for the previous experimental series, logs and npz-files tracing the sampled parameters are provided within the archive. Every .hdf5 file should be placed into the 'results/single_units' directory of the source code repository. 4_test_references.7z: examples of testing scripts output (core computations with a limited number of samples and checkpoints). Not related to the article course. The unpacking procedure for archives 1-3 is automated by the bash script located in tools/unpack_results.sh of the GitHub repository.本仓库收录了下述研究生成的数据集：P. Kharyuk、S. Matveev、I. Oseledets，《探索卷积神经网络（Convolutional Neural Network, CNN）在同步图像增强场景下的专业化程度与敏感性》，arXiv:2503.03283。 对应的源代码仓库：https://github.com/kharyuk/activation_sa 基于Places365的数据集部分：10.5281/zenodo.18098133 0_models.7z：本研究所用卷积神经网络模型的副本（参考来源：https://docs.pytorch.org/vision/main/models.html） 1_sensitivity_values.7z：包含第一组实验中计算得到的敏感性指标——索伯尔指数（Sobol indices）与夏普利值（Shapley values），此外还打包了实验日志与存储采样参数的npz文件。若需在Jupyter Notebook中使用该数据集，需将所有.hdf5文件放置于源代码仓库的`results`目录下。 2_guided_masking_predictions.7z：该归档文件包含第二组实验的Top-5类别预测结果与对应分类层的输出。所有.hdf5文件需放置于源代码仓库的`results`目录下。归档中同时附带了实验日志与存储采样参数的pkl文件。 3_single_channelled_segments.7z：包含第三组实验（针对独立片段）计算得到的敏感性指标——索伯尔指数与夏普利值。与前述实验组一致，归档中提供了实验日志与记录采样参数的npz文件。所有.hdf5文件需放置于源代码仓库的`results/single_units`目录下。 4_test_references.7z：包含测试脚本输出示例（样本与检查点数量有限的核心计算结果），与本文研究内容无关。 归档1至3的解压流程可通过GitHub仓库中`tools/unpack_results.sh`路径下的Bash脚本自动完成。