DATASETS: TRAIN: ("VG_stanford_filtered_with_attribute_train",) VAL: ("VG_stanford_filtered_with_attribute_val",) TEST: ("VG_stanford_filtered_with_attribute_test",)

KaihuaTang / Scene-Graph-Benchmark.pytorch

A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training CVPR 2020”

MIT License

1.06k stars 229 forks source link

DATASETS: TRAIN: ("VG_stanford_filtered_with_attribute_train",) VAL: ("VG_stanford_filtered_with_attribute_val",) TEST: ("VG_stanford_filtered_with_attribute_test",) #170

Open cpperrpr opened 2 years ago

cpperrpr commented 2 years ago

❓ Questions and Help

跑Detect Scene Graphs on Your Custom Images 🌟 时候配置文件需要下列数据集： DATASETS: TRAIN: ("VG_stanford_filtered_with_attribute_train",) VAL: ("VG_stanford_filtered_with_attribute_val",) TEST: ("VG_stanford_filtered_with_attribute_test",)

请问这些数据是在哪，怎么划分的，运行relation_test_net.py时候加载数据为0，看了下paths_catalog.py并没有标明，很困扰

1286169349 commented 10 months ago

我也是，请问你解决了吗