rllab-snu / TopologicalSemanticGraphMemory

Topological Semantic Graph Memory for Image Goal Navigation (CoRL 2022 oral)
MIT License
109 stars 8 forks source link

Training command RecursionError #19

Open SeryeongKim opened 4 months ago

SeryeongKim commented 4 months ago

"The entire network (image graph, object graph, LSTM, etc.) proposed in this paper needs to be trained on various datasets.

When using the provided training code to train the entire network: python train_il.py --policy TSGMPolicy --config configs/TSGM.yaml --version exp_name --data-dir IL_data/gibson --prebuild-path IL_data/gibson_graph

a Recursion Error occurs. Could you advise on how to resolve this error? image

Additionally, the configs/TSGM.yaml file seems to perform image goal navigation.

If I want to change the navigation objective to a different object, which configuration file should I modify?