Kenneth-Wong

start-hadoop.sh执行后无法访问192.168.99.100:50070

1

在执行start-hadoop.sh后，仍然无法访问hadoop主页是什么情况？

Out of memory when training with a TITAN X

1

I met with the OOM problem when training with a TITAN X graphic card. The log is as follows: I tensorflow/core/common_runtime/bfc_allocator.cc:643] Bin (256): Total Chunks: 0, Chunks in use: 0...

Thanks for your great job. And here I want to report some bugs and I have remedied them. 1. In the https://github.com/Uehwan/3-D-Scene-Graph/blob/0deb403f77f43c48fd730091fb8cd065a3dc0a59/object_prior_extraction.py#L45 and https://github.com/Uehwan/3-D-Scene-Graph/blob/0deb403f77f43c48fd730091fb8cd065a3dc0a59/relation_prior_extraction.py#L103, the key 'name' may not appear...

About the dataset

2

Is the relational_captions.json your final data for training the model? Could you provide the codes for preprocessing the raw VG dataset and explain how to get the relational_captions.json file? Thanks.

Code

3

Congratulations on being accepted by ICCV 2023! Hope to release the code!!!

I found an interesting implementation in your codes: In Line 644-674 of MotionDirector_train.py, the spatial_lora is added for each video, it will lead to a result that the Linear layer...