Chen Yuhan
Chen Yuhan
Hi, Shizhe, thanks for the wonderful work! For a new dataset, how can I get the `word2int.json`, `int2word.npy` and `word.embedding.glove42.th`? I assume that you used a `Glove` model for word...
I found that some files are missing in the data file downloaded from BaiduNetdisk. There are 6 files in ```MSRVTT/annotation/RET``` (```int2word.npy```, ```ref_cpation.json```, ```sent2rolegraoh.augment.json```, ```sent2srl.json``` and ```word2int.json```), but some are not...
## Some common problems & solutions when installing maskrcnn_benchmark. **1. THC.h: No such file or directory/THCeilDiv Undefined/** [see this](https://blog.csdn.net/code_zhao/article/details/129172817) **2. identifier "THCudaCheck" is undefined** [see this](https://blog.csdn.net/weixin_46559271/article/details/128781665) **3. `torch.utils.cpp_extension.load` stuck** [see...
Thank you for your wonderful work! Are there any demos of generating scene graphs for custom images?