Naoto Inoue
Naoto Inoue
I have the same issue. I would appreciate it if you could provide it.
Wow you are right, thank you so much for the suggestion!
I'm not sure how the progress goes in your faces dataset (in Places2, 160k is at least OK). Since this implementation is based on the paper published four years ago,...
Thanks for your answer and sorry for disturbing you during the holidays;
When I get start/end position by `get_random_navigable_point`, it works! However, sometimes it seems the agent is out of the room, and the some or complete part of the view is...
I downloaded clipart dataset to my local PC right now and confirmed that it exists. ``` naoto@inouenaoto-no-MacBook-Pro:~/Downloads $ ls -lat clipart/JPEGImages | grep 322583407.jpg -rw-r--r-- 1 naoto staff 32095 Mar...
You can get your own dataset and modify places2.py to load the images in it.
I've modified the code and tried testing performance on VOC2007-test, but the mAP was 74.2 on 416x416 input, 0.45 nms thresh, 0.005 detection thresh (all parameters are written in the...
@Breakend Sorry for my extremely late reply! I tried to simply load the weights from darknet and tested.
Hi, thank you for your interest in our project. I guess your understanding of fine-tuning is correct. We use a lower learning rate for fine-tuning than pre-training. > it will...