Satoshi Tsutsui

Alright, I am still waiting for training script for YOLO.... Well, it's so sad that chainercv do not support any training of YOLO. This issue is for multi-gpu but actually...

Hi, I am trying to do this too. Did you make it? I guess you need to make a dataset class like this: https://github.com/apple2373/chainer-faster-rcnn/blob/master/lib/dataset_custom.py The data can be stored in...

Nope, I am using YOLO now.

Yes, at least I was able to solve my own problem. I am using YOLO 2 with darknet and darkflow (tensorflow ported version), but I am also aware of chained...

I use a university server, and don't have root. I simply can't run `apt-get`.

Thanks! I'll try later. FIY, I actually tried `conda install openmpi` before but didn't work. Well, to be clear, I am NOT asking help for installing MPI or setting up...

Thanks for the comment! I am in favor of option 1. Not everyone has the same environment, and to me, it's acceptable that users have to adjust command line arguments...

I'd like to suggest another option. Maybe you can call option 3. How about using gradient accomulation to emulate a large batch size for the single GPU case? I asked...

Thanks for the reply! I think I am confused. If you will simply drop channels, why don't you use that smaller channels in the training time? I mean, in the...

I still can't understand why this repository use strange channel dropping trick. Is it this repository owner's invented trick that training larger channel and dropping at inference time ? I...