Sebastian Michalowski

@lynetcha, one more modification: **In tools/train_net.py** ``` output_dir = get_output_dir(imdb) print 'Output will be saved to `{:s}`'.format(output_dir) train_net(args.solver, roidb, output_dir, pretrained_model=args.pretrained_model, max_iters=args.max_iters, **previous_state=args.previous_state**) ``` also remember to omit --weights param

I've used branch v0.15.5 and CUDNN 5

I've used DIGITS functionality to prepare data for training. Just took the first 18 categories from train.txt and val.txt (sorry, don't have files anymore). I wrote simple python script to...

@shadowf126 I've tested a bunch of different settings in solver and train_val. Using vanilla caffe I wasn't able to achieve top-1 better than ~0.65. nvidia caffe worked a lot better.

same here, but in mosh session and while I want to scroll through docker logs