Yasunori Kudo

Yes, this PR solves the issues #2 and #3.

I noticed that detecting 19 key points is not necessary to convert to Human3.6M’s key points. So I will fix.

Sorry for inconvenient. I fixed "predict.py". https://github.com/yasunorikudo/chainer-ResNet/commit/891cc9a2befe13eb7466226e3dc0d23287c13e28 Plese fix the code or pull this repository again.

Sorry for inconvenient. This repository doesn't include training scripts. If you want to train ResNet from scratch, see the chainer sample code that train CNN for ImageNet.(https://github.com/pfnet/chainer/tree/master/examples/imagenet) You can use...

You can download through DropBox link as described in README (https://github.com/yasunorikudo/chainer-ResNet/blob/master/v2/README.md)