Re:Show HN: Get Paid to Build Your Next Side Project
by mattlondon on Wednesday June 14, 2017 @11:01AM
(#14553219)
In terms of ML you could probably load a pre-trained image classification convolutional model and fine-tune it a bit and get quite a reliable if not superbly exact "here is some text" classifier without too much effort. Perhaps not 10 minutes, but maybe a weekend to allow for training.
[ Parent
| on HN ]
Re:Show HN: Get Paid to Build Your Next Side Project
by yorwba on Wednesday June 14, 2017 @11:59AM
(#14553640)
E.g [1] trained for 20 * 10^5 iterations at 2.1 seconds per image, coming out to 48 days (!) in total. Maybe the 2.1 seconds also include the post-processing to get bounding boxes, though. Anyway, you need lots of training time.
[1] https://arxiv.org/abs/1604.04018 "Multi-Oriented Text Detection with Fully Convolutional Networks"
Re:Show HN: Get Paid to Build Your Next Side Project
by mattlondon on Wednesday June 14, 2017 @01:37PM
(#14554412)
Looks like they only used a single GPU for training though - you could trivially get that time down a lot if you used one of the cloud ML platforms (and were prepared to pay)