# HG changeset patch # User Laman # Date 2019-05-30 12:49:35 # Node ID d4478db55eec9976c9dc3b2942524b3d681d4235 # Parent 7cb01d4080c978bfc9d697f49fc81af5d2e191da readme: line breaks diff --git a/readme.md b/readme.md --- a/readme.md +++ b/readme.md @@ -11,7 +11,7 @@ Therefore our current research focuses o ### Sansa ### First detector approximately locates the board in the picture. It uses SSD (single shot detector) with MobileNet and is working decently. -Examples (downloaded from Flickr under CC0 license): +Examples (downloaded from Flickr under CC0 license): ![Sansa example 1](static/s16.jpg) ![Sansa example 2](static/s12.jpg) @@ -19,10 +19,10 @@ Examples (downloaded from Flickr under C ### Dochi ### Then the cropped and normed image is fed to the second detector, designed to return precise grid corners' coordinates. This is currently implemented by a convolutional neural network and obtaining the required precision is a major hurdle to be passed. -Pretty good: +Pretty good: ![Dochi example 1](static/dochi-16.jpg) -Also good, but not enough: +Also good, but not enough: ![Dochi example 2](static/dochi-12.jpg) ### Genjo ### @@ -35,12 +35,12 @@ Base case: we have two correctly recogni Issues: - * illegal positions → ignorable + * illegal positions -> ignorable * positions unreachable from the previous state * reachable from any past state. (Incorrect states inbetween.) How to pick the correct leaf of such a tree? * reachable by more than one move. (Lost states inbetween.) Issues with branching factor. * stone shifts - * stone stops being recognized → fixable manually and even ignorable + * stone stops being recognized -> fixable manually and even ignorable * stone is recognized at an empty intersection. It can be occupied later for real. What do? This is handled by the `statebag` package and its documentation also states the problem and used solution in precise terms.