> The neural network knows the stitch names, but it doesn’t understand what the stitches do. It doesn’t know that a k2tog is knitting two stitches together (a decrease) and a yo is a yarn-over (a lacy increase), so it doesn’t know to keep the stitch counts consistent, or to deliberately change them to make a particular shape.”
This seems like the sort of detail that could be learned with sufficient data. 500 patterns doesn't seem like it would be enough. I'm a bit surprised that it managed to learn to number the rows consistently.
This seems like the sort of detail that could be learned with sufficient data. 500 patterns doesn't seem like it would be enough. I'm a bit surprised that it managed to learn to number the rows consistently.