Closed drujensen closed 4 years ago
closing... I think I tracked it down.
@drujensen what was it?
I had the wrong data structure for the inputs: Array(Array(Array(Array(Float64))))
. I was doing Images / Rows / Columns / Channels but it needs to be Images / Channels / Rows / Columns. I am still trying to train the model but at least I am getting results.
@drujensen I'm happy to hear you're making progress, I think I'll take the next weekend to add some MT support to SHAInet, it would be a bit of a hard task as most vars are instance shared so in a Multi-Fiber environment lots of Mutexes will be used, I'll see if I can do it without breaking the whole project down :) that would make the training faster
@drujensen I would also love to hear about your progress, and if you feel like the SHAInet CNN is giving you what you need for your project :slightly_smiling_face:
I have been playing with the CNN network trying to get any results but continue to hit roadblocks and I'm hoping to get some help.
I first converted the images to 48x48x1 greyscale to try and keep things as simple as possible.
I built a network as follows:
I have tried many different configurations for training the model but all seem to error out:
No matter what I try, I get:
Here is the project: https://github.com/drujensen/cats_dogs
Any ideas?