Can't get it to work, overfitting? about computer-vision-basics-with-python-keras-and-opencv HOT 5 OPEN

It's hard to tell without code. If you can link me a repo with your fork, it would be a lot easier.

Also you posted two training accuracy graphs, what does validation look like over the training?

from computer-vision-basics-with-python-keras-and-opencv.

Thank you sir for quick reply

I plotted the data from different try on one graph:

Pushed my changes here: (there are training and validation images in the repo too)
https://github.com/thejacket/Computer-Vision-Basics-with-Python-Keras-and-OpenCV/blob/master/notebook.ipynb

I've tried to tinker with the ImageDataGeneration parameters but still the results are pretty bad.
Also I have recorded the training data several times, trying to move my hand, fingers a little but with no positive results.

from computer-vision-basics-with-python-keras-and-opencv.

Did you take any look? I've also had an idea that due to dilation the picture's hand structure is too thick (having in consideration how NN's pooling algorithms work) so i tried to erode instead - it gives me much more skeleton-like pictures. Unfortunately still no look, and the model is skewed towards predicting 'five'

from computer-vision-basics-with-python-keras-and-opencv.

I seem to be having a similar problem, any fix? @thejacket @jrobchin

from computer-vision-basics-with-python-keras-and-opencv.

Sorry for not responding earlier. I was never able to diagnose the problem. I would say try the model that is provided in the model folder first and make sure it’s not an issue with the code.

from computer-vision-basics-with-python-keras-and-opencv.