thejacket

I know this is old, but try running the script with elevated permissions (sudo) Also try bash instead of sh It helped me

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...

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...

Overall the whole thing seems buggy. Experiencing the same thing on latest versions of Edge and Brave as well.