train epoch acc have no change
myegdfz opened this issue · comments
firstly thx for yr work, and since the version, i made some change in your code, but it works nothing, and every epoch the accurcy rate was not change, like this.
Hi! could you elaborate on what did you change to the code?
since the original not at version tf 2.4, so I change the _write_logs_to_tensorboard to adapt version 2.4, this one
, and the Modified_SGD class's learning_rate, because lr is the father class's attribute.
and i also have a question, i modified the structure of the net, replace the original convolutional layer with vgg16 and add a netvald layer before the last layer
but loss will increase to 36.xx from 5.0. and I can't understand.
Thanks for the details. I would suggest for making sure that the original architecture will decrease the training error in a small dataset.
Only after that I would start making adjustments to the model architecture and follow the same process. Make sure you test adam/modified SGD with different learning rates. By making big adjustments it's hard to identify the reason of non convergence. Hope I was helpful
do you mean if my initial loss is too high, it would be stoped very fast? maybe at iteration 4.
No, I was meaning that making sure you can guarantee first that the architecture converges in a small dataset and that the training loss is decreasing.
I would suggest reading this blog post by Andrej Karpathy, especially the overfit section: