Ananas120
Ananas120
I re-implemented your model architecture in python 3 in my personal project
Yes it is normal ! I found that siamese networks need some epoch (sometimes more than 5 or 10 !) to increase their accuracy and this can be explained as...
I begin to train wavenet now and same issue, i just comment the 2 lines and no other issue (i think) :')
AH... another solution ? ^^'
Do you try to solve it yourself ? I change 1 thing and add 2 things (not sure they are usefull) but it seems to work now... It loads the...
The "wavenet tf-2.0" on your github is a working implementation or it's not finished ? and i don't change that i just change the saver... in the Tacotron model he...
After 5k step training no result but the evaluation at step 4k was bad too so... i will train it for 15k step and see ^^' NOTE : i train...
> Here are some papers that may have the same bug: > "Multi-class motor imagery EEG classification method with high accuracy and low individual differences based on hybrid neural network"...
Yes indeed, my first target was to do it based on a IPTopo class but i didn’t find the information of AS in the class Furthermore, the « json »...
Ok thank you, then i will try to convert a IPTopo to a json file it can be good to visualize the topology etc ! I will not have the...