https://colab.research.google.com/drive/1IS4waAk1BBP2x6DmFOSYeY1dvixyzjlf
Can u suggest me some changes that may increase validation accuracy ?
Low val_acc using Transfer Learning for Pokemon classification
Hey @nuts2021, remove this line from your code
X_train = X_train/255.0
Also always make a split using sklearn’s train_test_split like this
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(Xdata, Ydata, test_size=0.20, random_state=42,shuffle = True)
And pass them while training as follows
hist = model_new.fit(X_train,y_train,epochs = 10, batch_size = 16,validation_data = (X_test,y_test),callbacks=[er,mc,rr]).
This gives more trustworthy results than others.
Hope this cleared your doubt.
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.