Neural Network Architecture - Accuracy issue

Keras
,
#1

I have a structured dataset having features and 570 classes. I have done a lot of experiments with the architecture but accuracy doesn’t increase. I also normalized the dataset before passing it into the model.
Here is the model architecture.

loss=‘categorical_crossentropy’,
optimizer=‘adam’ also tried SGD(lr=0.01) as well

md=model.fit(X_train,Y_train,validation_data=(X_test,Y_test_c),epochs=1500,batch_size=512, verbose=2 ,shuffle=True, callbacks=[es])

image
image981×544 24.9 KB

#3

It’s ambiguous what you’re doing.
Have you tried TabNet?

#4

No, I haven’t. I try to make my own architecture