Closed ersamo closed 3 years ago
is there any help please ?
Better suited for stackoverflow
@ersamo try tuning the layers and hyperparameters using keras tuner
@ersamo This is not Build/Installation or Bug/Performance issue. Please post this kind of support questions at TF Forum. There is a big community to support and learn from your questions. GitHub is mainly for addressing bugs in installation and performance. Thanks!
Looking at your model, i think you may need to add some more hidden layers, change some hyper parameters, tune the model, check the diversity in the input data, etc. I am sure, you will get much more support from TF Forum. Thanks!
the model as follows
i set
history = model.fit(train_generator, epochs=20, steps_per_epoch=train_steps, verbose=1, callbacks=[checkpoint], validation_data=val_generator, validation_steps=val_steps,batch_size=16)
and got
training set is 82700 and testing is 40500 .. Should i wait until i got the lower val_loss ? or what the factors that should i take to decide that model best fit ? i run it before and got at epoch 6 that there is no improvement .. is there any problem in the model ? Should i increase epochs to 70 instead of 20 ?