Actually i am able to implement the autodl using talos model ,but the problem is that model..predict getting same class for all the input samples ,i done R & D on this , i got to know that one we need to add learning rate for model for getting good results in this scenarios, so i would like to know how can i add learning rate in param dict in talos .
here i am providing my parameter dict for reference please suggest on this :
Actually i am able to implement the autodl using talos model ,but the problem is that model..predict getting same class for all the input samples ,i done R & D on this , i got to know that one we need to add learning rate for model for getting good results in this scenarios, so i would like to know how can i add learning rate in param dict in talos .
here i am providing my parameter dict for reference please suggest on this :
p = {'activation':['relu', 'elu'], 'optimizer': ['Nadam', 'Adam'], 'losses': ['logcosh'], 'shapes': ['brick'], 'first_neuron': [16, 32, 64, 128], 'hidden_layers':[0, 1, 2, 3], 'dropout': [.2, .3, .4], 'batch_size': [20, 30, 40, 50], 'epochs': [10]}