def network1( input_shape=INPUT_SHAPE ): #before proceding further please analyse the network.py,pipeline.py in folder pipeline(it's an order not a request!!) return (NeuralNetwork().input(input_shape).conv( [5, 5, 6]) #filters in conv. layer .max_pool().relu().flatten().dense(120) #neurons in dense layer .relu().dense(N_CLASSES))
def make_network2(input_shape=INPUT_SHAPE): return (NeuralNetwork() .input(input_shape) .conv([5, 5, 12]) # <== doubled .max_pool() .relu() .conv([5, 5, 32]) # <== doubled .max_pool() .relu() .flatten() .dense(240) # <== doubled .relu() .dense(N_CLASSES))
def make_network5(input_shape=INPUT_SHAPE): return (NeuralNetwork().input(input_shape).conv( [5, 5, 24]).max_pool().elu() # <== ELU .conv([5, 5, 64]).max_pool().elu() # <== ELU .flatten().dense(480).elu() # <== ELU .dense(N_CLASSES))
def make_network7(input_shape=INPUT_SHAPE): return (NeuralNetwork().input(input_shape).conv( [5, 5, 24]).max_pool().relu().conv( [5, 5, 64]).max_pool().relu().flatten().dense(480).relu().dense( 240) # <== one more dense layer .relu().dense(N_CLASSES))
def make_network9(input_shape=INPUT_SHAPE): return (NeuralNetwork().input(input_shape).conv( [5, 5, 24]).max_pool().relu().conv([5, 5, 64]).max_pool().relu().conv( [3, 3, 64]) # <= smaller kernel here (the image is small by here) .max_pool().relu().flatten().dense(480).relu().dense(N_CLASSES))