Now, we'll define a class called GradientAgreement_MAML, where we'll implement the gradient agreement MAML algorithm. In the __init__ method, we'll initialize all of the necessary variables. Then, we'll define our sigmoid activation function. Following this, we'll define our train function.
Let's see this step by step and we'll see the overall code:
class GradientAgreement_MAML(object):
We define the __init__ method and initialize all variables:
def __init__(self): #initialize number of tasks i.e number of tasks we need in each batch of tasks self.num_tasks = 2 #number of samples i.e number of shots -number of data points (k) we need to have in each task self.num_samples = 10 #number of epochs i.e training iterations ...
