Now, we define a class called MetaSGD where we implement the Meta-SGD algorithm. In the __init__ method, we'll initialize all the necessary variables. Then, we define our sigmoid activation function. After this, we define our train function:
class MetaSGD(object):
We define the __init__ method and initialize all necessary 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 self.epochs = 10000 #hyperparameter for the outer loop (outer gradient update) i.e meta optimization self.beta = 0.0001 #randomly ...
