import minitorch
import datasets
import time
import matplotlib.pyplot as plt
PTS = 50
DATASET = datasets.Xor(PTS, vis=True)
HIDDEN = 10
RATE = 0.5
def RParam(*shape):
r = 2 * (minitorch.rand(shape) - 0.5)
return minitorch.Parameter(r)
class Network(minitorch.Module):
def __init__(self):
super().__init__()
# Submodules
self.layer1 = Linear(2, HIDDEN)
self.layer2 = Linear(HIDDEN, HIDDEN)
self.layer3 = Linear(HIDDEN, 1)
def forward(self, x):
# TODO: Implement for Task 2.5.
out = self.layer1.forward(x).relu()
out = self.layer2.forward(out).relu()
return self.layer3.forward(out).sigmoid()
import torch
import datasets
import matplotlib.pyplot as plt
PTS = 250
DATASET = datasets.Xor(PTS)
HIDDEN = 10
RATE = 0.5
# Model with
class Network(torch.nn.Module):
def __init__(self):
super().__init__()
# Submodules
self.layer1 = Linear(2, HIDDEN)
self.layer2 = Linear(HIDDEN, HIDDEN)
self.layer3 = Linear(HIDDEN, 1)
def forward(self, x):
h = self.layer1.forward(x).relu()
h = self.layer2.forward(h).relu()
return self.layer3.forward(h).sigmoid()
class Linear(torch.nn.Module):
def __init__(self, in_size, out_size):
super().__init__()
self.weight = torch.nn.Parameter(2 *
(torch.rand(in_size, out_size) - 0.5))