vaibhavkumar049

learning_rate = 0.2
epochs = 10000

X_train = X_train.float()
Y_train = Y_train.long()

loss_arr = []
acc_arr = []

for epoch in range(epochs):

vaibhavkumar049

torch.manual_seed(0)
weights1 = torch.randn(2, 2) / math.sqrt(2)
weights1.requires_grad_()
bias1 = torch.zeros(2, requires_grad=True)

weights2 = torch.randn(2, 4) / math.sqrt(2)
weights2.requires_grad_()
bias2 = torch.zeros(4, requires_grad=True)

vaibhavkumar049

def accuracy(y_hat, y):
  pred = torch.argmax(y_hat, dim=1)
  return (pred == y).float().mean()

vaibhavkumar049

def loss_fn(y_hat, y):
  return -(y_hat[range(y.shape[0]), y].log()).mean()

vaibhavkumar049

a = torch.rand(2,4)
print(a)
print(a.exp())
print(a.exp().sum(-1))
print(a.exp().sum(-1).shape)
print(a.exp().sum(-1).unsqueeze(-1))
print(a.exp().sum(-1).unsqueeze(-1).shape)

vaibhavkumar049

def model(x):
  a1 = torch.matmul(x, weights1) + bias1 # (N, 2) x (2, 2) -> (N, 2)
  h1 = a1.sigmoid() # (N, 2)
  a2 = torch.matmul(h1, weights2) + bias2 # (N, 2) x (2, 4) -> (N, 4)
  h2 = a2.exp()/a2.exp().sum(-1).unsqueeze(-1) # (N, 4)
  return h2

vaibhavkumar049

X_train, Y_train, X_val, Y_val = map(torch.tensor, (X_train, Y_train, X_val, Y_val))
print(X_train.shape, Y_train.shape)

//torch.Size([750, 2]) torch.Size([750])

vaibhavkumar049

X_train, X_val, Y_train, Y_val = train_test_split(data, labels, stratify=labels, random_state=0)
print(X_train.shape, X_val.shape, labels.shape)

//(750, 2) (250, 2) (1000,)

vaibhavkumar049

my_cmap = matplotlib.colors.LinearSegmentedColormap.from_list("", ["red","yellow","green"])

plt.scatter(data[:,0], data[:,1], c=labels, cmap=my_cmap)
plt.show()

vaibhavkumar049

data, labels = make_blobs(n_samples=1000, centers=4, n_features=2, random_state=0)
print(data.shape, labels.shape)

//(1000, 2) (1000,)