def test02_sgd_sanity_with_epochs(self):
C, W0, X, _, _ = create_C_W_X_d()
optimizer = SGD(batch_size=256, m=X.shape[1])
W = W0.copy()
for epoch in range(15):
W = optimizer.optimize(W,
X,
C,
objective_soft_max,
objective_soft_max_gradient_W,
lr=1)
self.assertTrue(True)
def train(C_train, C_val, X_train, X_val, batch_size, epochs, lr, momentum=0):
# ----------------- hyper params init -----------------
W0 = randn(X_train.shape[0], C_train.shape[0])
m, n = W0.shape
W = W0.copy()
optimizer = SGD(batch_size=batch_size, m=X_train.shape[1])
# ----------------------------------------------------
# ----------------- stats lists init -----------------
W_history = zeros((W.shape[0] * W.shape[1], epochs))
val_score = []
train_score = []
train_acc = []
val_acc = []
# ----------------------------------------------------
for epoch in range(epochs):
W = optimizer.optimize(W,
X_train,
C_train,
objective_soft_max,
objective_soft_max_gradient_W,
lr=lr,
momentum=momentum)
W_history[:, epoch] = W.reshape(W.shape[0] * W.shape[1])
train_score.append(objective_soft_max(X_train, W, C_train))
val_score.append(objective_soft_max(X_val, W, C_val))
train_acc.append(accuracy(X_train, W, C_train))
val_acc.append(accuracy(X_val, W, C_val))
W_res = average(W_history, axis=1).reshape(m, n)
train_score.append(objective_soft_max(X_train, W_res, C_train))
val_score.append(objective_soft_max(X_val, W_res, C_val))
# todo add plot epoch \ accuracy (wrote in train)
plot(range(len(train_score)), train_score)
return train_score, train_acc, val_score, val_acc
def test01_sgd_sanity(self):
C, W0, X, _, _ = create_C_W_X_d()
optimizer = SGD(batch_size=256, m=X.shape[1])
W = optimizer.optimize(W0, X, C, objective_soft_max,
objective_soft_max_gradient_W)
self.assertTrue(True)