def set_train_model(self, train_set, cost_func, batch_size, learning_rate, l1_a=0.0, l2_a=0.0001):
cost = cost_func(self.p_y, self.y) \
+ self.l1 * l1_a + self.l2 * l2_a
print('compiling train model..')
# compute gradients of weights and biases
updates = []
for i in range(self.depth):
g_w = T.grad(cost, self.weights[i])
g_b = T.grad(cost, self.biases[i])
updates += [(self.weights[i], self.weights[i] - learning_rate * g_w),
(self.biases[i], self.biases[i] - learning_rate * g_b)]
# print(self.train_set[1:3])
train_set_x, train_set_y = train_set
index = self.index
self.train_model = my_theano.function([index], cost, updates=updates, givens={
self.x: self._get_mini_batch(train_set_x, batch_size, index),
self.y: self._get_mini_batch(train_set_y, batch_size, index)
})
# check if using gpu
tu.check_gpu(self.train_model)
def set_train_model(self, train_set, cost_func, batch_size, learning_rate, l1_a=0.0, l2_a=0.0001):
self.p_y = self.forward(self.x, batch_size)
cost = cost_func(self.p_y, self.y) + self.l1 * l1_a + self.l2 * l2_a
# set early stopping patience
self.patience = 20
self.lest_valid_error = np.inf
print('compiling train model..')
# compute gradients of weights and biases
updates = []
for layer in reversed(self.weighted_layers):
g_w = T.grad(cost, layer.w)
g_b = T.grad(cost, layer.b)
updates += [(layer.w, layer.w - learning_rate * g_w),
(layer.b, layer.b - learning_rate * g_b)]
train_set_x, train_set_y = train_set
index = self.index
self.train_model = my_theano.function([index], cost, updates=updates, givens={
self.x: self._get_mini_batch(train_set_x, batch_size, index),
self.y: self._get_mini_batch(train_set_y, batch_size, index)
})
# check if using gpu
tu.check_gpu(self.train_model)
def set_train_model(self,
train_set,
cost_func,
batch_size,
learning_rate,
l1_a=0.0,
l2_a=0.0001):
self.p_y = self.forward(self.x, batch_size)
cost = cost_func(self.p_y, self.y) + self.l1 * l1_a + self.l2 * l2_a
# set early stopping patience
self.patience = 20
self.lest_valid_error = np.inf
print('compiling train model..')
# compute gradients of weights and biases
updates = []
for layer in reversed(self.weighted_layers):
g_w = T.grad(cost, layer.w)
g_b = T.grad(cost, layer.b)
updates += [(layer.w, layer.w - learning_rate * g_w),
(layer.b, layer.b - learning_rate * g_b)]
train_set_x, train_set_y = train_set
index = self.index
self.train_model = my_theano.function(
[index],
cost,
updates=updates,
givens={
self.x: self._get_mini_batch(train_set_x, batch_size, index),
self.y: self._get_mini_batch(train_set_y, batch_size, index)
})
# check if using gpu
tu.check_gpu(self.train_model)
