test_optimizers_by_linear_model.py 文件源码

def _train_linear_classifier(self, model, optimizer, gpu):
        def _make_label(x):
            a = (np.dot(x, self.w) + self.b).reshape((self.BATCH_SIZE, ))
            t = np.empty_like(a).astype(np.int32)
            t[a >= 0] = 0
            t[a < 0] = 1
            return t

        def _make_dataset(batch_size, unit_num, gpu):
            x_data = np.random.uniform(
                -1, 1, (batch_size, unit_num)).astype(np.float32)
            t_data = _make_label(x_data)
            if gpu:
                x_data = cuda.to_gpu(x_data)
                t_data = cuda.to_gpu(t_data)
            x = chainer.Variable(x_data)
            t = chainer.Variable(t_data)
            return x, t

        for _ in six.moves.range(self.EPOCH):
            x, t = _make_dataset(self.BATCH_SIZE, self.UNIT_NUM, gpu)
            model.zerograds()
            y = model(x)
            loss = F.softmax_cross_entropy(y, t)
            loss.backward()
            optimizer.update()

        x_test, t_test = _make_dataset(self.BATCH_SIZE, self.UNIT_NUM, gpu)
        y_test = model(x_test)
        return F.accuracy(y_test, t_test)