# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import unittest

import numpy as np

import paddle


class TestAdamaxAPI(unittest.TestCase):
    def test_adamax_api_dygraph(self):
        paddle.disable_static()
        value = np.arange(26).reshape(2, 13).astype("float32")
        a = paddle.to_tensor(value)
        linear = paddle.nn.Linear(13, 5)
        adam = paddle.optimizer.Adamax(
            learning_rate=0.01,
            parameters=linear.parameters(),
            weight_decay=0.01,
        )
        out = linear(a)
        out.backward()
        adam.step()
        adam.clear_gradients()


class TestAdamaxAPIWeightDecay(unittest.TestCase):
    def test_weight_decay_int(self):
        paddle.disable_static()
        value = np.arange(26).reshape(2, 13).astype("float32")
        a = paddle.to_tensor(value)
        linear = paddle.nn.Linear(13, 5)
        adam = paddle.optimizer.Adamax(
            learning_rate=0.01,
            parameters=linear.parameters(),
            weight_decay=1,
        )
        out = linear(a)
        out.backward()
        adam.step()
        adam.clear_gradients()


class TestAdamaxAPIGroup(TestAdamaxAPI):
    def test_adamax_api_dygraph(self):
        paddle.disable_static()
        value = np.arange(26).reshape(2, 13).astype("float32")
        a = paddle.to_tensor(value)
        linear_1 = paddle.nn.Linear(13, 5)
        linear_2 = paddle.nn.Linear(5, 3)
        # This can be any optimizer supported by dygraph.
        adam = paddle.optimizer.Adamax(
            learning_rate=0.01,
            parameters=[
                {'params': linear_1.parameters()},
                {
                    'params': linear_2.parameters(),
                    'weight_decay': 0.001,
                    'beta1': 0.1,
                    'beta2': 0.99,
                },
            ],
            weight_decay=0.1,
        )
        out = linear_1(a)
        out = linear_2(out)
        out.backward()
        adam.step()
        adam.clear_gradients()


if __name__ == "__main__":
    unittest.main()