# 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 paddle
import numpy as np
import paddle.fluid as fluid


class TestAdamWOp(unittest.TestCase):
    def test_adamw_op_dygraph(self):
        paddle.disable_static()
        value = np.arange(26).reshape(2, 13).astype("float32")
        a = paddle.to_variable(value)
        linear = paddle.nn.Linear(13, 5, dtype="float32")
        adam = paddle.optimizer.AdamW(
            learning_rate=0.01,
            parameters=linear.parameters(),
            apply_decay_param_fun=lambda name: True,
            weight_decay=0.01)
        out = linear(a)
        out.backward()
        adam.step()
        adam.clear_gradients()

    def test_adamw_op_coverage(self):
        paddle.disable_static()
        value = np.arange(26).reshape(2, 13).astype("float32")
        a = paddle.to_variable(value)
        linear = paddle.nn.Linear(13, 5, dtype="float32")
        adam = paddle.optimizer.AdamW(
            learning_rate=0.0,
            parameters=linear.parameters(),
            apply_decay_param_fun=lambda name: True,
            weight_decay=0.01)
        assert (adam.__str__() is not None)

    def test_adamw_op(self):
        place = fluid.CPUPlace()
        shape = [2, 3, 8, 8]
        exe = fluid.Executor(place)
        train_prog = fluid.Program()
        startup = fluid.Program()
        with fluid.program_guard(train_prog, startup):
            with fluid.unique_name.guard():
                data = fluid.data(name="data", shape=shape)
                conv = fluid.layers.conv2d(data, 8, 3)
                loss = paddle.mean(conv)

                beta1 = fluid.layers.create_global_var(
                    shape=[1], value=0.85, dtype='float32', persistable=True)
                beta2 = fluid.layers.create_global_var(
                    shape=[1], value=0.95, dtype='float32', persistable=True)
                betas = [beta1, beta2]
                opt = paddle.optimizer.AdamW(
                    learning_rate=1e-5,
                    beta1=beta1,
                    beta2=beta2,
                    weight_decay=0.01,
                    epsilon=1e-8)
                opt.minimize(loss)

        exe.run(startup)
        data_np = np.random.random(shape).astype('float32')
        rets = exe.run(train_prog, feed={"data": data_np}, fetch_list=[loss])
        assert rets[0] is not None


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