# Copyright 2020 Huawei Technologies Co., Ltd
#
# 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.
# ============================================================================
"""
Lenet Tutorial
"""
import os
import argparse
import mindspore.dataset as ds
import mindspore.nn as nn
from mindspore import context, Tensor
from mindspore.train.serialization import load_checkpoint, load_param_into_net
from mindspore.train.callback import ModelCheckpoint, CheckpointConfig, LossMonitor
from mindspore.train import Model
import mindspore.ops.operations as P
from mindspore.common.initializer import TruncatedNormal
import mindspore.dataset.transforms.vision.c_transforms as CV
import mindspore.dataset.transforms.c_transforms as C
from mindspore.dataset.transforms.vision import Inter
from mindspore.nn.metrics import Accuracy
from mindspore.common import dtype as mstype
from mindspore.nn.loss import SoftmaxCrossEntropyWithLogits


def create_dataset(data_path, batch_size=32, repeat_size=1,
                   num_parallel_workers=1):
    """
    create dataset for train or test
    """
    # define dataset
    mnist_ds = ds.MnistDataset(data_path)

    resize_height, resize_width = 32, 32
    rescale = 1.0 / 255.0
    shift = 0.0
    rescale_nml = 1 / 0.3081
    shift_nml = -1 * 0.1307 / 0.3081

    # define map operations
    resize_op = CV.Resize((resize_height, resize_width), interpolation=Inter.LINEAR)  # Bilinear mode
    rescale_nml_op = CV.Rescale(rescale_nml, shift_nml)
    rescale_op = CV.Rescale(rescale, shift)
    hwc2chw_op = CV.HWC2CHW()
    type_cast_op = C.TypeCast(mstype.int32)

    # apply map operations on images
    mnist_ds = mnist_ds.map(input_columns="label", operations=type_cast_op, num_parallel_workers=num_parallel_workers)
    mnist_ds = mnist_ds.map(input_columns="image", operations=resize_op, num_parallel_workers=num_parallel_workers)
    mnist_ds = mnist_ds.map(input_columns="image", operations=rescale_op, num_parallel_workers=num_parallel_workers)
    mnist_ds = mnist_ds.map(input_columns="image", operations=rescale_nml_op, num_parallel_workers=num_parallel_workers)
    mnist_ds = mnist_ds.map(input_columns="image", operations=hwc2chw_op, num_parallel_workers=num_parallel_workers)

    # apply DatasetOps
    buffer_size = 10000
    mnist_ds = mnist_ds.shuffle(buffer_size=buffer_size)  # 10000 as in LeNet train script
    mnist_ds = mnist_ds.batch(batch_size, drop_remainder=True)
    mnist_ds = mnist_ds.repeat(repeat_size)

    return mnist_ds

def conv(in_channels, out_channels, kernel_size, stride=1, padding=0):
    """
    conv layer weight initial
    """
    weight = weight_variable()
    return nn.Conv2d(in_channels, out_channels,
                     kernel_size=kernel_size, stride=stride, padding=padding,
                     weight_init=weight, has_bias=False, pad_mode="valid")

def fc_with_initialize(input_channels, out_channels):
    """
    fc layer weight initial
    """
    weight = weight_variable()
    bias = weight_variable()
    return nn.Dense(input_channels, out_channels, weight, bias)

def weight_variable():
    """
    weight initial
    """
    return TruncatedNormal(0.02)

class LeNet5(nn.Cell):
    """
    Lenet network
    """
    def __init__(self):
        super(LeNet5, self).__init__()
        self.batch_size = 32
        self.conv1 = conv(1, 6, 5)
        self.conv2 = conv(6, 16, 5)
        self.fc1 = fc_with_initialize(16 * 5 * 5, 120)
        self.fc2 = fc_with_initialize(120, 84)
        self.fc3 = fc_with_initialize(84, 10)
        self.relu = nn.ReLU()
        self.max_pool2d = nn.MaxPool2d(kernel_size=2, stride=2)
        self.reshape = P.Reshape()

    def construct(self, x):
        x = self.conv1(x)
        x = self.relu(x)
        x = self.max_pool2d(x)
        x = self.conv2(x)
        x = self.relu(x)
        x = self.max_pool2d(x)
        x = self.reshape(x, (self.batch_size, -1))
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        x = self.relu(x)
        x = self.fc3(x)
        return x

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='MindSpore LeNet Example')
    parser.add_argument('--device_target', type=str, default="CPU", choices=['Ascend', 'GPU', 'CPU'],
                        help='device where the code will be implemented (default: CPU)')
    parser.add_argument('--dataset_sink_mode', type=bool, default=False, help='dataset_sink_mode is False or True')
    args = parser.parse_args()
    context.set_context(mode=context.GRAPH_MODE, device_target=args.device_target,
                        enable_mem_reuse=False)
    lr = 0.01
    momentum = 0.9
    epoch_size = 1
    mnist_path = "/tmp/test/MNIST/MNIST_Data/"
    net_loss = SoftmaxCrossEntropyWithLogits(is_grad=False, sparse=True, reduction='mean')
    repeat_size = epoch_size
    network = LeNet5()
    net_opt = nn.Momentum(network.trainable_params(), lr, momentum)
    config_ck = CheckpointConfig(save_checkpoint_steps=1875, keep_checkpoint_max=10)
    ckpoint_cb = ModelCheckpoint(prefix="checkpoint_lenet", config=config_ck)
    model = Model(network, net_loss, net_opt, metrics={"Accuracy": Accuracy()})

    print("============== Starting Training ==============")
    ds_train = create_dataset(os.path.join(mnist_path, "train"), 32, repeat_size)
    model.train(epoch_size, ds_train, callbacks=[ckpoint_cb, LossMonitor()],
                dataset_sink_mode=args.dataset_sink_mode) # train

    print("============== Starting Testing ==============")
    param_dict = load_checkpoint("checkpoint_lenet-1_1875.ckpt")
    load_param_into_net(network, param_dict)
    ds_eval = create_dataset(os.path.join(mnist_path, "test")) # test
    acc = model.eval(ds_eval, dataset_sink_mode=args.dataset_sink_mode)
    print("============== Accuracy:{} ==============".format(acc))