# Copyright (c) Chris Choy (chrischoy@ai.stanford.edu).
#
# Permission is hereby granted, free of charge, to any person obtaining a copy of
# this software and associated documentation files (the "Software"), to deal in
# the Software without restriction, including without limitation the rights to
# use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
# of the Software, and to permit persons to whom the Software is furnished to do
# so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#
# Please cite "4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural
# Networks", CVPR'19 (https://arxiv.org/abs/1904.08755) if you use any part
# of the code.
import torch
import torch.nn as nn
from torch.optim import SGD

import MinkowskiEngine as ME

from tests.python.common import data_loader


class ExampleNetwork(ME.MinkowskiNetwork):

    def __init__(self, in_feat, out_feat, D):
        super(ExampleNetwork, self).__init__(D)
        self.net = nn.Sequential(
            ME.MinkowskiConvolution(
                in_channels=in_feat,
                out_channels=64,
                kernel_size=3,
                stride=2,
                dilation=1,
                bias=False,
                dimension=D), ME.MinkowskiBatchNorm(64), ME.MinkowskiReLU(),
            ME.MinkowskiConvolution(
                in_channels=64,
                out_channels=128,
                kernel_size=3,
                stride=2,
                dimension=D), ME.MinkowskiBatchNorm(128), ME.MinkowskiReLU(),
            ME.MinkowskiGlobalPooling(),
            ME.MinkowskiLinear(128, out_feat))

    def forward(self, x):
        return self.net(x)


if __name__ == '__main__':
    # loss and network
    criterion = nn.CrossEntropyLoss()
    net = ExampleNetwork(in_feat=3, out_feat=5, D=2)
    print(net)

    # a data loader must return a tuple of coords, features, and labels.
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

    net = net.to(device)
    optimizer = SGD(net.parameters(), lr=1e-1)

    for i in range(10):
        optimizer.zero_grad()

        # Get new data
        coords, feat, label = data_loader()
        input = ME.SparseTensor(feat, coords, device=device)
        label = label.to(device)

        # Forward
        output = net(input)

        # Loss
        loss = criterion(output.F, label)
        print('Iteration: ', i, ', Loss: ', loss.item())

        # Gradient
        loss.backward()
        optimizer.step()

    # Saving and loading a network
    torch.save(net.state_dict(), 'test.pth')
    net.load_state_dict(torch.load('test.pth'))