# Copyright (C) 2017-2023  Cleanlab Inc.
# This file is part of cleanlab.
#
# cleanlab is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published
# by the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# cleanlab is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with cleanlab.  If not, see <https://www.gnu.org/licenses/>.

"""
A PyTorch CNN which can be used for finding label issues in CIFAR-10 and CleanLearning with co-teaching.

Code adapted from: https://github.com/bhanML/Co-teaching/blob/master/model.py

You must have PyTorch installed: https://pytorch.org/get-started/locally/
"""


import torch.nn as nn
import torch.nn.functional as F


def call_bn(bn, x):
    return bn(x)


class CNN(nn.Module):
    """A CNN architecture shown to be a good baseline for a CIFAR-10 benchmark.

    Parameters
    ----------
    input_channel : int
    n_outputs : int
    dropout_rate : float
    top_bn : bool

    Methods
    -------
    forward
      forward pass in PyTorch"""

    def __init__(self, input_channel=3, n_outputs=10, dropout_rate=0.25, top_bn=False):
        self.dropout_rate = dropout_rate
        self.top_bn = top_bn
        super(CNN, self).__init__()
        self.c1 = nn.Conv2d(input_channel, 128, kernel_size=3, stride=1, padding=1)
        self.c2 = nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1)
        self.c3 = nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1)
        self.c4 = nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1)
        self.c5 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1)
        self.c6 = nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1)
        self.c7 = nn.Conv2d(256, 512, kernel_size=3, stride=1, padding=0)
        self.c8 = nn.Conv2d(512, 256, kernel_size=3, stride=1, padding=0)
        self.c9 = nn.Conv2d(256, 128, kernel_size=3, stride=1, padding=0)
        self.l_c1 = nn.Linear(128, n_outputs)
        self.bn1 = nn.BatchNorm2d(128)
        self.bn2 = nn.BatchNorm2d(128)
        self.bn3 = nn.BatchNorm2d(128)
        self.bn4 = nn.BatchNorm2d(256)
        self.bn5 = nn.BatchNorm2d(256)
        self.bn6 = nn.BatchNorm2d(256)
        self.bn7 = nn.BatchNorm2d(512)
        self.bn8 = nn.BatchNorm2d(256)
        self.bn9 = nn.BatchNorm2d(128)

    def forward(
        self,
        x,
    ):
        h = x
        h = self.c1(h)
        h = F.leaky_relu(call_bn(self.bn1, h), negative_slope=0.01)
        h = self.c2(h)
        h = F.leaky_relu(call_bn(self.bn2, h), negative_slope=0.01)
        h = self.c3(h)
        h = F.leaky_relu(call_bn(self.bn3, h), negative_slope=0.01)
        h = F.max_pool2d(h, kernel_size=2, stride=2)
        h = F.dropout2d(h, p=self.dropout_rate)

        h = self.c4(h)
        h = F.leaky_relu(call_bn(self.bn4, h), negative_slope=0.01)
        h = self.c5(h)
        h = F.leaky_relu(call_bn(self.bn5, h), negative_slope=0.01)
        h = self.c6(h)
        h = F.leaky_relu(call_bn(self.bn6, h), negative_slope=0.01)
        h = F.max_pool2d(h, kernel_size=2, stride=2)
        h = F.dropout2d(h, p=self.dropout_rate)

        h = self.c7(h)
        h = F.leaky_relu(call_bn(self.bn7, h), negative_slope=0.01)
        h = self.c8(h)
        h = F.leaky_relu(call_bn(self.bn8, h), negative_slope=0.01)
        h = self.c9(h)
        h = F.leaky_relu(call_bn(self.bn9, h), negative_slope=0.01)
        h = F.avg_pool2d(h, kernel_size=h.data.shape[2])

        h = h.view(h.size(0), h.size(1))
        logit = self.l_c1(h)
        if self.top_bn:
            logit = call_bn(self.bn_c1, logit)
        return logit