import torch
import torch.nn as nn
import math
import torch.optim as optim
import sys
import os

def op_name(op_name, m):
    m.op_name = op_name
    return m

class Flatten(nn.Module):
    def __init__(self, axis):
        super(Flatten, self).__init__()

    def forward(self, x):
        x = x.view(-1, 2560)
        return x

def flatten(name, axis):
    return op_name(name, Flatten(axis))

def conv_bn_relu(name, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, momentum = 0.1, track_running_stats=True):
    return nn.Sequential(
        op_name(name, nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, dilation, groups, False)),
        op_name(name + '/bn', nn.BatchNorm2d(out_channels, momentum = momentum, track_running_stats = track_running_stats)),
        op_name(name + '/relu', nn.ReLU(inplace=True)),
    )

def linear_bn_relu(name, in_features, out_features, momentum = 0.1, track_running_stats=True):
    return nn.Sequential(
        op_name(name + '/FC', nn.Linear(in_features, out_features)),
        op_name(name + '/bn', nn.BatchNorm1d(out_features, momentum = momentum, track_running_stats = track_running_stats)),
        op_name(name + '/relu', nn.ReLU(inplace=True)),
    )

# Define a Basic resnet block
class BasicResnetBlock(nn.Module):
    def __init__(self, name, in_channels, out_channels, kernel_size=3, stride=2, padding=1, direct_plus=False):
        super(BasicResnetBlock, self).__init__()

        self.op_name = name

        self.conv_block = nn.Sequential(
            conv_bn_relu(name=name + '/conv1', in_channels=in_channels, out_channels=out_channels,
                         kernel_size=kernel_size, stride=stride, padding=padding),

            conv_bn_relu(name=name + '/conv2', in_channels=out_channels, out_channels=out_channels,
                         kernel_size=3, stride=1, padding=1)
        )

        if direct_plus and (in_channels == out_channels) and (stride == 1):
            self.sc_block = None
        else:
            self.sc_block = conv_bn_relu(name=name + '/sc_conv', in_channels=in_channels, out_channels=out_channels,
                                         kernel_size=1, stride=stride, padding=0)

    def forward(self, x):
        if self.sc_block is None:
            out = x + self.conv_block(x)
        else:
            out = self.conv_block(x) + self.sc_block(x)
        return out

class SuperBigResNetV2(nn.Module):
    def __init__(self, name, in_channels, out_channels):
        super(SuperBigResNetV2, self).__init__()
        self.op_name = name

        input_size = 256

        op_list = []

        stride_cnt = 4

        op_list += [conv_bn_relu(name + '/first_conv', in_channels, 48, kernel_size=5, stride=4, padding=2)]

        ch_num = [48, 64, 96, 128, 160]
        for i in range(len(ch_num) - 1):
            if ch_num[i] == ch_num[i+1]:
                op_list += [BasicResnetBlock(name + '/stage%d'%(i + 1), ch_num[i], ch_num[i+1], kernel_size=3, stride=1, direct_plus=True)]
            else:
                stride_cnt = stride_cnt * 2
                op_list += [BasicResnetBlock(name + '/stage%d'%(i + 1), ch_num[i], ch_num[i+1], kernel_size=3, stride=2)]

        item_cnt = int((input_size / stride_cnt) * (input_size / stride_cnt) * ch_num[-1])
        op_list += [flatten(name + '/flatten', 1),
                     linear_bn_relu(name + '/FC1', item_cnt, 512),
                     op_name(name + '/FC2', nn.Linear(512, out_channels))]

        self.conv_block = nn.Sequential(*op_list)

        self.model_path, _ = os.path.split(os.path.realpath(__file__))

        self.weights = torch.load(os.path.join(self.model_path, 'SuperBigResNetV2_latest.pth'),
                             map_location=lambda storage, loc: storage)

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

if __name__=='__main__':
    pass