# -*- coding: utf-8 -*-


import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import models
from torchvision.models.vgg import VGG
# from BagData import dataloader
from data_train import dataloader
from data_val import dataloader_val
import pdb
import numpy as np 
import time
import matplotlib.pyplot as plt
# import visdom
import os




class FCN32s(nn.Module):

    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  # size=(N, 512, x.H/32, x.W/32)

        score = self.bn1(self.relu(self.deconv1(x5)))     # size=(N, 512, x.H/16, x.W/16)
        score = self.bn2(self.relu(self.deconv2(score)))  # size=(N, 256, x.H/8, x.W/8)
        score = self.bn3(self.relu(self.deconv3(score)))  # size=(N, 128, x.H/4, x.W/4)
        score = self.bn4(self.relu(self.deconv4(score)))  # size=(N, 64, x.H/2, x.W/2)
        score = self.bn5(self.relu(self.deconv5(score)))  # size=(N, 32, x.H, x.W)
        score = self.classifier(score)                    # size=(N, n_class, x.H/1, x.W/1)

        return score  # size=(N, n_class, x.H/1, x.W/1)


class FCN16s(nn.Module):

    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  # size=(N, 512, x.H/32, x.W/32)
        x4 = output['x4']  # size=(N, 512, x.H/16, x.W/16)

        score = self.relu(self.deconv1(x5))               # size=(N, 512, x.H/16, x.W/16)
        score = self.bn1(score + x4)                      # element-wise add, size=(N, 512, x.H/16, x.W/16)
        score = self.bn2(self.relu(self.deconv2(score)))  # size=(N, 256, x.H/8, x.W/8)
        score = self.bn3(self.relu(self.deconv3(score)))  # size=(N, 128, x.H/4, x.W/4)
        score = self.bn4(self.relu(self.deconv4(score)))  # size=(N, 64, x.H/2, x.W/2)
        score = self.bn5(self.relu(self.deconv5(score)))  # size=(N, 32, x.H, x.W)
        score = self.classifier(score)                    # size=(N, n_class, x.H/1, x.W/1)

        return score  # size=(N, n_class, x.H/1, x.W/1)


class FCN8s(nn.Module):

    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  # size=(N, 512, x.H/32, x.W/32)
        x4 = output['x4']  # size=(N, 512, x.H/16, x.W/16)
        x3 = output['x3']  # size=(N, 256, x.H/8,  x.W/8)

        score = self.relu(self.deconv1(x5))               # size=(N, 512, x.H/16, x.W/16)
        score = self.bn1(score + x4)                      # element-wise add, size=(N, 512, x.H/16, x.W/16)
        score = self.relu(self.deconv2(score))            # size=(N, 256, x.H/8, x.W/8)
        score = self.bn2(score + x3)                      # element-wise add, size=(N, 256, x.H/8, x.W/8)
        score = self.bn3(self.relu(self.deconv3(score)))  # size=(N, 128, x.H/4, x.W/4)
        score = self.bn4(self.relu(self.deconv4(score)))  # size=(N, 64, x.H/2, x.W/2)
        score = self.bn5(self.relu(self.deconv5(score)))  # size=(N, 32, x.H, x.W)
        score = self.classifier(score)                    # size=(N, n_class, x.H/1, x.W/1)

        return score  # size=(N, n_class, x.H/1, x.W/1)


class FCNs(nn.Module):

    def __init__(self, pretrained_net, n_class):
        super().__init__()
        self.n_class = n_class
        self.pretrained_net = pretrained_net
        self.relu    = nn.ReLU(inplace=True)
        self.deconv1 = nn.ConvTranspose2d(512, 512, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn1     = nn.BatchNorm2d(512)
        self.deconv2 = nn.ConvTranspose2d(512, 256, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn2     = nn.BatchNorm2d(256)
        self.deconv3 = nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn3     = nn.BatchNorm2d(128)
        self.deconv4 = nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn4     = nn.BatchNorm2d(64)
        self.deconv5 = nn.ConvTranspose2d(64, 32, kernel_size=3, stride=2, padding=1, dilation=1, output_padding=1)
        self.bn5     = nn.BatchNorm2d(32)
        self.classifier = nn.Conv2d(32, n_class, kernel_size=1)

    def forward(self, x):
        output = self.pretrained_net(x)
        x5 = output['x5']  # size=(N, 512, x.H/32, x.W/32)
        x4 = output['x4']  # size=(N, 512, x.H/16, x.W/16)
        x3 = output['x3']  # size=(N, 256, x.H/8,  x.W/8)
        x2 = output['x2']  # size=(N, 128, x.H/4,  x.W/4)
        x1 = output['x1']  # size=(N, 64, x.H/2,  x.W/2)

        score = self.bn1(self.relu(self.deconv1(x5)))     # size=(N, 512, x.H/16, x.W/16)
        score = score + x4                                # element-wise add, size=(N, 512, x.H/16, x.W/16)
        score = self.bn2(self.relu(self.deconv2(score)))  # size=(N, 256, x.H/8, x.W/8)
        score = score + x3                                # element-wise add, size=(N, 256, x.H/8, x.W/8)
        score = self.bn3(self.relu(self.deconv3(score)))  # size=(N, 128, x.H/4, x.W/4)
        score = score + x2                                # element-wise add, size=(N, 128, x.H/4, x.W/4)
        score = self.bn4(self.relu(self.deconv4(score)))  # size=(N, 64, x.H/2, x.W/2)
        score = score + x1                                # element-wise add, size=(N, 64, x.H/2, x.W/2)
        score = self.bn5(self.relu(self.deconv5(score)))  # size=(N, 32, x.H, x.W)
        score = self.classifier(score)                    # size=(N, n_class, x.H/1, x.W/1)

        return score  # size=(N, n_class, x.H/1, x.W/1)


class VGGNet(VGG):
    def __init__(self, pretrained=True, model='vgg16', requires_grad=True, remove_fc=True, show_params=False):
        super().__init__(make_layers(cfg[model]))
        self.ranges = ranges[model]

        if pretrained:
            exec("self.load_state_dict(models.%s(pretrained=True).state_dict())" % model)

        if not requires_grad:
            for param in super().parameters():
                param.requires_grad = False

        if remove_fc:  # delete redundant fully-connected layer params, can save memory
            del self.classifier

        if show_params:
            for name, param in self.named_parameters():
                print(name, param.size())

    def forward(self, x):
        output = {}
        # get the output of each maxpooling layer (5 maxpool in VGG net)
        for idx in range(len(self.ranges)):
            for layer in range(self.ranges[idx][0], self.ranges[idx][1]):
                x = self.features[layer](x)
            output["x%d"%(idx+1)] = x

        return output


ranges = {
    'vgg11': ((0, 3), (3, 6),  (6, 11),  (11, 16), (16, 21)),
    'vgg13': ((0, 5), (5, 10), (10, 15), (15, 20), (20, 25)),
    'vgg16': ((0, 5), (5, 10), (10, 17), (17, 24), (24, 31)),
    'vgg19': ((0, 5), (5, 10), (10, 19), (19, 28), (28, 37))
}

# cropped version from https://github.com/pytorch/vision/blob/master/torchvision/models/vgg.py
cfg = {
    'vgg11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'vgg13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'vgg16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'vgg19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}

def make_layers(cfg, batch_norm=False):
    layers = []
    in_channels = 3
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    return nn.Sequential(*layers)


if __name__ == "__main__":
    # vis = visdom.Visdom()
    vgg_model = VGGNet(requires_grad=True)
    fcn_model = FCNs(pretrained_net=vgg_model, n_class=2)
    fcn_model = fcn_model.cuda()
    criterion = nn.BCELoss().cuda()
    optimizer = optim.SGD(fcn_model.parameters(), lr=1e-2, momentum=0.7)
    #input = torch.autograd.Variable(torch.randn(batch_size, 3, h, w))
    #y = torch.autograd.Variable(torch.randn(batch_size, n_class, h, w), requires_grad=False)
    # saving_index =0
    print('Train {},Validation {}'.format(len(dataloader)*4,len(dataloader_val)*4))
    epochs=10
    train_loss=[]
    valid_loss=[]
    for epo in range(epochs):
        start = time.time()
        
        epo_loss = 0
        fcn_model.train()
        for item in dataloader:
            input = item['A']
            y = item['B']
            input = torch.autograd.Variable(input)
            y = torch.autograd.Variable(y)
            input = input.cuda()
            y = y.cuda()
            optimizer.zero_grad()
            output = fcn_model(input)
            output = nn.functional.sigmoid(output)
            loss = criterion(output, y)
            loss.backward()
            epo_loss +=  loss.item()
            optimizer.step()

            # output_np = output.cpu().data.numpy().copy()
            # output_np = np.argmin(output_np, axis=1)
            # y_np = y.cpu().data.numpy().copy()
            # y_np = np.argmin(y_np, axis=1)
            
        val_loss = 0
        fcn_model.eval()
        with torch.no_grad():
            for item in dataloader_val:
                input = item['A']
                y = item['B']
                input = torch.autograd.Variable(input)
                y = torch.autograd.Variable(y)
                input = input.cuda()
                y = y.cuda()
                optimizer.zero_grad()
                output = fcn_model(input)
                output = nn.functional.sigmoid(output)
                loss = criterion(output, y)
                
                val_loss += loss.item()
            # optimizer.step()
            
            # output_np = output.cpu().data.numpy().copy()
            # output_np = np.argmin(output_np, axis=1)
            # y_np = y.cpu().data.numpy().copy()
            # y_np = np.argmin(y_np, axis=1)
            

        end = time.time()
        trainingLoss = epo_loss/len(dataloader)
        validationLoss = val_loss/len(dataloader_val)
        train_loss.append(trainingLoss)
        valid_loss.append(validationLoss)
        print('epoch loss = %f'%(trainingLoss),
               'validation loss = %f'%(validationLoss),
              'time cost',end-start,'s')
        
        # if np.mod(saving_index, 2)==1:
        if not os.path.exists('checkpoints'):
            os.makedirs('checkpoints')
        torch.save(fcn_model, 'checkpoints/fcn_model_{}.pt'.format(epo))
        print('saveing checkpoints/fcn_model_{}.pt \n'.format(epo))
    
        np.save('training loss', train_loss)
        np.save('validation loss', valid_loss)
    
        # imagename = 'Loss'
        # print(a)
    y1 = train_loss
    y2 = valid_loss
        # print(y)
    x = np.array(range(epochs))
        # print(x.shape)
    plt.plot(x,y1, label = 'trainingloss')
    plt.plot(x,y2, label = 'validloss')
    plt.xlabel('Epoch')
    plt.ylabel('Loss')
    plt.legend()
    plt.savefig('Loss'+'.png')
    plt.show()