import pytorch_lightning as pl

import torch
from torch import nn
from torch.nn import functional as F
from torch.utils.data import random_split, DataLoader
import torch.optim as optim

from torchmetrics import Accuracy

from torchvision import transforms




class BasicBlock(pl.LightningModule):
    expansion = 1

    def __init__(self, in_planes, planes, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)

        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != self.expansion*planes:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(self.expansion*planes)
            )

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        out += self.shortcut(x)
        out = F.relu(out)
        return out


class ResNet(pl.LightningModule):
    def __init__(self, block, num_blocks, num_classes=10):
        super(ResNet, self).__init__()
        self.in_planes = 64

        self.learning_rate = 0.001

        self.accuracy = Accuracy(task='multiclass', num_classes=10)



        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
        self.linear = nn.Linear(512*block.expansion, num_classes)

    def _make_layer(self, block, planes, num_blocks, stride):
        strides = [stride] + [1]*(num_blocks-1)
        layers = []
        for stride in strides:
            layers.append(block(self.in_planes, planes, stride))
            self.in_planes = planes * block.expansion
        return nn.Sequential(*layers)

    def forward(self, x):
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = F.avg_pool2d(out, 4)
        out = out.view(out.size(0), -1)
        out = self.linear(out)
        return out
################################################################################
    #train loop
    def training_step(self, batch, batch_idx):
        x, y = batch
        preds = self(x)
        loss = F.cross_entropy(preds, y)
        acc = self.accuracy(preds, y)
        # perform logging
        self.log("train_loss", loss, on_step=True, on_epoch=True, prog_bar=True, logger=True)
        self.log("train_acc", acc, on_step=True, on_epoch=True, prog_bar=True, logger=True)
        return loss

    def validation_step(self, batch, batch_idx):
        x, y = batch
        preds = self(x)
        loss = F.cross_entropy(preds, y)
        acc = self.accuracy(preds, y)
        # perform logging
        self.log("val_loss", loss, on_epoch=True, prog_bar=False, logger=True)
        self.log("val_acc", acc, on_epoch=True, prog_bar=True, logger=True)
        return loss

    def test_step(self, batch, batch_idx):
        x, y = batch
        preds = self(x)
        loss = F.cross_entropy(preds, y)
        acc = self.accuracy(preds, y)
        # perform logging
        self.log("test_loss", loss, on_step=True, prog_bar=True, logger=True)
        self.log("test_acc", acc, on_step=True, prog_bar=True, logger=True)
        return loss

    def configure_optimizers(self):
        optimizer = optim.SGD(self.parameters(), lr=self.learning_rate, momentum=0.9)

        return {
        "optimizer": optimizer,
        "lr_scheduler": {
            "scheduler": torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer, patience=2),
            "monitor": "val_loss",
            "frequency": 1,
        },
    }
###################################
        


def ResNet18():
    return ResNet(BasicBlock, [2, 2, 2, 2])