import torch
import torch.nn.functional as F
import torchvision.datasets as datasets
import torchvision.transforms as transforms
from torch import nn, optim
from torch.utils.data import DataLoader
from tqdm import tqdm
import pytorch_lightning as pl
import torchmetrics
from torchmetrics import Metric
import torchvision

class BasicBlock(nn.Module):

    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()

    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 CustomBlock(nn.Module):
    def __init__(self, in_channels, out_channels):
        super(CustomBlock, self).__init__()

        self.inner_layer = nn.Sequential(
            nn.Conv2d(
                in_channels=in_channels,
                out_channels=out_channels,
                kernel_size=3,
                stride=1,
                padding=1,
                bias=False,
            ),
            nn.MaxPool2d(kernel_size=2),
            nn.BatchNorm2d(out_channels),
            nn.ReLU(),
        )

        self.res_block = BasicBlock(out_channels, out_channels)

    def forward(self, x):
        x = self.inner_layer(x)
        r = self.res_block(x)

        out = x + r

        return out

class CustomResNet(pl.LightningModule):
    def __init__(self, input_size, learning_rate, num_classes=10):
        super().__init__()


        self.lr = learning_rate

        self.loss_fn = nn.CrossEntropyLoss()
        self.accuracy = torchmetrics.Accuracy(
            task="multiclass", num_classes=num_classes
        )
        self.accuracy1 = torchmetrics.Accuracy(
            task="multiclass", num_classes=num_classes
        )
        self.f1_score = torchmetrics.F1Score(task="multiclass", num_classes=num_classes)

        self.prep_layer = nn.Sequential(
            nn.Conv2d(
                in_channels=3,
                out_channels=64,
                kernel_size=3,
                stride=1,
                padding=1,
                bias=False,
            ),
            nn.BatchNorm2d(64),
            nn.ReLU(),
        )

        self.layer_1 = CustomBlock(in_channels=64, out_channels=128)

        self.layer_2 = nn.Sequential(
            nn.Conv2d(
                in_channels=128,
                out_channels=256,
                kernel_size=3,
                stride=1,
                padding=1,
                bias=False,
            ),
            nn.MaxPool2d(kernel_size=2),
            nn.BatchNorm2d(256),
            nn.ReLU(),
        )

        self.layer_3 = CustomBlock(in_channels=256, out_channels=512)

        self.max_pool = nn.Sequential(nn.MaxPool2d(kernel_size=4))

        self.fc = nn.Linear(512, num_classes)



    def forward(self, x):
        x = self.prep_layer(x)
        x = self.layer_1(x)
        x = self.layer_2(x)
        x = self.layer_3(x)
        x = self.max_pool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

    def training_step(self, batch, batch_idx):
        x, y = batch
        loss, scores, y = self._common_step(batch, batch_idx)
        accuracy = self.accuracy(scores, y)
        f1_score = self.f1_score(scores, y)
        self.log_dict(
            {
                "train_loss": loss,
                "train_accuracy": accuracy,
                "train_f1_score": f1_score,
            },
            on_step=False,
            on_epoch=True,
            prog_bar=True,
        )
        
        return {"loss": loss, "scores": scores, "y": y}

    def validation_step(self, batch, batch_idx):
        loss, scores, y = self._common_step(batch, batch_idx)
        accuracy = self.accuracy1(scores, y)
        #self.log("val_loss", loss)
        self.log_dict(
            {
                "val_loss": loss,
                "val_accuracy": accuracy,
                #"train_f1_score": f1_score,
            },
            on_step=False,
            on_epoch=True,
            prog_bar=True,
        )

        return {"loss": loss, "scores": scores, "y": y}

    def test_step(self, batch, batch_idx):
        loss, scores, y = self._common_step(batch, batch_idx)
        self.log("test_loss", loss)
        return loss

    def _common_step(self, batch, batch_idx):
        x, y = batch
        #x = x.reshape(x.size(0), -1)
        scores = self.forward(x)
        loss = self.loss_fn(scores, y)
        return loss, scores, y

    def predict_step(self, batch, batch_idx):
        x, y = batch
        #x = x.reshape(x.size(0), -1)
        scores = self.forward(x)
        preds = torch.argmax(scores, dim=1)
        return preds

    def configure_optimizers(self):
        return optim.Adam(self.parameters(), lr=self.lr)