import streamlit as st
import torch
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
import torchvision.transforms as transforms
from torchvision.datasets import CIFAR10
from torch.utils.data import DataLoader

# Define the ResNet model
class BasicBlock(nn.Module):
    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):
        identity = x
        out = F.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        out += self.shortcut(identity)
        out = F.relu(out)
        return out

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

        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

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

# Define a function to load CIFAR-10 dataset
def load_data():
    transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
    train_set = CIFAR10(root='./data', train=True, download=True, transform=transform)
    train_loader = DataLoader(train_set, batch_size=100, shuffle=True, num_workers=2)
    return train_loader

# Streamlit Interface
st.title('ResNet with Streamlit')
st.write("This is an example of integrating a ResNet model with Streamlit.")

# Load data button
if st.button('Load Data'):
    st.write("Loading CIFAR-10 data...")
    train_loader = load_data()
    st.write("Data loaded successfully!")

# Initialize and test the model
if st.button('Initialize and Test ResNet18'):
    net = ResNet18()
    sample_input = torch.randn(1, 3, 32, 32)
    output = net(sample_input)
    st.write("Output size: ", output.size())

# Train the model (for demonstration, we'll just do one epoch)
if st.button('Train ResNet18'):
    st.write("Training ResNet18 on CIFAR-10...")
    net = ResNet18()
    train_loader = load_data()
    criterion = nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(net.parameters(), lr=0.001)

    net.train()
    for epoch in range(1):  # Single epoch for demonstration
        running_loss = 0.0
        for i, data in enumerate(train_loader, 0):
            inputs, labels = data
            optimizer.zero_grad()
            outputs = net(inputs)
            loss = criterion(outputs, labels)
            loss.backward()
            optimizer.step()
            running_loss += loss.item()
            if i % 100 == 99:  # Print every 100 mini-batches
                st.write(f'Epoch [{epoch + 1}], Step [{i + 1}], Loss: {running_loss / 100:.4f}')
                running_loss = 0.0

    st.write("Training complete!")

# Plotting example (dummy plot for demonstration)
if st.button('Show Plot'):
    st.write("Displaying a sample plot...")
    fig, ax = plt.subplots()
    ax.plot([1, 2, 3, 4], [1, 4, 2, 3])
    st.pyplot(fig)

# To run the Streamlit app, use the command below in your terminal:
# streamlit run your_script_name.py