#!/usr/bin/env python
# coding: utf-8

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor
import matplotlib.pyplot as plt

training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

class_names = [
    "Haut de t-shirt",
    "Pantalon",
    "Pull",
    "Robe",
    "Manteau",
    "Sandale",
    "Chemise",
    "Basket",
    "Sac",
    "Bottine"
]

def plot_images(images, labels, predictions=None):
    plt.figure(figsize=(10, 10))
    for i in range(min(25, len(images))):
        plt.subplot(5, 5, i + 1)
        plt.xticks([])
        plt.yticks([])
        plt.grid(False)
        plt.imshow(images[i].numpy().squeeze(), cmap=plt.cm.binary)
        plt.xlabel(class_names[labels[i]])
        
        if predictions is not None:
            plt.title(class_names[predictions[i]])
            
batch_size = 64
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)

images, labels = next(iter(train_dataloader))
plot_images(images, labels)
plt.show()

device = "cuda" if torch.cuda.is_available() else "cpu"

################################ Notre réseau de neurone est ici ################################ 
class NeuralNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 256),
            nn.Tanh(),#sig c
            nn.Linear(256, 1028),
            nn.Sigmoid(),
            nn.Linear(1028, 10),
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits
################################################################################################
    
model = NeuralNetwork().to(device)

loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)


def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        pred = model(X)
        loss = loss_fn(pred, y)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"perte: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= num_batches
    correct /= size
    print(f"Test Erreur: \n Exactitude: {(100*correct):>0.1f}%, Perte: {test_loss:>8f} \n")

epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model, loss_fn)
print("Done!")


model.eval()
x, y = test_data[0][0], test_data[0][1]
with torch.no_grad():
    pred = model(x)
    predicted, actual = classes[pred[0].argmax(0)], classes[y]
    print(f'Prediction: "{predicted}", Vraie Valeure: "{actual}"')