import os
import sys

import matplotlib.pyplot as plt
from pandas.core.common import flatten

import torch
from torch import nn
from torch import optim
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader
from torchvision import datasets, transforms, models
import albumentations as A
from albumentations.pytorch import ToTensorV2

from tqdm import tqdm
import random

sys.path.append('/workspace')
import dataset



train_transforms = A.Compose(
    [
        A.SmallestMaxSize(max_size=350),
        A.ShiftScaleRotate(shift_limit=0.05, scale_limit=0.05, rotate_limit=360, p=0.5),
        A.RandomCrop(height=256, width=256),
        A.RGBShift(r_shift_limit=15, g_shift_limit=15, b_shift_limit=15, p=0.5),
        A.RandomBrightnessContrast(p=0.5),
        A.MultiplicativeNoise(multiplier=[0.5,2], per_channel=True, p=0.2),
        A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
        A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit=0.2, val_shift_limit=0.2, p=0.5),
        A.RandomBrightnessContrast(brightness_limit=(-0.1,0.1), contrast_limit=(-0.1, 0.1), p=0.5),
        ToTensorV2(),
    ]
)

test_transforms = A.Compose(
    [
        A.SmallestMaxSize(max_size=350),
        A.CenterCrop(height=256, width=256),
        A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
        ToTensorV2(),
    ]
)

dataset_CV = dataset.MotorbikeDataset_CV(
    root='/workspace/data/',
    train_transforms=train_transforms,
    val_transforms=test_transforms
    )

train_dataset, val_dataset = dataset_CV.get_split()

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True, drop_last=True)
val_loader = DataLoader(val_dataset,batch_size=64, shuffle=False)

device = torch.device("cuda:3") if torch.cuda.is_available() else torch.device("cpu")

model = models.resnet50(pretrained=True)
model.fc = nn.Sequential(
    nn.Dropout(0.5),
    nn.Linear(model.fc.in_features, 2)
)

for n, p in model.named_parameters():
    if 'fc' in n:
        p.requires_grad = True
    else:
        p.requires_grad = False

model.to(device)

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.5)
best_acc = 0.0

for epoch in range(10):
    model.train()
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        inputs, labels = data[0].to(device), data[1].to(device)
        
        optimizer.zero_grad()
        
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    scheduler.step()
    
    print(f'[{epoch + 1}, {i + 1:5d}] loss: {running_loss / 2000:.3f}')
    # print("TRAIN acc = {}".format(acc))
    running_loss = 0.0
    
    with torch.no_grad():
        model.eval()
        running_loss = 0.0
        correct =0
        for i, data in enumerate(val_loader, 0):
            inputs, labels = data[0].to(device), data[1].to(device)
            outputs = model(inputs)
            _, preds = outputs.max(1)
            loss = criterion(outputs, labels)
            running_loss += loss.item()
            labels_one_hot = F.one_hot(labels, 2)
            outputs_one_hot = F.one_hot(preds, 2)
            correct = correct + (labels_one_hot + outputs_one_hot == 2).sum().to(torch.float)
        
        acc = 100 * correct / len(val_dataset)
        print(f'VAL: [{epoch + 1}, {i + 1:5d}] loss: {running_loss / len(val_loader):.3f}')
        print("VAL acc = {:.2f}".format(acc))
        if best_acc < acc:
            torch.save(model.state_dict(), './result/best_model.pth')