"""
Finetuning Torchvision Models

"""

from __future__ import print_function 
from __future__ import division
import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy
import argparse
import pretrainedmodels.models.resnext as resnext

print("PyTorch Version: ",torch.__version__)
print("Torchvision Version: ",torchvision.__version__)


# Top level data directory. Here we assume the format of the directory conforms 
#  to the ImageFolder structure
#data_dir = "./data/hymenoptera_data"
data_dir = "/media/dell/dell/data/13/"
# Models to choose from [resnet, alexnet, vgg, squeezenet, densenet, inception]
model_name = "resnext"

# Number of classes in the dataset
num_classes = 171

# Batch size for training (change depending on how much memory you have)
batch_size = 16

# Number of epochs to train for 
num_epochs = 1000

# Flag for feature extracting. When False, we finetune the whole model, 
#  when True we only update the reshaped layer params
feature_extract = False

# 参数设置,使得我们能够手动输入命令行参数，就是让风格变得和Linux命令行差不多
parser = argparse.ArgumentParser(description='PyTorch seresnet')
parser.add_argument('--outf', default='/home/dell/Desktop/zhou/train7', help='folder to output images and model checkpoints') #输出结果保存路径
parser.add_argument('--net', default='/home/dell/Desktop/zhou/train7/resnext.pth', help="path to net (to continue training)") #恢复训练时的模型路径
args = parser.parse_args()


def train_model(model, dataloaders, criterion, optimizer, num_epochs=25,is_inception=False):
#def train_model(model, dataloaders, criterion, optimizer, num_epochs=25,scheduler, is_inception=False):
  since = time.time()

  val_acc_history = []
  
  best_model_wts = copy.deepcopy(model.state_dict())
  best_acc = 0.0
  print("Start Training, resnext!") # 定义遍历数据集的次数
  with open("/home/dell/Desktop/zhou/train7/acc.txt", "w") as f1:
    with open("/home/dell/Desktop/zhou/train7/log.txt", "w")as f2:
      for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch+1, num_epochs))
        print('*' * 10)
        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
          if phase == 'train':
            #scheduler.step()
            model.train() # Set model to training mode
          else:
            model.eval()  # Set model to evaluate mode
    
          running_loss = 0.0
          running_corrects = 0
    
          # Iterate over data.
          for inputs, labels in dataloaders[phase]:
            inputs = inputs.to(device)
            labels = labels.to(device)
    
            # zero the parameter gradients
            optimizer.zero_grad()
    
            # forward
            # track history if only in train
            with torch.set_grad_enabled(phase == 'train'):
              # Get model outputs and calculate loss
              # Special case for inception because in training it has an auxiliary output. In train
              #  mode we calculate the loss by summing the final output and the auxiliary output
              #  but in testing we only consider the final output.
              if is_inception and phase == 'train':
                # From https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
                outputs, aux_outputs = model(inputs)
                loss1 = criterion(outputs, labels)
                loss2 = criterion(aux_outputs, labels)
                loss = loss1 + 0.4*loss2
              else:
                outputs = model(inputs)
                loss = criterion(outputs, labels)
    
              _, preds = torch.max(outputs, 1)
    
              # backward + optimize only if in training phase
              if phase == 'train':
                loss.backward()
                optimizer.step()
    
            # statistics
            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)
          epoch_loss = running_loss / len(dataloaders[phase].dataset)
          epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
    
          print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
          f2.write('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
          f2.write('\n')
          f2.flush()           
          # deep copy the model
          if phase == 'val':
            if (epoch+1)%5==0:
              #print('Saving model......')
              torch.save(model.state_dict(), '%s/inception_%03d.pth' % (args.outf, epoch + 1))
            f1.write("EPOCH=%03d,Accuracy= %.3f%%" % (epoch + 1, 100*epoch_acc))
            f1.write('\n')
            f1.flush()
          if phase == 'val' and epoch_acc > best_acc:
            f3 = open("/home/dell/Desktop/zhou/train7/best_acc.txt", "w")
            f3.write("EPOCH=%d,best_acc= %.3f%%" % (epoch + 1,100*epoch_acc))
            f3.close()
            best_acc = epoch_acc
            best_model_wts = copy.deepcopy(model.state_dict())
          if phase == 'val':
            val_acc_history.append(epoch_acc)

  time_elapsed = time.time() - since
  print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
  print('Best val Acc: {:4f}'.format(best_acc))
  # load best model weights
  model.load_state_dict(best_model_wts)
  return model, val_acc_history


def set_parameter_requires_grad(model, feature_extracting):
  if feature_extracting:
    for param in model.parameters():
      param.requires_grad = False



def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):
  # Initialize these variables which will be set in this if statement. Each of these
  #  variables is model specific.
  model_ft = None
  input_size = 0

  if model_name == "resnet":
    """ Resnet18
    """
    model_ft = models.resnet18(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    num_ftrs = model_ft.fc.in_features
    model_ft.fc = nn.Linear(num_ftrs, num_classes)
    input_size = 224

  elif model_name == "alexnet":
    """ Alexnet
    """
    model_ft = models.alexnet(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    num_ftrs = model_ft.classifier[6].in_features
    model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
    input_size = 224

  elif model_name == "vgg":
    """ VGG11_bn
    """
    model_ft = models.vgg11_bn(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    num_ftrs = model_ft.classifier[6].in_features
    model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
    input_size = 224

  elif model_name == "squeezenet":
    """ Squeezenet
    """
    model_ft = models.squeezenet1_0(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))
    model_ft.num_classes = num_classes
    input_size = 224

  elif model_name == "densenet":
    """ Densenet
    """
    model_ft = models.densenet121(pretrained=use_pretrained)
    set_parameter_requires_grad(model_ft, feature_extract)
    num_ftrs = model_ft.classifier.in_features
    model_ft.classifier = nn.Linear(num_ftrs, num_classes) 
    input_size = 224

  elif model_name == "resnext":
    """ resnext
    Be careful, expects (3,224,224) sized images 
    """
    model_ft = resnext.resnext101_64x4d(num_classes=1000, pretrained='imagenet')
    set_parameter_requires_grad(model_ft, feature_extract)
    model_ft.last_linear = nn.Linear(2048, num_classes)   
    #pre='/home/dell/Desktop/zhou/train6/inception_009.pth'
    #model_ft.load_state_dict(torch.load(pre))
    input_size = 224

  else:
    print("Invalid model name, exiting...")
    exit()
  
  return model_ft, input_size

# Initialize the model for this run
model_ft, input_size = initialize_model(model_name, num_classes, feature_extract, use_pretrained=True)

# Print the model we just instantiated
#print(model_ft) 



data_transforms = {
  'train': transforms.Compose([
    transforms.RandomResizedCrop(input_size),
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
  ]),
  'val': transforms.Compose([
    transforms.Resize(input_size),
    transforms.CenterCrop(input_size),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
  ]),
}

print("Initializing Datasets and Dataloaders...")


# Create training and validation datasets
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}
# Create training and validation dataloaders
dataloaders_dict = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True, num_workers=4) for x in ['train', 'val']}

# Detect if we have a GPU available
device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")

#we='/home/dell/Desktop/dj/inception_050.pth'
#model_ft.load_state_dict(torch.load(we))#diaoyong
# Send the model to GPU
model_ft = model_ft.to(device)

params_to_update = model_ft.parameters()
print("Params to learn:")
if feature_extract:
  params_to_update = []
  for name,param in model_ft.named_parameters():
    if param.requires_grad == True:
      params_to_update.append(param)
      print("\t",name)
else:
  for name,param in model_ft.named_parameters():
    if param.requires_grad == True:
      print("\t",name)

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(params_to_update, lr=0.01, momentum=0.9)
# Decay LR by a factor of 0.1 every 7 epochs
#exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=30, gamma=0.95)

# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
print(model_ft)
# Train and evaluate
model_ft, hist = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=False)