import numpy as np
import matplotlib.pyplot as plt
import os
import torch
import torch.nn as nn
import torchvision
from torchvision import models,transforms,datasets
import time
import json
# 判断是否存在GPU设备
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print('Using gpu: %s ' % torch.cuda.is_available())
#处理数据
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
vgg_format = transforms.Compose([
                 transforms.CenterCrop(224),
                 transforms.ToTensor(),
                 normalize,
               ])
 
data_dir = "/content/cat_dog"
 
dsets = {x: datasets.ImageFolder(os.path.join(data_dir, x), vgg_format)
           for x in ['train', 'val']}
   
dset_sizes = {x: len(dsets[x]) for x in ['train', 'val']}
dset_classes = dsets['train'].classes

#修改batch_size
loader_train = torch.utils.data.DataLoader(dsets['train'], batch_size=128, shuffle=True, num_workers=6)
loader_valid = torch.utils.data.DataLoader(dsets['val'], batch_size=5, shuffle=False, num_workers=6)
#加载vgg16模型
!wget https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json
#使用vgg16需要
model_vgg = models.vgg16(pretrained=True)

print(model_vgg)
 
model_vgg_new = model_vgg;
 
#冻结VGG16中的参数，不进行梯度下降
for param in model_vgg_new.parameters():
    param.requires_grad = False
#修改模型后两层
model_vgg_new.classifier._modules['6'] = nn.Linear(4096, 2)
model_vgg_new.classifier._modules['7'] = torch.nn.LogSoftmax(dim = 1)
model_vgg_new = model_vgg_new.to(device)

print(model_vgg_new.classifier)

'''
第一步：创建损失函数和优化器

损失函数 NLLLoss() 的 输入 是一个对数概率向量和一个目标标签.
它不会为我们计算对数概率，适合最后一层是log_softmax()的网络.
'''
criterion = nn.NLLLoss()

# 学习率
lr = 0.001

#修改为Adam优化器
optimizer_vgg = torch.optim.Adam(model_vgg_new.classifier[6].parameters(), lr=lr)

'''
第二步：训练模型
'''

def train_model(model,dataloader,size,epochs=1,optimizer=None):
    model.train()
    max_acc = 0
    for epoch in range(epochs):
        running_loss = 0.0
        running_corrects = 0
        count = 0
        for inputs,classes in dataloader:
            inputs = inputs.to(device)
            classes = classes.to(device)
            outputs = model(inputs)
            loss = criterion(outputs,classes)           
            optimizer = optimizer
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            _,preds = torch.max(outputs.data,1)
            # statistics
            running_loss += loss.data.item()
            running_corrects += torch.sum(preds == classes.data)
            count += len(inputs)
            #print('Training: No. ', count, ' process ... total: ', size)
        epoch_loss = running_loss / size
        epoch_acc = running_corrects.data.item() / size

        print('epoch: {:} Loss: {:.4f} Acc: {:.4f}\n'.format(epoch,epoch_loss, epoch_acc))
        if epoch_acc > max_acc:
          max_acc = epoch_acc
          path = './sample_data' + str(epoch+1) + '' + str(epoch_acc) + '' + '.pth'
          torch.save(model, path)
          print("save: ", path,"\n")

# 模型训练,修改训练次数10次
train_model(model_vgg_new, loader_train, size=dset_sizes['train'], epochs=10,
            optimizer=optimizer_vgg)

# 第三步：测试模型
def test_model(model,dataloader,size):
    model.eval()
    predictions = np.zeros(size)
    all_classes = np.zeros(size)
    all_proba = np.zeros((size,2))
    i = 0
    running_loss = 0.0
    running_corrects = 0
    for inputs,classes in dataloader:
        inputs = inputs.to(device)
        classes = classes.to(device)
        outputs = model(inputs)
        loss = criterion(outputs,classes)           
        _,preds = torch.max(outputs.data,1)
        # statistics
        running_loss += loss.data.item()
        running_corrects += torch.sum(preds == classes.data)
        predictions[i:i+len(classes)] = preds.to('cpu').numpy()
        all_classes[i:i+len(classes)] = classes.to('cpu').numpy()
        all_proba[i:i+len(classes),:] = outputs.data.to('cpu').numpy()
        i += len(classes)
        print('Testing: No. ', i, ' process ... total: ', size)        
    epoch_loss = running_loss / size
    epoch_acc = running_corrects.data.item() / size
    print('Loss: {:.4f} Acc: {:.4f}'.format(
                     epoch_loss, epoch_acc))
    return predictions, all_proba, all_classes

# 模型测试
predictions, all_proba, all_classes = test_model(model_vgg_new,loader_valid,size=dset_sizes['val'])

import torch
import numpy as np
from torchvision import transforms,datasets
from tqdm import tqdm
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") 
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
vgg_format = transforms.Compose([
                transforms.CenterCrop(224),
                transforms.ToTensor(),
                normalize,
            ])

dsets_mine = datasets.ImageFolder(r"/content/cat_dog", vgg_format)
loader_test = torch.utils.data.DataLoader(dsets_mine, batch_size=1, shuffle=False, num_workers=0)
model_vgg_new = torch.load(r'/content/sample_data100.98115.pth')
model_vgg_new = model_vgg_new.to(device)
dic = {}
def test(model,dataloader,size):
    model.eval()
    predictions = np.zeros(size)
    cnt = 0
    for inputs,_ in tqdm(dataloader):
        inputs = inputs.to(device)
        outputs = model(inputs)
        _,preds = torch.max(outputs.data,1)    
        #这里是切割路径，因为dset中的数据不是按1-2000顺序排列的
        key = dsets_mine.imgs[cnt][0].split("\\")[-1].split('.')[0]
        dic[key] = preds[0]
        cnt = cnt +1
test(model_vgg_new,loader_test,size=2000)
with open("result.csv",'a+') as f:
    for key in range(2000):
        f.write("{},{}\n".format(key,dic["/content/cat_dog/test/"+str(key)]))