import torch
import torchvision
from torchvision import datasets, models, transforms
import torch.nn as nn
import torch.nn.functional as F
import os
import clip
from utils import normalize

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


def get_prompt(cfg):
    model, preprocess = clip.load("ViT-B/32", device=device)
    prompt=cfg.prompt
    text=clip.tokenize(prompt).to(device)
    with torch.no_grad():
            prompt = model.encode_text(text)
    return prompt
# class GanAttack(nn.Module):
    
class GanAttack(nn.Module):
    def __init__(self, stylegan_generator, inverter,images_resize,prompt):
        super().__init__()

        self.generator = stylegan_generator
        self.generator.eval()
        self.inverter=inverter
        self.images_resize=images_resize
        self.prompt=prompt
        text_len=self.prompt.shape[0]
        self.mlp=nn.Sequential(
            nn.Linear(text_len+512, 4096),
                                 nn.ReLU(inplace=True),
                                 nn.Linear(4096, 512)
        )


    def forward(self, img,img_path):
        _, _, _, refine_images, latent_codes, _=self.inverter(img,self.images_resize,img_path)
        x=latent_codes
        batch_size=img.shape[0]
        prompt=self.prompt.repeat(batch_size).to(device)
        x_prompt=torch.cat([latent_codes,prompt],dim=1)
        x_prompt=self.mlp(x_prompt)
        x=x_prompt+x
        im,_=self.generator(x,input_is_latent=True, randomize_noise=False)


        return refine_images,im,x
    
class CLIPLoss(torch.nn.Module):
    def __init__(self):
        super(CLIPLoss, self).__init__()
        self.model, self.preprocess = clip.load("ViT-B/32", device="cuda")
        self.model.eval()
        self.face_pool = torch.nn.AdaptiveAvgPool2d((224, 224))
        # self.mean = torch.tensor([0.48145466, 0.4578275, 0.40821073], device="cuda").view(1,3,1,1)
        # self.std = torch.tensor([0.26862954, 0.26130258, 0.27577711], device="cuda").view(1,3,1,1)

    def forward(self, image, text):
        image=normalize(image)
        image = self.face_pool(image)
        similarity = 1 - self.model(image, text)[0]/ 100
        return similarity
    

class VggLoss(torch.nn.Module):
    def __init__(self):
        super(VggLoss, self).__init__()
        self.model=models.vgg11(pretrained=True)
        self.model.features=nn.Sequential()
        
        # self.mean = torch.tensor([0.48145466, 0.4578275, 0.40821073], device="cuda").view(1,3,1,1)
        # self.std = torch.tensor([0.26862954, 0.26130258, 0.27577711], device="cuda").view(1,3,1,1)

    def forward(self, image1, image2):
        # image=normalize(image)
        with torch.no_grad:
            feature1=self.model(image1)
            feature2=self.model(image2)
        feature1=torch.flatten(feature1)
        feature2=torch.flatten(feature2)
        similarity = F.cosine_similarity(feature1,feature2)
        return similarity