import torch
import torch.nn as nn
# from diffusers import AutoencoderKL as vae
# import copy
from clip.model import Transformer, LayerNorm
# import clip
# import torchvision.transforms as transforms

import os
import certifi
# import urllib
os.environ["REQUESTS_CA_BUNDLE"] = certifi.where()
os.environ["SSL_CERT_FILE"] = certifi.where()
# result = urllib.request.urlopen('https://www.example.com')

class VisionTransformer(nn.Module):
    def __init__(self, input_resolution: int, patch_size: int, width: int, layers: int, heads: int, output_dim: int):
        super().__init__()
        self.input_resolution = input_resolution
        self.output_dim = output_dim
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=width, kernel_size=patch_size, stride=patch_size, bias=False)

        scale = width ** -0.5
        self.class_embedding = nn.Parameter(scale * torch.randn(width))
        self.positional_embedding = nn.Parameter(scale * torch.randn((input_resolution // patch_size) ** 2 + 1, width))
        self.ln_pre = LayerNorm(width)

        self.transformer = Transformer(width, layers, heads)

        self.ln_post = LayerNorm(width)
        self.proj = nn.Parameter(scale * torch.randn(width, output_dim))

    def forward(self, x: torch.Tensor):
        x = self.conv1(x)  # shape = [*, width, grid, grid]
        x = x.reshape(x.shape[0], x.shape[1], -1)  # shape = [*, width, grid ** 2]
        x = x.permute(0, 2, 1)  # shape = [*, grid ** 2, width]
        x = torch.cat([self.class_embedding.to(x.dtype) + torch.zeros(x.shape[0], 1, x.shape[-1], dtype=x.dtype, device=x.device), x], dim=1)  # shape = [*, grid ** 2 + 1, width]
        x = x + self.positional_embedding.to(x.dtype)
        x = self.ln_pre(x)

        x = x.permute(1, 0, 2)  # NLD -> LND
        x = self.transformer(x)
        x = x.permute(1, 0, 2)  # LND -> NLD

        # x = self.ln_post(x[:, 0, :])
        #
        # if self.proj is not None:
        #     x = x @ self.proj

        x = self.ln_post(x)

        return x