import streamlit as st
from fastai.vision import open_image, load_learner, show_image
import PIL.Image
from PIL import Image
from io import BytesIO
import requests
import torch.nn as nn
import os
import tempfile
import shutil

# Define the FeatureLoss class
class FeatureLoss(nn.Module):
    def __init__(self, m_feat, layer_ids, layer_wgts):
        super().__init__()
        self.m_feat = m_feat
        self.loss_features = [self.m_feat[i] for i in layer_ids]
        self.hooks = hook_outputs(self.loss_features, detach=False)
        self.wgts = layer_wgts
        self.metric_names = ['pixel',] + [f'feat_{i}' for i in range(len(layer_ids))] + [f'gram_{i}' for i in range(len(layer_ids))]

    def make_features(self, x, clone=False):
        self.m_feat(x)
        return [(o.clone() if clone else o) for o in self.hooks.stored]

    def forward(self, input, target):
        out_feat = self.make_features(target, clone=True)
        in_feat = self.make_features(input)
        self.feat_losses = [base_loss(input, target)]
        self.feat_losses += [base_loss(f_in, f_out) * w for f_in, f_out, w in zip(in_feat, out_feat, self.wgts)]
        self.feat_losses += [base_loss(gram_matrix(f_in), gram_matrix(f_out)) * w**2 * 5e3 for f_in, f_out, w in zip(in_feat, out_feat, self.wgts)]
        self.metrics = dict(zip(self.metric_names, self.feat_losses))
        return sum(self.feat_losses)

    def __del__(self): self.hooks.remove()

def add_margin(pil_img, top, right, bottom, left, color):
    width, height = pil_img.size
    new_width = width + right + left
    new_height = height + top + bottom
    result = Image.new(pil_img.mode, (new_width, new_height), color)
    result.paste(pil_img, (left, top))
    return result

def inference(image_path_or_url, learn):
    if image_path_or_url.startswith('http://') or image_path_or_url.startswith('https://'):
        response = requests.get(image_path_or_url)
        img = PIL.Image.open(BytesIO(response.content)).convert("RGB")
    else:
        img = PIL.Image.open(image_path_or_url).convert("RGB")

    im_new = add_margin(img, 250, 250, 250, 250, (255, 255, 255))
    im_new.save("test.jpg", quality=95)
    img = open_image("test.jpg")
    p, img_hr, b = learn.predict(img)
    return img_hr

# Streamlit application
st.title("Image Inference with Fastai")

# Download the model file from the Hugging Face repository
model_url = "https://huggingface.co/Hammad712/image2sketch/resolve/main/image2sketch.pkl"
model_file_path = 'image2sketch.pkl'

if not os.path.exists(model_file_path):
    with st.spinner('Downloading model...'):
        response = requests.get(model_url)
        with open(model_file_path, 'wb') as f:
            f.write(response.content)
    st.success('Model downloaded successfully!')

# Create a temporary directory for the model
with tempfile.TemporaryDirectory() as tmpdirname:
    shutil.move(model_file_path, os.path.join(tmpdirname, 'export.pkl'))
    learn = load_learner(tmpdirname)

# Input for image URL or path
image_path_or_url = st.text_input("Enter image path or URL", "")

# Run inference button
if st.button("Run Inference"):
    if image_path_or_url:
        with st.spinner('Processing...'):
            high_res_image = inference(image_path_or_url, learn)
            st.image(high_res_image, caption='High Resolution Image', use_column_width=True)
    else:
        st.error("Please enter a valid image path or URL.")