app.py

import os
import numpy as np
import torch
from torch.autograd import Variable
from torchvision import transforms
import torch.nn.functional as F
from flask import Flask, request, jsonify, render_template, send_from_directory
from PIL import Image
import warnings
warnings.filterwarnings("ignore")

# Clone repository and setup (only run once)
if not os.path.exists("DIS"):
    os.system("git clone https://github.com/xuebinqin/DIS")
    os.system("mv DIS/IS-Net/* .")

# Project imports
from data_loader_cache import normalize, im_reader, im_preprocess 
from models import *

# Setup device
device = 'cuda' if torch.cuda.is_available() else 'cpu'

# Download official weights if not exists
if not os.path.exists("saved_models"):
    os.makedirs("saved_models", exist_ok=True)
    if not os.path.exists("saved_models/isnet.pth"):
        if os.path.exists("isnet.pth"):
            os.rename("isnet.pth", "saved_models/isnet.pth")

class GOSNormalize(object):
    def __init__(self, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]):
        self.mean = mean
        self.std = std

    def __call__(self, image):
        image = normalize(image, self.mean, self.std)
        return image

transform = transforms.Compose([GOSNormalize([0.5, 0.5, 0.5], [1.0, 1.0, 1.0])])

def load_image(im_path, hypar):
    im = im_reader(im_path)
    
    # Convert numpy array to PIL Image if needed
    if isinstance(im, np.ndarray):
        if im.ndim == 3 and im.shape[2] == 4:  # RGBA image
            im = Image.fromarray(im).convert('RGB')
        elif im.ndim == 3:  # RGB image
            im = Image.fromarray(im)
        elif im.ndim == 2:  # Grayscale image
            im = Image.fromarray(im).convert('RGB')
    
    # If it's already PIL Image, check mode
    elif hasattr(im, 'mode'):
        if im.mode == 'RGBA':
            im = im.convert('RGB')
    
    im, im_shp = im_preprocess(im, hypar["cache_size"])
    im = torch.divide(im, 255.0)
    shape = torch.from_numpy(np.array(im_shp))
    return transform(im).unsqueeze(0), shape.unsqueeze(0)

def build_model(hypar, device):
    net = hypar["model"]
    
    if hypar["model_digit"] == "half":
        net.half()
        for layer in net.modules():
            if isinstance(layer, nn.BatchNorm2d):
                layer.float()

    net.to(device)

    if hypar["restore_model"] != "":
        net.load_state_dict(torch.load(os.path.join(hypar["model_path"], hypar["restore_model"]), 
                                     map_location=device))
    net.eval()
    return net

def predict(net, inputs_val, shapes_val, hypar, device):
    net.eval()

    if hypar["model_digit"] == "full":
        inputs_val = inputs_val.type(torch.FloatTensor)
    else:
        inputs_val = inputs_val.type(torch.HalfTensor)

    inputs_val_v = Variable(inputs_val, requires_grad=False).to(device)
    ds_val = net(inputs_val_v)[0]

    pred_val = ds_val[0][0, :, :, :]

    pred_val = torch.squeeze(F.upsample(torch.unsqueeze(pred_val, 0), 
                           (shapes_val[0][0], shapes_val[0][1]), mode='bilinear'))

    ma = torch.max(pred_val)
    mi = torch.min(pred_val)
    pred_val = (pred_val - mi) / (ma - mi)

    if device == 'cuda': 
        torch.cuda.empty_cache()
    return (pred_val.detach().cpu().numpy() * 255).astype(np.uint8)

# Set Parameters
hypar = {
    "model_path": "./saved_models",
    "restore_model": "isnet.pth",
    "interm_sup": False,
    "model_digit": "full",
    "seed": 0,
    "cache_size": [1024, 1024],
    "input_size": [1024, 1024],
    "crop_size": [1024, 1024],
    "model": ISNetDIS()
}

# Build Model
net = build_model(hypar, device)

# Flask app
app = Flask(__name__)
app.config['UPLOAD_FOLDER'] = 'uploads'
app.config['RESULT_FOLDER'] = 'results'

os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
os.makedirs(app.config['RESULT_FOLDER'], exist_ok=True)

@app.route('/', methods=['GET'])
def index():
    return render_template('index.html')

@app.route('/api/remove_bg', methods=['POST'])
def remove_background():
    if 'image' not in request.files:
        return jsonify({'error': 'No image provided'}), 400
    
    file = request.files['image']
    if file.filename == '':
        return jsonify({'error': 'No image selected'}), 400
    
    # Save uploaded file
    upload_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
    file.save(upload_path)
    
    try:
        # Process image
        image_tensor, orig_size = load_image(upload_path, hypar) 
        mask = predict(net, image_tensor, orig_size, hypar, device)
        
        # Create results
        pil_mask = Image.fromarray(mask).convert('L')
        im_rgb = Image.open(upload_path).convert("RGB")
        im_rgba = im_rgb.copy()
        im_rgba.putalpha(pil_mask)
        
        # Save results
        result_rgba_path = os.path.join(app.config['RESULT_FOLDER'], f"rgba_{file.filename}")
        result_mask_path = os.path.join(app.config['RESULT_FOLDER'], f"mask_{file.filename}")
        
        im_rgba.save(result_rgba_path, format="PNG")
        pil_mask.save(result_mask_path, format="PNG")
        
        return jsonify({
            'rgba_image': f"/results/rgba_{file.filename}",
            'mask_image': f"/results/mask_{file.filename}",
            'original_filename': file.filename
        })
    except Exception as e:
        return jsonify({'error': str(e)}), 500

@app.route('/results/<filename>')
def serve_result(filename):
    return send_from_directory(app.config['RESULT_FOLDER'], filename)

@app.route('/uploads/<filename>')
def serve_upload(filename):
    return send_from_directory(app.config['UPLOAD_FOLDER'], filename)

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5000, debug=True)