Update app.py

app.py

@@ -1,5 +1,4 @@
 import cv2
-import gradio as gr
 import os
 from PIL import Image
 import numpy as np
@@ -7,147 +6,131 @@ import torch
 from torch.autograd import Variable
 from torchvision import transforms
 import torch.nn.functional as F
-import gdown
-import matplotlib.pyplot as plt
+from flask import Flask, request, jsonify, send_file
+import io
+from werkzeug.utils import secure_filename
 import warnings
 warnings.filterwarnings("ignore")
 
-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 *
-
-#Helpers
+# モデルと設定の初期化
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
-# Download official weights
-if not os.path.exists("saved_models"):
-    os.mkdir("saved_models")
-    os.system("mv isnet.pth saved_models/")
-    
 class GOSNormalize(object):
-    '''
-    Normalize the Image using torch.transforms
-    '''
     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)
+    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])])
+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)
     im, im_shp = im_preprocess(im, hypar["cache_size"])
-    im = torch.divide(im,255.0)
+    im = torch.divide(im, 255.0)
     shape = torch.from_numpy(np.array(im_shp))
-    return transform(im).unsqueeze(0), shape.unsqueeze(0) # make a batch of image, shape
+    return transform(im).unsqueeze(0), shape.unsqueeze(0)
 
-
-def build_model(hypar,device):
-    net = hypar["model"]#GOSNETINC(3,1)
-
-    # convert to half precision
+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(hypar["model_path"]+"/"+hypar["restore_model"], map_location=device))
         net.to(device)
     net.eval()  
     return net
 
-    
-def predict(net,  inputs_val, shapes_val, hypar, device):
-    '''
-    Given an Image, predict the mask
-    '''
+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) # wrap inputs in Variable
-   
-    ds_val = net(inputs_val_v)[0] # list of 6 results
-
-    pred_val = ds_val[0][0,:,:,:] # B x 1 x H x W    # we want the first one which is the most accurate prediction
+    inputs_val_v = Variable(inputs_val, requires_grad=False).to(device)
+    ds_val = net(inputs_val_v)[0]
+    pred_val = ds_val[0][0,:,:,:]
 
-    ## recover the prediction spatial size to the orignal image size
     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) # max = 1
+    pred_val = (pred_val-mi)/(ma-mi)
 
     if device == 'cuda': torch.cuda.empty_cache()
-    return (pred_val.detach().cpu().numpy()*255).astype(np.uint8) # it is the mask we need
-    
-# Set Parameters
-hypar = {} # paramters for inferencing
-
-
-hypar["model_path"] ="./saved_models" ## load trained weights from this path
-hypar["restore_model"] = "isnet.pth" ## name of the to-be-loaded weights
-hypar["interm_sup"] = False ## indicate if activate intermediate feature supervision
-
-##  choose floating point accuracy --
-hypar["model_digit"] = "full" ## indicates "half" or "full" accuracy of float number
-hypar["seed"] = 0
-
-hypar["cache_size"] = [1024, 1024] ## cached input spatial resolution, can be configured into different size
-
-## data augmentation parameters ---
-hypar["input_size"] = [1024, 1024] ## mdoel input spatial size, usually use the same value hypar["cache_size"], which means we don't further resize the images
-hypar["crop_size"] = [1024, 1024] ## random crop size from the input, it is usually set as smaller than hypar["cache_size"], e.g., [920,920] for data augmentation
-
-hypar["model"] = ISNetDIS()
-
- # Build Model
+    return (pred_val.detach().cpu().numpy()*255).astype(np.uint8)
+
+# パラメータ設定
+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()
+}
+
+# モデルをビルド
 net = build_model(hypar, device)
 
+app = Flask(__name__)
+app.config['UPLOAD_FOLDER'] = 'uploads'
+os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
 
-def inference(image):
-  image_path = image
-  
-  image_tensor, orig_size = load_image(image_path, hypar) 
-  mask = predict(net, image_tensor, orig_size, hypar, device)
-  
-  pil_mask = Image.fromarray(mask).convert('L')
-  im_rgb = Image.open(image).convert("RGB")
-  
-  im_rgba = im_rgb.copy()
-  im_rgba.putalpha(pil_mask)
-
-  return [im_rgba, pil_mask]
-
-
-title = "Highly Accurate Dichotomous Image Segmentation"
-description = "This is an unofficial demo for DIS, a model that can remove the background from a given image. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below.<br>GitHub: https://github.com/xuebinqin/DIS<br>Telegram bot: https://t.me/restoration_photo_bot<br>[![](https://img.shields.io/twitter/follow/DoEvent?label=@DoEvent&style=social)](https://twitter.com/DoEvent)"
-article = "<div><center><img src='https://visitor-badge.glitch.me/badge?page_id=max_skobeev_dis_cmp_public' alt='visitor badge'></center></div>"
-
-interface = gr.Interface(
-    fn=inference,
-    inputs=gr.Image(type='filepath'),
-    outputs=[gr.Image(type='filepath', format="png"), gr.Image(type='filepath', format="png")],
-    examples=[['robot.png'], ['ship.png']],
-    title=title,
-    description=description,
-    article=article,
-    flagging_mode="never",
-    cache_mode="lazy",
-    ).queue(api_open=True).launch(show_error=True, show_api=True)
+@app.route('/api/remove-background', methods=['POST'])
+def remove_background():
+    if 'file' not in request.files:
+        return jsonify({"error": "No file provided"}), 400
+    
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({"error": "No selected file"}), 400
+    
+    # ファイルを保存
+    filename = secure_filename(file.filename)
+    filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+    file.save(filepath)
+    
+    try:
+        # 画像処理
+        image_tensor, orig_size = load_image(filepath, hypar) 
+        mask = predict(net, image_tensor, orig_size, hypar, device)
+        
+        pil_mask = Image.fromarray(mask).convert('L')
+        im_rgb = Image.open(filepath).convert("RGB")
+        im_rgba = im_rgb.copy()
+        im_rgba.putalpha(pil_mask)
+        
+        # 結果をバイトデータとして返す
+        output_buffer = io.BytesIO()
+        im_rgba.save(output_buffer, format="PNG")
+        output_buffer.seek(0)
+        
+        # 一時ファイルを削除
+        os.remove(filepath)
+        
+        return send_file(
+            output_buffer,
+            mimetype='image/png',
+            as_attachment=True,
+            download_name='output.png'
+        )
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+@app.route('/api/health', methods=['GET'])
+def health_check():
+    return jsonify({"status": "healthy"}), 200
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000, debug=True)