Update app.py

app.py

@@ -1,4 +1,3 @@
-from flask import Flask, request, jsonify, render_template
 import cv2
 import os
 from PIL import Image
@@ -7,18 +6,32 @@ import torch
 from torch.autograd import Variable
 from torchvision import transforms
 import torch.nn.functional as F
-import uuid
-
-import gdown
-import matplotlib.pyplot as plt
+from flask import Flask, request, jsonify, render_template, send_from_directory
 import warnings
+warnings.filterwarnings("ignore")
 
-app = Flask(__name__)
+# 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 *
 
-# モデル設定と初期化コード
+# 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.mkdir("saved_models")
+    if not os.path.exists("saved_models/isnet.pth"):
+        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
@@ -34,16 +47,20 @@ def load_image(im_path, hypar):
     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)
+    return transform(im).unsqueeze(0), shape.unsqueeze(0) # make a batch of image, shape
 
 def build_model(hypar,device):
-    net = hypar["model"]
+    net = hypar["model"]#GOSNETINC(3,1)
+
+    # convert to half precision
     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)
@@ -51,46 +68,60 @@ def build_model(hypar,device):
     return net
 
 def predict(net, inputs_val, shapes_val, hypar, device):
+    '''
+    Given an Image, predict the mask
+    '''
     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,:,:,:]
+
+    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
+
+    ## 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)
+    pred_val = (pred_val-mi)/(ma-mi) # max = 1
+
     if device == 'cuda': torch.cuda.empty_cache()
-    return (pred_val.detach().cpu().numpy()*255).astype(np.uint8)
-
-# モデル初期化
-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()
-}
+    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
+hypar["model_digit"] = "full" ## indicates "half" or "full" accuracy of float number
+hypar["seed"] = 0
+hypar["cache_size"] = [1024, 1024] ## cached input spatial resolution
+hypar["input_size"] = [1024, 1024] ## model input spatial size
+hypar["crop_size"] = [1024, 1024] ## random crop size from the input
+hypar["model"] = ISNetDIS()
 
+# Build Model
 net = build_model(hypar, device)
 
-# 結果を保存するディレクトリを作成
-os.makedirs('static/results', exist_ok=True)
+# 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('/')
+@app.route('/', methods=['GET'])
 def index():
     return render_template('index.html')
 
 @app.route('/api/remove_bg', methods=['POST'])
-def remove_bg():
+def remove_background():
     if 'image' not in request.files:
         return jsonify({'error': 'No image provided'}), 400
     
@@ -98,40 +129,42 @@ def remove_bg():
     if file.filename == '':
         return jsonify({'error': 'No image selected'}), 400
     
-    # 一時ファイルとして保存
-    temp_path = f"static/temp_{uuid.uuid4().hex}.png"
-    file.save(temp_path)
+    # Save uploaded file
+    upload_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
+    file.save(upload_path)
     
     try:
-        # 画像処理
-        image_tensor, orig_size = load_image(temp_path, hypar) 
+        # 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(temp_path).convert("RGB")
-        
-        # 結果を保存
-        result_id = uuid.uuid4().hex
-        rgba_path = f"static/results/{result_id}_rgba.png"
-        mask_path = f"static/results/{result_id}_mask.png"
-        
+        im_rgb = Image.open(upload_path).convert("RGB")
         im_rgba = im_rgb.copy()
         im_rgba.putalpha(pil_mask)
-        im_rgba.save(rgba_path)
-        pil_mask.save(mask_path)
         
-        # 一時ファイルを削除
-        os.remove(temp_path)
+        # 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_url': f"/{rgba_path}",
-            'mask_url': f"/{mask_path}"
+            'rgba_image': f"/results/rgba_{file.filename}",
+            'mask_image': f"/results/mask_{file.filename}"
         })
     except Exception as e:
-        # エラーが発生したら一時ファイルを削除
-        if os.path.exists(temp_path):
-            os.remove(temp_path)
         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(debug=True)
+    app.run(host='0.0.0.0', port=5000, debug=True)