feat : upgrade clearify

app.py

@@ -1,5 +1,6 @@
-from fastapi import FastAPI, Request, Response, UploadFile, File
-from fastapi.responses import JSONResponse, StreamingResponse
+from fastapi import FastAPI, Request, Response
+from fastapi.responses import JSONResponse
+import requests
 
 import traceback
 import torch
@@ -9,13 +10,17 @@ from PIL import Image
 import io
 import numpy as np
 import os
+from datetime import datetime
 
 from models.fpn_inception import FPNInception  # 你自己的模型類別
 
+STATIC_DIR = "static"
+
 os.environ["TORCH_HOME"] = "./.cache"
 os.environ["HF_HOME"] = "./.cache"
 os.environ["TRANSFORMERS_CACHE"] = "./.cache"
 os.makedirs("./.cache", exist_ok=True)
+os.makedirs(STATIC_DIR, exist_ok=True)
 
 # =====================
 # 初始化模型
@@ -101,22 +106,49 @@ def greet_json(request: Request, response: Response):
     return JSONResponse(content={"message": "Hello World", "client": client_host})
 
 @app.post("/predict")
-async def predict(file: UploadFile = File(...)):
+async def predict( request: Request, response: Response ):
     try:
-        # 讀取上傳圖片
-        contents = await file.read()
-        img = Image.open(io.BytesIO(contents)).convert("RGB")
-
-        # 去模糊
+        # 1️⃣ 讀取 form-data
+        form = await request.form()
+        file_name = form.get("file_name")
+        file_format = form.get("file_format")
+        file_url = form.get("file_url")
+        file_width = int(form.get("file_width", 0))
+        file_height = int(form.get("file_height", 0))
+        file_created_at = form.get("file_created_at")
+
+        if not file_url:
+            return JSONResponse(
+                {"status": "error", "message": "file_url is required"},
+                status_code=400
+            )
+
+        # 2️⃣ 從 URL 下載圖片
+        resp = requests.get(file_url)
+        resp.raise_for_status()
+        img = Image.open(io.BytesIO(resp.content)).convert("RGB")
+
+        # 3️⃣ 去模糊
         result = deblur_image_tiled(G, img, device)
 
-        # 輸出為 bytes
-        img_byte_arr = io.BytesIO()
-        result.save(img_byte_arr, format="PNG")
-        img_byte_arr.seek(0)
-
-        # 直接回傳圖片
-        return StreamingResponse(img_byte_arr, media_type="image/png")
+        # 4️⃣ 產生檔名
+        base_name = f"{file_name}_{file_width}_{file_height}_{file_created_at}.jpg"
+        file_path = os.path.join(STATIC_DIR, base_name)
+
+        # 5️⃣ 儲存到 static
+        result.save(file_path, format="jpg")
+
+        # 6️⃣ 回傳前端可取用的 URL
+        file_url_return = str(request.base_url) + f"static/{base_name}"
+        return {
+            "status": "success", 
+            "file_url": file_url_return,
+            "file_name": base_name,
+            "file_format": "jpg",
+            "file_width": result.width,
+            "file_height": result.height,
+            "file_created_at": datetime.now().strftime("%Y%m%d%H%M%S")
+        }
 
     except Exception as e:
         import traceback

app_DeblurGan_PyTorch.py

@@ -27,13 +27,15 @@ print(f"🔹 Using device: {device}")
 
 # 模型 checkpoint 路徑
 checkpoint_dir = os.path.join(os.getcwd(), "model")
-ckpt_path = os.path.join(checkpoint_dir, "deblurgan_v2_latest.pth")
+ckpt_path = os.path.join(checkpoint_dir, "deblurgan_v2_latest_L1_vgg_D_jason_r20.pth")
 
 # 初始化模型
 G = FPNInception(norm_layer=nn.InstanceNorm2d).to(device)
 checkpoint = torch.load(ckpt_path, map_location=device)
 G.load_state_dict(checkpoint["G"], strict=False)
+num_epoch = checkpoint["epoch"] + 1
 G.eval()
+print("✅ num epoch", num_epoch)
 print("✅ Model loaded from", ckpt_path)
 
 
@@ -145,6 +147,11 @@ class ImageViewerApp:
         self.canvas_original.image = photo
 
         result_img = self.model.predict(image_path)
+        
+        saveimg_dir = os.path.join(os.getcwd(), "rimg")
+        #saveimg_path = os.path.join(saveimg_dir, "result_fullsize.png")
+        
+        #result_img.save(saveimg_path) 
         result_img.thumbnail((480, 420))
         photo_result = ImageTk.PhotoImage(result_img)
         self.canvas_result.create_image(0, 0, anchor="nw", image=photo_result)