Update app.py

app.py

@@ -120,204 +120,6 @@ def load_img_1_(nparr, gray: bool = False):
     return np_img, alpha_channel
     
 model = None
-def model_process_pil(input):
-    global model
-    
-    # input = request.files
-    # RGB
-    # origin_image_bytes = input["image"].read()
-    image_pil = input['image']
-    mask_pil = input['mask']
-        
-    image = np.array(image_pil)
-    mask = np.array(mask_pil.convert("L"))
-    # print(f'image_pil_ = {type(image_pil)}')
-    # print(f'mask_pil_ = {type(mask_pil)}') 
-    # mask_pil.save(f'./mask_pil.png')         
-        
-    #image, alpha_channel = load_img(image)
-    # Origin image shape: (512, 512, 3)
-    
-    alpha_channel = (np.ones((image.shape[0],image.shape[1]))*255).astype(np.uint8)
-    original_shape = image.shape
-    interpolation = cv2.INTER_CUBIC    
-    
-    # form = request.form
-    print(f'liuyz_3_here_', original_shape, alpha_channel, image.dtype, mask.dtype)
-
-    size_limit = "Original" # image.shape[1] # : Union[int, str] = form.get("sizeLimit", "1080")
-    if size_limit == "Original":
-        size_limit = max(image.shape)
-    else:
-        size_limit = int(size_limit)
-
-    config = Config(
-        ldm_steps=25,
-        ldm_sampler='plms',
-        zits_wireframe=True,
-        hd_strategy='Original',
-        hd_strategy_crop_margin=196,
-        hd_strategy_crop_trigger_size=1280,
-        hd_strategy_resize_limit=2048,
-        prompt='',
-        use_croper=False,
-        croper_x=0,
-        croper_y=0,
-        croper_height=512,
-        croper_width=512,
-        sd_mask_blur=5,
-        sd_strength=0.75,
-        sd_steps=50,
-        sd_guidance_scale=7.5,
-        sd_sampler='ddim',
-        sd_seed=42,
-        cv2_flag='INPAINT_NS',
-        cv2_radius=5,
-    )
-   
-    # print(f'config = {config}')
-    
-    print(f'config/alpha_channel/size_limit = {config} / {alpha_channel} / {size_limit}')
-    if config.sd_seed == -1:
-        config.sd_seed = random.randint(1, 999999999)
-    
-    # logger.info(f"Origin image shape: {original_shape}")
-    print(f"Origin image shape: {original_shape} / {image[250][250]}")
-    image = resize_max_size(image, size_limit=size_limit, interpolation=interpolation)
-    # logger.info(f"Resized image shape: {image.shape}")
-    print(f"Resized image shape: {image.shape} / {image[250][250]} / {image.dtype}")
-    
-    # mask, _ = load_img(mask, gray=True)
-    #mask = np.array(mask_pil)
-    mask = resize_max_size(mask, size_limit=size_limit, interpolation=interpolation)
-    print(f"mask image shape: {mask.shape} / {type(mask)} / {mask[250][250]} / {mask.dtype}")
-
-    if model is None:
-        return None
-        
-    start = time.time()
-    res_np_img = model(image, mask, config)
-    logger.info(f"process time: {(time.time() - start) * 1000}ms, {res_np_img.shape}")
-    print(f"process time_1_: {(time.time() - start) * 1000}ms, {alpha_channel.shape}, {res_np_img.shape} / {res_np_img[250][250]} / {res_np_img.dtype}")
-
-    torch.cuda.empty_cache()
-
-    if alpha_channel is not None:
-        print(f"liuyz_here_10_: {alpha_channel.shape} / {alpha_channel.dtype} / {res_np_img.dtype}") 
-        if alpha_channel.shape[:2] != res_np_img.shape[:2]:
-            print(f"liuyz_here_20_: {alpha_channel.shape} / {res_np_img.shape}")
-            alpha_channel = cv2.resize(
-                alpha_channel, dsize=(res_np_img.shape[1], res_np_img.shape[0])
-            )
-        print(f"liuyz_here_30_: {alpha_channel.shape} / {res_np_img.shape} / {alpha_channel.dtype} / {res_np_img.dtype}")
-        res_np_img = np.concatenate(
-            (res_np_img, alpha_channel[:, :, np.newaxis]), axis=-1
-        )
-        print(f"liuyz_here_40_: {alpha_channel.shape} / {res_np_img.shape} / {alpha_channel.dtype} / {res_np_img.dtype}")
-    print(f"process time_2_: {(time.time() - start) * 1000}ms, {alpha_channel.shape}, {res_np_img.shape} / {res_np_img[250][250]} / {res_np_img.dtype}")
-    ext = 'png'
-    image = Image.open(io.BytesIO(numpy_to_bytes(res_np_img, ext)))
-    image.save(f'./result_image.png')
-    return image # res_np_img.astype(np.uint8) # image
-    
-    '''
-    ext = get_image_ext(origin_image_bytes)
-    return ext
-    '''
-    
-def model_process_filepath(input): #image, mask):
-    global model
-    # {'image': '/tmp/tmp8mn9xw93.png', 'mask': '/tmp/tmpn5ars4te.png'}
-    # input = request.files
-    # RGB
-    origin_image_bytes = read_content(input["image"])
-    print(f'origin_image_bytes = ', type(origin_image_bytes), len(origin_image_bytes))
-
-    image, alpha_channel = load_img(origin_image_bytes)
-    
-    alpha_channel = (np.ones((image.shape[0],image.shape[1]))*255).astype(np.uint8)
-    original_shape = image.shape
-    interpolation = cv2.INTER_CUBIC
-
-    image_pil = Image.fromarray(image)
-    # mask_pil = Image.fromarray(mask).convert("L")
-    
-    # form = request.form
-    # print(f'size_limit_1_ =  ', form["sizeLimit"], type(input["image"]))
-    size_limit = "Original" #: Union[int, str] = form.get("sizeLimit", "1080")
-    print(f'size_limit_2_ =  {size_limit}')
-    if size_limit == "Original":
-        size_limit = max(image.shape)
-    else:
-        size_limit = int(size_limit)
-    print(f'size_limit_3_ =  {size_limit}')
-
-    config = Config(
-        ldm_steps=25,
-        ldm_sampler='plms',
-        zits_wireframe=True,
-        hd_strategy='Original',
-        hd_strategy_crop_margin=196,
-        hd_strategy_crop_trigger_size=1280,
-        hd_strategy_resize_limit=2048,
-        prompt='',
-        use_croper=False,
-        croper_x=0,
-        croper_y=0,
-        croper_height=512,
-        croper_width=512,
-        sd_mask_blur=5,
-        sd_strength=0.75,
-        sd_steps=50,
-        sd_guidance_scale=7.5,
-        sd_sampler='ddim',
-        sd_seed=42,
-        cv2_flag='INPAINT_NS',
-        cv2_radius=5,
-    )
-    
-    print(f'config/alpha_channel/size_limit = {config} / {alpha_channel} / {size_limit}')
-    if config.sd_seed == -1:
-        config.sd_seed = random.randint(1, 999999999)
-
-    logger.info(f"Origin image shape: {original_shape}")
-    print(f"Origin image shape: {original_shape} / {image[250][250]}")
-    image = resize_max_size(image, size_limit=size_limit, interpolation=interpolation)
-    logger.info(f"Resized image shape: {image.shape} / {type(image)}")
-    print(f"Resized image shape: {image.shape} / {image[250][250]}")
-
-    mask, _ = load_img(read_content(input["mask"]), gray=True)
-    mask = resize_max_size(mask, size_limit=size_limit, interpolation=interpolation)
-    print(f"mask image shape: {mask.shape} / {type(mask)} / {mask[250][250]} / {alpha_channel}")
-
-    if model is None:
-        return None
-        
-    start = time.time()
-    res_np_img = model(image, mask, config)
-    logger.info(f"process time: {(time.time() - start) * 1000}ms, {res_np_img.shape}")
-    print(f"process time_1_: {(time.time() - start) * 1000}ms, {alpha_channel.shape}, {res_np_img.shape} / {res_np_img[250][250]} / {res_np_img.dtype}")
-
-    torch.cuda.empty_cache()
-
-    if alpha_channel is not None:
-        print(f"liuyz_here_10_: {alpha_channel.shape} / {alpha_channel.dtype} / {res_np_img.dtype}") 
-        if alpha_channel.shape[:2] != res_np_img.shape[:2]:
-            print(f"liuyz_here_20_: {alpha_channel.shape} / {res_np_img.shape}")
-            alpha_channel = cv2.resize(
-                alpha_channel, dsize=(res_np_img.shape[1], res_np_img.shape[0])
-            )
-        print(f"liuyz_here_30_: {alpha_channel.shape} / {res_np_img.shape} / {alpha_channel.dtype} / {res_np_img.dtype}")
-        res_np_img = np.concatenate(
-            (res_np_img, alpha_channel[:, :, np.newaxis]), axis=-1
-        )
-        print(f"liuyz_here_40_: {alpha_channel.shape} / {res_np_img.shape} / {alpha_channel.dtype} / {res_np_img.dtype}")
-    ext = get_image_ext(origin_image_bytes)
-    print(f"process time_2_: {(time.time() - start) * 1000}ms, {alpha_channel.shape}, {res_np_img.shape} / {res_np_img[250][250]} / {res_np_img.dtype} /{ext}")
-  
-    image = Image.open(io.BytesIO(numpy_to_bytes(res_np_img, ext)))
-    image.save(f'./result_image.png')
-    return  image # image
 
 def model_process(image, mask, alpha_channel, ext):
     global model
@@ -382,6 +184,7 @@ def model_process(image, mask, alpha_channel, ext):
 
     torch.cuda.empty_cache()
 
+    alpha_channel = None
     if alpha_channel is not None:
         print(f"liuyz_here_10_: {alpha_channel.shape} / {alpha_channel.dtype} / {res_np_img.dtype}") 
         if alpha_channel.shape[:2] != res_np_img.shape[:2]: