Update app.py

app.py

@@ -12,21 +12,27 @@ import matplotlib.pyplot as plt
 import warnings
 warnings.filterwarnings("ignore")
 
+# Clean up any previous runs
+if os.path.exists("DIS"):
+    os.system("rm -rf DIS")
+
+# Clone and setup the model
 os.system("git clone https://github.com/xuebinqin/DIS")
 os.system("mv DIS/IS-Net/* .")
 
-# project imports
+# Project imports
 from data_loader_cache import normalize, im_reader, im_preprocess 
 from models import *
 
-#Helpers
+# Device configuration
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
-# Download official weights
+# Setup model directory and weights
 if not os.path.exists("saved_models"):
-    os.mkdir("saved_models")
-    os.system("mv isnet.pth saved_models/")
-    
+    os.makedirs("saved_models", exist_ok=True)
+    if os.path.exists("isnet.pth"):
+        os.system("mv isnet.pth saved_models/")
+
 class GOSNormalize(object):
     '''
     Normalize the Image using torch.transforms
@@ -35,26 +41,24 @@ class GOSNormalize(object):
         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)
 
-def build_model(hypar,device):
-    net = hypar["model"]#GOSNETINC(3,1)
-
-    # convert to half precision
-    if(hypar["model_digit"]=="half"):
+    # Convert to half precision
+    if hypar["model_digit"] == "half":
         net.half()
         for layer in net.modules():
             if isinstance(layer, nn.BatchNorm2d):
@@ -62,92 +66,109 @@ def build_model(hypar,device):
 
     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)
+    if hypar["restore_model"] != "":
+        net.load_state_dict(torch.load(
+            hypar["model_path"]+"/"+hypar["restore_model"], 
+            map_location=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"):
+    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
-   
+    inputs_val_v = Variable(inputs_val, requires_grad=False).to(device)
     ds_val = net(inputs_val_v)[0] # list of 6 results
+    pred_val = ds_val[0][0,:,:,:] # B x 1 x H x W
 
-    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'))
+    # Recover the prediction spatial size to the original 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
 
-    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
+    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)
 
-
 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]
-
+    try:
+        image_path = image.name if hasattr(image, 'name') else 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_path).convert("RGB")
+        
+        im_rgba = im_rgb.copy()
+        im_rgba.putalpha(pil_mask)
+
+        return [im_rgba, pil_mask]
+    except Exception as e:
+        print(f"Error during inference: {str(e)}")
+        raise e
 
 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)"
+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.
+<br>GitHub: https://github.com/xuebinqin/DIS
+<br>Telegram bot: https://t.me/restoration_photo_bot
+[![](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>"
 
+# Create interface
 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']],
+    inputs=gr.Image(type="filepath"),
+    outputs=[
+        gr.Image(type="pil", label="Image with Transparency"),
+        gr.Image(type="pil", label="Mask Only")
+    ],
+    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)
+    allow_flagging="never"
+)
+
+# Launch with more robust settings
+interface.launch(
+    server_name="0.0.0.0",
+    server_port=7860,
+    enable_queue=True,
+    share=False,
+    debug=True,
+    show_error=True
+)