added logging

app.py

@@ -11,6 +11,7 @@ import gdown
 import matplotlib.pyplot as plt
 import warnings
 warnings.filterwarnings("ignore")
+import time
 
 os.system("git clone https://github.com/xuebinqin/DIS")
 os.system("mv DIS/IS-Net/* .")
@@ -39,7 +40,6 @@ class GOSNormalize(object):
         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])])
 
 def load_image(im_path, hypar):
@@ -49,11 +49,10 @@ def load_image(im_path, hypar):
     shape = torch.from_numpy(np.array(im_shp))
     return transform(im).unsqueeze(0), shape.unsqueeze(0) # make a batch of image, shape
 
+def build_model(hypar, device):
+    net = hypar["model"]
 
-def build_model(hypar,device):
-    net = hypar["model"]#GOSNETINC(3,1)
-
-    # convert to half precision
+    # convert to half precision if needed
     if(hypar["model_digit"]=="half"):
         net.half()
         for layer in net.modules():
@@ -68,7 +67,6 @@ def build_model(hypar,device):
     net.eval()  
     return net
 
-    
 def predict(net,  inputs_val, shapes_val, hypar, device):
     '''
     Given an Image, predict the mask
@@ -80,74 +78,84 @@ def predict(net,  inputs_val, shapes_val, hypar, device):
     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
-
-    ## 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'))
+    inputs_val_v = Variable(inputs_val, requires_grad=False).to(device) 
+    ds_val = net(inputs_val_v)[0]
+    pred_val = ds_val[0][0,:,:,:]
+    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
-
+    pred_val = (pred_val-mi)/(ma-mi) # normalize to 0~1
 
-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
+    if device == 'cuda': 
+        torch.cuda.empty_cache()
+    return (pred_val.detach().cpu().numpy()*255).astype(np.uint8)
 
-##  choose floating point accuracy --
-hypar["model_digit"] = "full" ## indicates "half" or "full" accuracy of float number
+# Set Parameters
+hypar = {} 
+hypar["model_path"] ="./saved_models"
+hypar["restore_model"] = "isnet.pth"
+hypar["interm_sup"] = False
+hypar["model_digit"] = "full"
 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["cache_size"] = [1024, 1024]
+hypar["input_size"] = [1024, 1024]
+hypar["crop_size"] = [1024, 1024]
 hypar["model"] = ISNetDIS()
 
- # Build Model
+# 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")
+def inference(image, logs):
+    start_time = time.time()
+    
+    image_tensor, orig_size = load_image(image, hypar) 
+    mask = predict(net, image_tensor, orig_size, hypar, device)
   
-  im_rgba = im_rgb.copy()
-  im_rgba.putalpha(pil_mask)
+    pil_mask = Image.fromarray(mask).convert('L')
+    im_rgb = Image.open(image).convert("RGB")
 
-  return [im_rgba, pil_mask]
+    im_rgba = im_rgb.copy()
+    im_rgba.putalpha(pil_mask)
+    
+    end_time = time.time()
+    elapsed = round(end_time - start_time, 2)
+    
+    # Update and return logs
+    logs = logs or ""
+    logs += f"Processed in {elapsed} seconds.\n"
 
+    # Return (gallery output), the logs state, and the logs display
+    return [im_rgba, pil_mask], logs, logs
 
 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>"
+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.Gallery(format="png"),
+    inputs=[gr.Image(type='filepath'), gr.State()],
+    outputs=[
+        gr.Gallery(format="png"),
+        gr.State(),
+        gr.Textbox(label="Logs", lines=6)
+    ],
     examples=[['robot.png'], ['ship.png']],
     title=title,
     description=description,
     article=article,
     flagging_mode="never",
     cache_mode="lazy",
-    ).queue().launch(show_api=True, show_error=True)
+).queue().launch(show_api=True, show_error=True)