Update app.py

app.py

@@ -47,103 +47,69 @@ 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) # 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)
-
-    # convert to half precision
+    net = hypar["model"]
     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)
     net.eval()  
     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) # 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
+    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
-
+    pred_val = (pred_val-mi)/(ma-mi)
     if device == 'cuda': torch.cuda.empty_cache()
-    return (pred_val.detach().cpu().numpy()*255).astype(np.uint8) # it is the mask we need
+    return (pred_val.detach().cpu().numpy()*255).astype(np.uint8)
     
-# 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 = {}
+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
 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]
 
 
-title = ""
-description = ""
-article = ""
-
 interface = gr.Interface(
     fn=inference,
     inputs=gr.Image(type='filepath'),
     outputs=[gr.Image(type='filepath', format="png"), gr.Image(type='filepath', format="png", visible=False)],
     flagging_mode="never",
     cache_mode="lazy",
-    ).queue(api_open=True).launch(show_error=True, show_api=True)
+    ).queue(api_open=True).launch(show_error=True, show_api=True, share=False)