Update app.py

app.py

@@ -8,7 +8,6 @@ from torch.autograd import Variable
 from torchvision import transforms
 import torch.nn.functional as F
 import gdown
-import matplotlib.pyplot as plt
 import warnings
 warnings.filterwarnings("ignore")
 
@@ -19,14 +18,14 @@ os.system("mv DIS/IS-Net/* .")
 from data_loader_cache import normalize, im_reader, im_preprocess 
 from models import *
 
-#Helpers
+# Helpers
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
 # Download official weights
 if not os.path.exists("saved_models"):
     os.mkdir("saved_models")
     os.system("mv isnet.pth saved_models/")
-    
+
 class GOSNormalize(object):
     '''
     Normalize the Image using torch.transforms
@@ -39,8 +38,7 @@ 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])])
+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)
@@ -49,9 +47,8 @@ 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"]#GOSNETINC(3,1)
+    net = hypar["model"]
 
     # convert to half precision
     if(hypar["model_digit"]=="half"):
@@ -68,8 +65,7 @@ def build_model(hypar,device):
     net.eval()  
     return net
 
-    
-def predict(net,  inputs_val, shapes_val, hypar, device):
+def predict(net, inputs_val, shapes_val, hypar, device):
     '''
     Given an Image, predict the mask
     '''
@@ -80,14 +76,11 @@ 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
+    # 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'))
 
     ma = torch.max(pred_val)
@@ -98,8 +91,7 @@ def predict(net,  inputs_val, shapes_val, hypar, device):
     return (pred_val.detach().cpu().numpy()*255).astype(np.uint8) # it is the mask we need
     
 # Set Parameters
-hypar = {} # paramters for inferencing
-
+hypar = {} # parameters 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
@@ -112,42 +104,38 @@ 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["input_size"] = [1024, 1024] ## model 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
+# Build Model
 net = build_model(hypar, device)
 
-
 def inference(image):
-  image_path = image
+    image_path = image
+    image_tensor, orig_size = load_image(image_path, hypar) 
+    mask = predict(net, image_tensor, orig_size, hypar, device)
   
-  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")
   
-  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]
+    im_rgba = im_rgb.copy()
+    im_rgba.putalpha(pil_mask)
 
+    return [im_rgba, pil_mask]
 
-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>"
+title = "Image Segmentation"
+description = ""
+article = ""
 
 interface = gr.Interface(
     fn=inference,
     inputs=gr.Image(type='filepath'),
     outputs=["image", "image"],
-    examples=[['robot.png'], ['ship.png']],
     title=title,
     description=description,
     article=article,
     allow_flagging='never',
     cache_examples=False,
-    ).queue().launch(show_error=True)
+).queue().launch(show_error=True)