Update app.py

app.py

@@ -1,115 +1,145 @@
-import cv2
-import gradio as gr
 import os
-from PIL import Image
+import warnings
 import numpy as np
 import torch
+import torch.nn as nn
+import torch.nn.functional as F
 from torch.autograd import Variable
 from torchvision import transforms
-import torch.nn.functional as F
-import gdown
-import matplotlib.pyplot as plt
-import warnings
+from PIL import Image
+import gradio as gr
+
+# Suppress warnings
 warnings.filterwarnings("ignore")
 
-os.system("git clone https://github.com/xuebinqin/DIS")
-os.system("mv DIS/IS-Net/* .")
+# Clone DIS repo if not exists
+if not os.path.exists("DIS"):
+    os.system("git clone https://github.com/xuebinqin/DIS")
 
-# project imports
-from data_loader_cache import normalize, im_reader, im_preprocess 
+# Move model files
+if not os.path.exists("models.py"):
+    os.system("mv DIS/IS-Net/* .")
+
+# Project imports
+from data_loader_cache import normalize, im_reader, im_preprocess
 from models import *
 
-#Helpers
+# Setup device
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
-# Download official weights
+# Prepare saved models folder
 if not os.path.exists("saved_models"):
     os.mkdir("saved_models")
+    # NOTE: make sure isnet.pth is available, otherwise manual download needed
     os.system("mv isnet.pth saved_models/")
-    
+
+# --- Helpers ---
 class GOSNormalize(object):
-    '''
-    Normalize the Image using torch.transforms
-    '''
     def __init__(self, mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225]):
         self.mean = mean
         self.std = std
 
-    def __call__(self,image):
-        image = normalize(image,self.mean,self.std)
-        return image
-
+    def __call__(self, image):
+        return normalize(image, self.mean, self.std)
 
-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)
 
-
-def build_model(hypar,device):
+def build_model(hypar, device):
     net = hypar["model"]
-    if(hypar["model_digit"]=="half"):
+    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()  
+    if hypar["restore_model"] != "":
+        net.load_state_dict(torch.load(
+            os.path.join(hypar["model_path"], hypar["restore_model"]),
+            map_location=device
+        ))
+    net.eval()
     return net
 
-def predict(net,  inputs_val, shapes_val, hypar, device):
+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)
-    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'))
+    ds_val = net(inputs_val_v)[0]
+    pred_val = ds_val[0][0, :, :, :]
+    pred_val = torch.squeeze(F.interpolate(
+        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)
-    if device == 'cuda': torch.cuda.empty_cache()
-    return (pred_val.detach().cpu().numpy()*255).astype(np.uint8)
-    
-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]
-hypar["input_size"] = [1024, 1024]
-hypar["crop_size"] = [1024, 1024]
-hypar["model"] = ISNetDIS()
-net = build_model(hypar, device)
+    pred_val = (pred_val - mi) / (ma - mi)
+    if device == 'cuda':
+        torch.cuda.empty_cache()
+    return (pred_val.detach().cpu().numpy() * 255).astype(np.uint8)
+
+# --- Prepare model ---
+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()
+}
 
+net = build_model(hypar, device)
 
+# --- Inference ---
 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]
+    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_path).convert("RGB")
+    im_rgba = im_rgb.copy()
+    im_rgba.putalpha(pil_mask)
+
+    return [im_rgba, pil_mask]
 
+# --- Custom CSS to hide footer ---
+css_hide_footer = """
+footer {display: none !important;}
+#share-btn-container {display: none !important;}
+"""
 
+# --- Gradio Interface ---
 interface = gr.Interface(
     fn=inference,
     inputs=gr.Image(type='filepath', height=300, width=300),
-    outputs=[gr.Image(type='filepath', format="png"), gr.Image(type='filepath', format="png", visible=False)],
+    outputs=[
+        gr.Image(type='filepath', format="png"),
+        gr.Image(type='filepath', format="png", visible=False)
+    ],
     flagging_mode="never",
-    cache_mode="lazy",
-    ).queue(api_open=False).launch(show_error=False, show_api=False, share=False)
+    cache_mode="lazy"
+)
+
+interface.launch(
+    show_error=False,
+    show_api=False,
+    share=False,
+    css=css_hide_footer
+)