Update app.py

app.py

@@ -1,64 +1,153 @@
-from flask import Flask, request, jsonify
-from gradio_client import Client, handle_file
+import cv2
+import gradio as gr
+import os
 from PIL import Image
-import requests
-import io
-import base64
 import numpy as np
-from io import BytesIO
+import torch
+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")
 
-app = Flask(__name__)
+os.system("git clone https://github.com/xuebinqin/DIS")
+os.system("mv DIS/IS-Net/* .")
 
-client = Client("ECCV2022/dis-background-removal")
+# project imports
+from data_loader_cache import normalize, im_reader, im_preprocess 
+from models import *
 
-def image_to_data_url(img: Image.Image) -> str:
-    buffered = io.BytesIO()
-    img.save(buffered, format="PNG")
-    img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
-    return f"data:image/png;base64,{img_str}"
-def base64_to_image(data_url):
-    header, encoded = data_url.split(",", 1)
-    binary_data = base64.b64decode(encoded)
-    image = Image.open(BytesIO(binary_data))
-    return image
+#Helpers
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
-import tempfile
+# 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
+    '''
+    def __init__(self, mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225]):
+        self.mean = mean
+        self.std = std
 
-@app.route("/remove_background", methods=["POST"])
-def remove_background():
-    data = request.json
-    data_url = data.get("image_url")
+    def __call__(self,image):
+        image = normalize(image,self.mean,self.std)
+        return image
 
-    if not data_url:
-        return jsonify({"error": "image_url is required"}), 400
 
-    try:
-        # base64データURLから画像を取得して一時ファイルに保存
-        input_image = base64_to_image(data_url).convert("RGB")
-        with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp:
-            input_image.save(tmp, format="PNG")
-            temp_path = tmp.name
+transform =  transforms.Compose([GOSNormalize([0.5,0.5,0.5],[1.0,1.0,1.0])])
 
-        # Gradioのモデルに画像を渡して背景除去を実行
-        result = client.predict(
-            image=handle_file(temp_path),
-            api_name="/predict"
-        )
+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)
+    shape = torch.from_numpy(np.array(im_shp))
+    return transform(im).unsqueeze(0), shape.unsqueeze(0) # make a batch of image, shape
 
-        # 結果として返される2つの画像パスを取得
-        image_path1, image_path2 = result
-        depth_image = Image.open(image_path2)
-        processed_image = Image.open(image_path1)
 
-        return jsonify({
-            "depth_image": image_to_data_url(depth_image),
-            "semi_transparent_image": image_to_data_url(processed_image)
-        })
+def build_model(hypar,device):
+    net = hypar["model"]#GOSNETINC(3,1)
 
-    except Exception as e:
-        return jsonify({"error": str(e)}), 500
+    # convert to half precision
+    if(hypar["model_digit"]=="half"):
+        net.half()
+        for layer in net.modules():
+            if isinstance(layer, nn.BatchNorm2d):
+                layer.float()
 
+    net.to(device)
 
-if __name__ == "__main__":
-    app.run(debug=True, host="0.0.0.0", port=7860)
+    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
+    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
+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 = "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>"
+
+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']],
+    title=title,
+    description=description,
+    article=article,
+    flagging_mode="never",
+    cache_mode="lazy",
+    ).queue(api_open=True).launch(show_error=True, show_api=True)