Update app.py

app.py

@@ -1,19 +1,12 @@
-import gradio as gr
-from gradio_imageslider import ImageSlider
-from loadimg import load_img
-from transformers import AutoModelForImageSegmentation
-import torch
-from torchvision import transforms
-from PIL import Image
-import os
+# GPU 설정을 CPU로 변경
+# GPU 설정을 삭제하거나 "cuda"를 "cpu"로 변경
+# torch.set_float32_matmul_precision("high")는 CPU에선 필요 없음.
 
-# 모델 로드 및 CPU로 설정
 birefnet = AutoModelForImageSegmentation.from_pretrained(
     "ZhengPeng7/BiRefNet", trust_remote_code=True
 )
 birefnet.to("cpu")  # GPU -> CPU로 변경
 
-# 이미지 전처리
 transform_image = transforms.Compose(
     [
         transforms.Resize((1024, 1024)),
@@ -22,10 +15,20 @@ transform_image = transforms.Compose(
     ]
 )
 
+def fn(image):
+    im = load_img(image, output_type="pil")
+    im = im.convert("RGB")
+    origin = im.copy()
+    processed_image = process(im)
+    return (processed_image, origin)
+
+# @spaces.GPU 데코레이터 제거
+# CPU 환경에서 동작하도록 설정
+
 def process(image):
     image_size = image.size
-    input_images = transform_image(image).unsqueeze(0).to("cpu")  # CPU로 변경
-    # 예측 수행
+    input_images = transform_image(image).unsqueeze(0).to("cpu")  # GPU -> CPU로 변경
+    # Prediction
     with torch.no_grad():
         preds = birefnet(input_images)[-1].sigmoid().cpu()
     pred = preds[0].squeeze()
@@ -34,50 +37,32 @@ def process(image):
     image.putalpha(mask)
     return image
 
-def fn(image):
-    im = load_img(image, output_type="pil")
+def process_file(f):
+    name_path = f.rsplit(".", 1)[0] + ".png"
+    im = load_img(f, output_type="pil")
     im = im.convert("RGB")
-    origin = im.copy()
-    processed_image = process(im)
-    
-    # JPG로 변환하여 저장
-    jpg_image = origin.copy()
-    jpg_image = jpg_image.convert("RGB")
-    jpg_path = "output.jpg"
-    jpg_image.save(jpg_path, format="JPEG")
-    
-    return [processed_image], jpg_path  # ImageSlider는 리스트를 기대함
-
-def convert_to_jpg(image):
-    if image is None:
-        return None
-    jpg_image = image.convert("RGB")
-    jpg_path = "downloaded_output.jpg"
-    jpg_image.save(jpg_path, format="JPEG")
-    return jpg_path
+    transparent = process(im)
+    transparent.save(name_path)
+    return name_path
 
-# Gradio 컴포넌트 정의
 slider1 = ImageSlider(label="Processed Image", type="pil")
+slider2 = ImageSlider(label="Processed Image from URL", type="pil")
 image_upload = gr.Image(label="Upload an image")
-output_download = gr.File(label="Download JPG File")
+image_file_upload = gr.Image(label="Upload an image", type="filepath")
+url_input = gr.Textbox(label="Paste an image URL")
+output_file = gr.File(label="Output PNG File")
 
-# 새로운 샘플 이미지 추가 (app.py와 동일한 폴더에 위치해야 함)
-sample_images = [["1.png"], ["2.jpg"], ["3.png"]]
+# Example images
+chameleon = load_img("butterfly.jpg", output_type="pil")
+url_example = "https://hips.hearstapps.com/hmg-prod/images/gettyimages-1229892983-square.jpg"
 
-# Gradio 인터페이스 설정
-tab1 = gr.Interface(
-    fn=fn, 
-    inputs=image_upload, 
-    outputs=[slider1, output_download], 
-    examples=sample_images, 
-    api_name="image"
-)
+tab1 = gr.Interface(fn, inputs=image_upload, outputs=slider1, examples=[chameleon], api_name="image")
+tab2 = gr.Interface(fn, inputs=url_input, outputs=slider2, examples=[url_example], api_name="text")
+tab3 = gr.Interface(process_file, inputs=image_file_upload, outputs=output_file, examples=["butterfly.jpg"], api_name="png")
 
-demo = gr.Interface(
-    tab1, 
-    title="Background Removal Tool", 
-    description="이미지를 업로드하면 배경이 제거된 이미지를 확인하고 JPG 파일로 다운로드할 수 있습니다."
+demo = gr.TabbedInterface(
+    [tab1, tab2, tab3], ["Image Upload", "URL Input", "File Output"], title="Background Removal Tool"
 )
 
 if __name__ == "__main__":
-    demo.launch(show_error=True)
+    demo.launch(show_error=True)