finish

app.py

@@ -109,37 +109,26 @@ def sepia(input_img):
 
 def segment_and_caption(input_img):
     input_img = Image.fromarray(input_img)
-
-    # 세그멘테이션 수행
     inputs = feature_extractor(images=input_img, return_tensors="tf")
     outputs = seg_model(**inputs)
     logits = outputs.logits
-
     logits = tf.transpose(logits, [0, 2, 3, 1])
     logits = tf.image.resize(
         logits, input_img.size[::-1]
     )
     seg = tf.math.argmax(logits, axis=-1)[0]
-
-    # 세그멘테이션 결과를 텍스트로 변환
     seg_text = ""
     for label, label_name in enumerate(labels_list):
         count = np.sum(seg.numpy() == label)
         seg_text += f"{label_name}: {count} pixels\n"
-
-    # 이미지 캡션 생성
     caption = caption_model.generate(input_img, max_length=20, num_return_sequences=1, return_dict_in_generate=True)
     caption_text = caption[0]['text']
-
-    # 세그멘테이션 결과와 캡션을 반환
     return input_img, seg_text, caption_text
 
 
-
-
 demo = gr.Interface(fn=segment_and_caption,
                     inputs=gr.Image(shape=(1024, 1024)),
-                    outputs=["image","text", "text"],
+                    outputs=["image", "text", "text"],
                     examples=["city-1.jpg", "city-2.jpg", "city-3.jpg", "city-4.jpg", "city-5.jpg"],
                     allow_flagging='never')