Create app.py

app.py

@@ -0,0 +1,39 @@
+import torch 
+import re 
+import gradio as gr
+from gradio.components import Image, Textbox
+from transformers import AutoTokenizer, ViTImageProcessor, VisionEncoderDecoderModel 
+
+device=torch.device("cuda" if torch.cuda.is_available() else "cpu")
+local_path = "/app/model/nlpconnect_vit-gpt2-image-captioning/"
+feature_extractor = ViTImageProcessor.from_pretrained(local_path)
+tokenizer = AutoTokenizer.from_pretrained(local_path)
+model = VisionEncoderDecoderModel.from_pretrained(local_path).to(device)
+
+gen_kwargs = {"max_length": 128, "num_beams": 8}
+def predict(image):
+    image = image.convert('RGB')
+    image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
+    clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
+    caption_ids = model.generate(image, **gen_kwargs)[0]
+    caption_text = clean_text(tokenizer.decode(caption_ids))
+    return caption_text 
+
+
+_input = Image(label="Upload any Image", type = 'pil')
+_output = Textbox(type="text",label="Captions")
+examples = [f"example{i}.jpg" for i in range(1,7)]
+
+title = "Image Captioning "
+description = "Made by : 炼丹侠"
+iface = gr.Interface(
+            
+        fn=predict,
+        description=description,
+        inputs=_input,
+        outputs=_output,
+        title=title,
+        examples = examples
+    )
+gr.close_all() #关闭所有正在运行的端口
+iface.launch(server_name="0.0.0.0", server_port=7860, debug=True)