Update app.py

app.py

@@ -1,22 +1,30 @@
-import gradio as gr
-from transformers import AutoProcessor, Pix2StructForConditionalGeneration
+from transformers import AutoProcessor, Pix2StructForConditionalGeneration, Pix2StructProcessor
+import requests
+import json
 from PIL import Image
 
-model = Pix2StructForConditionalGeneration.from_pretrained('google/deplot')
-processor = AutoProcessor.from_pretrained('google/deplot')
+model = Pix2StructForConditionalGeneration.from_pretrained("google/deplot")
+processor = AutoProcessor.from_pretrained("google/deplot")
+# processor = Pix2StructProcessor.from_pretrained('google/deplot')
+# url = "https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/val/png/5090.png"
+# image = Image.open(requests.get(url, stream=True).raw)
+image = Image.open('222.png')
 
-def process_image(image):
-    inputs = processor("Generate the underlying data table of the figure below:", image, return_tensors="pt")
-    predictions = model.generate(**inputs, max_new_tokens=512)
-    result = processor.decode(predictions[0], skip_special_tokens=True)
-    return result
+inputs = processor(images=image, text="Generate underlying data table of the figure below:", return_tensors="pt")
+predictions = model.generate(**inputs, max_new_tokens=512)
+print("prediction")
+print(processor.decode(predictions[0], skip_special_tokens=True))
 
-demo = gr.Interface(
-    fn=process_image,
-    inputs=gr.Image(type="pil"),
-    outputs="text",
-    title="Chart to Text Converter",
-    description="Upload a chart image to extract its data into table format"
-)
+raw_output = processor.decode(predictions[0], skip_special_tokens=True)
+split_by_newline = raw_output.split("<0x0A>")
+result_array = []
 
-demo.launch()
+for item in split_by_newline:
+    result_array.append([x.strip() for x in item.split("|")])
+
+print("result:")
+print(result_array)
+
+with open('test.log', mode='w') as file:
+    for row in result_array:
+        file.write(" | ".join(row) + "\n")