Create app.py

app.py

@@ -0,0 +1,38 @@
+import gradio as gr
+import torch
+from PIL import Image
+
+#from donut import DonutModel
+
+def demo_process(input_img):
+    global pretrained_model, task_prompt, task_name
+    # input_img = Image.fromarray(input_img)
+    output = pretrained_model.inference(image=input_img, prompt=task_prompt)["predictions"][0]
+    return output
+
+task_prompt = f"<s_cord-v2>"
+
+image = Image.open("/content/SKMBT_75122072616550_Page_37_Image_0001.png")
+image.save("cord_sample_receipt1.png")
+image = Image.open("/content/SKMBT_75122072616550_Page_50_Image_0001.png")
+image.save("cord_sample_receipt2.png")
+
+#pretrained_model = DonutModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
+#pretrained_model.encoder.to(torch.bfloat16)
+
+model = torch.load("/content/drive/MyDrive/fast_job/DONUT_model/donut/model.pt")
+# Move model to GPU
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+demo = gr.Interface(
+    fn=demo_process,
+    inputs= gr.inputs.Image(type="pil"),
+    outputs="json",
+    title=f"Donut 🍩 demonstration for `Medical Prescription Dataset` task",
+    description="""This model is trained with 200 medical prescription handwritten document images. <br>""",
+    examples=[["cord_sample_receipt1.png"], ["cord_sample_receipt2.png"]],
+    cache_examples=False,
+)
+
+demo.launch()