Init models only once

app.py

@@ -1,8 +1,8 @@
-import base64
-import os.path
-from io import BytesIO
-from pathlib import Path
 
+import base64
+import os
+import sys
+import csv
 import spaces
 import glob
 import numpy as np
@@ -10,19 +10,22 @@ import gradio as gr
 import rasterio as rio
 import matplotlib.pyplot as plt
 import matplotlib as mpl
+from io import BytesIO
+from pathlib import Path
 from PIL import Image
 from matplotlib import rcParams
 from msclip.inference import run_inference_classification
+from msclip.inference.utils import build_model
 
 rcParams["font.size"] = 9
 rcParams["axes.titlesize"] = 9
 IMG_PX = 300
 
-import sys
-import csv
-
 csv.field_size_limit(sys.maxsize)
 
+# Init Llama3-MS-CLIP from Hugging Face
+model, preprocess, tokenizer = build_model()
+
 EXAMPLES = {
     "EuroSAT": {
         "images": glob.glob("examples/eurosat/*.tif"),
@@ -163,7 +166,14 @@ def classify(images, class_text):
     class_names = [c.strip() for c in class_text.split(",") if c.strip()]
     cards = []
 
-    df = run_inference_classification(image_path=images, class_names=class_names, verbose=False)
+    df = run_inference_classification(
+        model=model,
+        preprocess=preprocess,
+        tokenizer=tokenizer,
+        image_path=images,
+        class_names=class_names,
+        verbose=False
+    )
     for img_path, (id, row) in zip(images, df.iterrows()):
         scores = row[2:].astype(float)  # drop filename column
         top = scores.sort_values(ascending=False)[:3]