Update app.py

app.py

@@ -122,7 +122,7 @@ clip_text_sess = ort.InferenceSession(CLIP_TEXT_ENCODER_PATH, providers=["CPUExe
 clip_tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-base-patch32")
 
 transform = transforms.Compose([
-    transforms.Resize((256, 256)),
+    transforms.Resize((224, 224)),
     transforms.ToTensor(),
     transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
 ])