Update app.py

app.py

@@ -1,18 +1,18 @@
 import os
-# ✅ MUST be before importing transformers
-os.environ["TRANSFORMERS_CACHE"] = "/tmp/huggingface"
+os.environ["HF_HOME"] = "/tmp/huggingface"
 
 from fastapi import FastAPI, UploadFile, File
-from transformers import AutoModelForImageClassification, AutoImageProcessor
+from transformers import SiglipForImageClassification, AutoImageProcessor
 from PIL import Image
-import torch.nn.functional as F
 import torch
+import torch.nn.functional as F
 import io
 
 app = FastAPI()
 
-model = AutoModelForImageClassification.from_pretrained("prithivMLmods/Gender-Classifier-Mini")
-processor = AutoImageProcessor.from_pretrained("prithivMLmods/Gender-Classifier-Mini")
+model_name = "prithivMLmods/Gender-Classifier-Mini"
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
 
 @app.post("/classify/")
 async def classify_gender(image: UploadFile = File(...)):
@@ -21,10 +21,11 @@ async def classify_gender(image: UploadFile = File(...)):
     inputs = processor(images=img, return_tensors="pt")
 
     with torch.no_grad():
-        logits = model(**inputs).logits
-        probs = F.softmax(logits, dim=1)
-        pred = torch.argmax(probs).item()
-        confidence = probs[0][pred].item()
-        label = model.config.id2label[pred]
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probs = F.softmax(logits, dim=1).squeeze().tolist()
+
+    labels = {"0": "Female ♀", "1": "Male ♂"}
+    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
 
-    return {"label": label, "confidence": confidence}
+    return predictions