Update app.py

app.py

@@ -1,8 +1,6 @@
 import gradio as gr
 from transformers import AutoProcessor, CLIPModel
-from fashion_clip.fashion_clip import FashionCLIP
 
-fclip = FashionCLIP('fashion-clip')
 
 # Charger le pipeline
 
@@ -12,12 +10,14 @@ processor = AutoProcessor.from_pretrained("patrickjohncyh/fashion-clip")
 # Définir la fonction pour la classification d'image avec du texte en entrée
 def classify_image_with_text(text, image):
     # Effectuer la classification d'image à l'aide du texte
-    image_embeddings = fclip.encode_images(image, batch_size=32)
-    text_embeddings = fclip.encode_text(text, batch_size=32)
-    # we normalize the embeddings to unit norm (so that we can use dot product instead of cosine similarity to do comparisons)
-    image_embeddings = image_embeddings/np.linalg.norm(image_embeddings, ord=2, axis=-1, keepdims=True)
-    text_embeddings = text_embeddings/np.linalg.norm(text_embeddings, ord=2, axis=-1, keepdims=True)
-    return text_embeddings;
+     inputs = processor(
+            text=["a photo of a man", "a photo of woman"], images=image, return_tensors="pt", padding=True
+    )
+    outputs = model(**inputs)
+    logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
+    probs = logits_per_image.softmax(dim=1)  
+    print(probs)
+    return probs
     
 # Créer l'interface Gradio avec l'API de Gradio Blocks
 with gr.Interface(