Fix: image feature calculated

src/CLIP.py

@@ -19,9 +19,9 @@ class CLIPImageEncoder:
         print(images)
         input = self.processor(images=images, return_tensors="pt")
         with torch.no_grad():
-            #image_features = self.model.get_image_features(**input)
-            image_features = self.model(**input).last_hidden_state[:,0].cpu()
+            image_features = self.model.get_image_features(**input)
+            #image_features = self.model(**input).last_hidden_state[:,0].cpu()
             print(image_features)
             print("--------------------")
             print(self.model.get_image_features(**input).cpu().detach().numpy()[0])
-        return {"clip_embeddings": image_features}
+        return {"clip_embeddings": image_features.cpu().detach().numpy()[0]}