Fix changes after merge

src/bioclip/predict.py

@@ -245,18 +245,18 @@ def forward(self, x: torch.Tensor) -> torch.Tensor:
         """
         img_features = self.model.encode_image(x)
         img_features = F.normalize(img_features, dim=-1)
-        return self.create_probabilities(img_features, self.txt_features)
+        return self.create_probabilities(img_features, self.txt_embeddings)
 
 
 class CustomLabelsClassifier(BaseClassifier):
     def __init__(self, cls_ary: List[str], **kwargs):
         super().__init__(**kwargs)
         self.tokenizer = create_bioclip_tokenizer(self.model_str)
         self.classes = [cls.strip() for cls in cls_ary]
-        self.txt_features = self._get_txt_features(self.classes)
+        self.txt_embeddings = self._get_txt_embeddings(self.classes)
 
     @torch.no_grad()
-    def _get_txt_features(self, classnames):
+    def _get_txt_embeddings(self, classnames):
         all_features = []
         for classname in classnames:
             txts = [template(classname) for template in OPENA_AI_IMAGENET_TEMPLATE]
@@ -272,7 +272,7 @@ def _get_txt_features(self, classnames):
     def predict(self, images: List[str] | str | List[PIL.Image.Image], k: int = None) -> dict[str, float]:
         if isinstance(images, str):
             images = [images]
-        probs = self.create_probabilities_for_images(images, self.txt_features)
+        probs = self.create_probabilities_for_images(images, self.txt_embeddings)
         result = []
         for i, image in enumerate(images):
             key = self.make_key(image, i)

tests/test_predict.py

@@ -211,7 +211,7 @@ def test_apply_filter(self):
 
     def test_forward(self):
         classifier = TreeOfLifeClassifier()
-        img = classifier.open_image(EXAMPLE_CAT_IMAGE)
+        img = classifier.ensure_rgb_image(EXAMPLE_CAT_IMAGE)
         img_features = torch.stack([classifier.preprocess(img)])
         result = classifier.forward(x=img_features)
         self.assertEqual(result.shape, torch.Size([1, len(classifier.txt_names)]))