model -> self.model.

pipeline.py

@@ -24,7 +24,7 @@ class PreTrainedPipeline():
 
         im = tf.image.resize(img, (128, 128))
         im = tf.cast(im, tf.float32) / 255.0
-        pred_mask = model.predict(im[tf.newaxis, ...])
+        pred_mask = self.model.predict(im[tf.newaxis, ...])
         
         # take the best performing class for each pixel
         # the output of argmax looks like this [[1, 2, 0], ...]
@@ -76,4 +76,4 @@ class PreTrainedPipeline():
                 "mask": mask_codes[f"mask_{cls}"],
                 "score": 1.0,
             })
-        return labels
+        return labels