Update tok2vec

spacy/pipeline/tagger.pyx

@@ -287,9 +287,24 @@ class Tagger(Pipe):
             self.add_label(tag)
         self.set_output(len(self.labels))
         if self.labels:
-            self.model.initialize(X=doc_sample)
+            label_sample = [
+                self.model.ops.alloc2f(len(doc), len(self.labels))
+                for doc in doc_sample
+            ]
+            for y in label_sample:
+                y[:, 0] = 1.0
         else:
-            self.model.initialize()
+            label_sample = None
+        if pipeline is not None:
+            for name, component in pipeline:
+                if component is self:
+                    break
+                if hasattr(component, "pipe"):
+                    doc_sample = list(component.pipe(doc_sample, batch_size=8))
+                else:
+                    doc_sample = [component(doc) for doc in doc_sample]
+ 
+        self.model.initialize(X=doc_sample, Y=label_sample)
         if sgd is None:
             sgd = self.create_optimizer()
         return sgd

spacy/pipeline/tok2vec.py

@@ -291,8 +291,15 @@ class Tok2VecListener(Model):
 
 def forward(model: Tok2VecListener, inputs, is_train: bool):
     """Supply the outputs from the upstream Tok2Vec component."""
+
     if is_train:
         model.verify_inputs(inputs)
         return model._outputs, model._backprop
     else:
-        return [doc.tensor for doc in inputs], lambda dX: []
+        width = model.get_dim("nO")
+        if model._outputs is None:
+            outputs = [model.ops.alloc2f(len(doc), width) for doc in inputs]
+        else:
+            outputs = model._outputs
+        model._outputs = None
+        return outputs, lambda dX: []