fix the error in interpreter when input is nd seq

zegnog · Jul 5, 2021 · 2415cb9 · 2415cb9
1 parent 5378533
commit 2415cb9
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 9 deletions.
diff --git a/allennlp/interpret/saliency_interpreters/integrated_gradient.py b/allennlp/interpret/saliency_interpreters/integrated_gradient.py
@@ -30,9 +30,9 @@ def saliency_interpret_from_json(self, inputs: JsonDict) -> JsonDict:
  # Normalize results
  for key, grad in grads.items():
  # The [0] here is undo-ing the batching that happens in get_gradients.
- embedding_grad = numpy.sum(grad[0], axis=1)
- norm = numpy.linalg.norm(embedding_grad, ord=1)
- normalized_grad = [math.fabs(e) / norm for e in embedding_grad]
+ embedding_grad = numpy.sum(grad[0], axis=-1)
+ norm = numpy.linalg.norm(embedding_grad, ord=1, keepdims=True)
+ normalized_grad = embedding_grad / norm
  grads[key] = normalized_grad
 
  instances_with_grads["instance_" + str(idx + 1)] = grads

diff --git a/allennlp/interpret/saliency_interpreters/simple_gradient.py b/allennlp/interpret/saliency_interpreters/simple_gradient.py
@@ -48,9 +48,9 @@ def saliency_interpret_from_json(self, inputs: JsonDict) -> JsonDict:
  # gradient and its respective embedding.
  input_idx = int(key[-1]) - 1
  # The [0] here is undo-ing the batching that happens in get_gradients.
- emb_grad = numpy.sum(grad[0] * embeddings_list[input_idx][0], axis=1)
- norm = numpy.linalg.norm(emb_grad, ord=1)
- normalized_grad = [math.fabs(e) / norm for e in emb_grad]
+ emb_grad = numpy.sum(grad[0] * embeddings_list[input_idx][0], axis=-1)
+ norm = numpy.linalg.norm(emb_grad, ord=1, keepdims=True)
+ normalized_grad = emb_grad / norm
  grads[key] = normalized_grad
 
  instances_with_grads["instance_" + str(idx + 1)] = grads

diff --git a/allennlp/interpret/saliency_interpreters/smooth_gradient.py b/allennlp/interpret/saliency_interpreters/smooth_gradient.py
@@ -39,9 +39,9 @@ def saliency_interpret_from_json(self, inputs: JsonDict) -> JsonDict:
  # Fine for now, but should fix for consistency.
 
  # The [0] here is undo-ing the batching that happens in get_gradients.
- embedding_grad = numpy.sum(grad[0], axis=1)
- norm = numpy.linalg.norm(embedding_grad, ord=1)
- normalized_grad = [math.fabs(e) / norm for e in embedding_grad]
+ embedding_grad = numpy.sum(grad[0], axis=-1)
+ norm = numpy.linalg.norm(embedding_grad, ord=1, keepdims=True)
+ normalized_grad = embedding_grad / norm
  grads[key] = normalized_grad
 
  instances_with_grads["instance_" + str(idx + 1)] = grads