训练 Faster R-CNN 时出错

Question

我正在尝试使用我的计算机在 Ubuntu 16.04 上运行 Faster R-CNN 和一些同行。 但我被困住了。 而且我在谷歌上找不到像我一样的错误。

Normalizing targets
done
Solving...
Traceback (most recent call last):
  File "./tools/train_net.py", line 96, in <module>
    max_iters=args.max_iters)
  File "/home/david/Faster-RCNN_TF/tools/../lib/fast_rcnn/train.py", line 222, in train_net
    sw.train_model(sess, max_iters)
  File "/home/david/Faster-RCNN_TF/tools/../lib/fast_rcnn/train.py", line 95, in train_model
    rpn_cross_entropy = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(rpn_cls_score, rpn_label))
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/nn_ops.py", line 1686, in sparse_softmax_cross_entropy_with_logits
    labels, logits)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/nn_ops.py", line 1535, in _ensure_xent_args
    "named arguments (labels=..., logits=..., ...)" % name)
ValueError: Only call `sparse_softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...)

我不知道这是什么错误以及如何解决此错误。 请帮帮我

Answer 1

而不是这个：

rpn_cross_entropy = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(rpn_cls_score, rpn_label))

尝试写作：

tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(rpn_label, rpn_cls_score))

如果不起作用，请尝试：

tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=rpn_label, logits=rpn_cls_score))