我在使用反卷积神经网络进行预测时遇到了这个异常。秩和形状看起来是相同的，所以我不确定问题出在哪里。

File "/home/Workspace/image-recognition/app/model/per_pixel_deconv.py", line 141, in Model    softmax = tf.nn.softmax(output, name=None)File "/home/anaconda2/envs/image-recognition/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 1396, in softmax    result = _op_def_lib.apply_op("Softmax", logits=logits, name=name)File "/home/anaconda2/envs/image-recognition/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 703, in apply_op    op_def=op_def)File "/home/anaconda2/envs/image-recognition/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2319, in create_op    set_shapes_for_outputs(ret)File "/home/anaconda2/envs/image-recognition/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1711, in set_shapes_for_outputs    shapes = shape_func(op)File "/home/anaconda2/envs/image-recognition/lib/python2.7/site-packages/tensorflow/python/framework/common_shapes.py", line 45, in _ShapeFunction    return [op.inputs[0].get_shape().with_rank(rank)]File "/home/anaconda2/envs/image-recognition/lib/python2.7/site-packages/tensorflow/python/framework/tensor_shape.py", line 641, in with_rank    raise ValueError("Shape %s must have rank %d" % (self, rank))ValueError: Shape (?, 128, 128, 2) must have rank 2

回答：

形状(?, 128, 128, 2)是一个秩4的张量，但softmax操作符显然期望的是一个秩2的张量。

看起来你在使用的是一个旧版本的TensorFlow。在0.10版本中，tf.nn.softmax要求输入必须是秩2：https://www.tensorflow.org/versions/r0.10/api_docs/python/nn/classification#softmax

在当前版本的TensorFlow中，tf.nn.softmax接受任何秩的输入：https://www.tensorflow.org/api_docs/python/nn/classification#softmax

尝试使用更新版本的TensorFlow。

希望这对你有帮助！