ValueError:输入张量必须至少具有秩5（深度方向）

Question

我正在努力使this repo运行

我发现这个{a2}还没有解决，也指出了我的问题。 我使用的是Tensorflow 1.13.1（也尝试了1.14）和python 3

我得到的错误在depthwise_conv2d中：

 "input tensor must have rank %d at least" % (expected_input_rank))
 ValueError: input tensor must have rank 5 at least

检查张量时，我得到以下结果：

input tensor: Tensor("network/concat:0", shape=(?, 180, 270, 304), dtype=float32)

 filters: <tf.Variable 'network/slim_decoder/conv2d/weights:0' shape=(3, 3, 304, 1) dtype=float32_ref>

以下是函数的定义：

@add_arg_scope

 def depthwise_conv2d(

         inputs, filters, bias=None,

         strides=list([1, 1, 1, 1]), padding='SAME', dilations=list([1, 1, 1, 1]),

         to_batch_norm=False, batch_norm_decay=0.997, is_training=True, activation_fn=None, name=None

 ):

     if isinstance(strides, int):

         strides = list([1, strides, strides, 1])

     if isinstance(dilations, int):

         dilations = list([1, dilations, dilations, 1])

     print("input tensor: " + inputs)

     print("filters: " + filters)

     output = tf.nn.depthwise_conv2d(

         input=inputs,

         filter=filters,

         strides=strides,

         padding=padding,

         rate=dilations,

         name=name

     )
 
    if bias is not None:

         output = tf.nn.bias_add(output, bias)

     if to_batch_norm:

         output = batch_norm(output, is_training, batch_norm_decay)

     if activation_fn is not None:

         output = activation_fn(output)

     return output

我迷路了，非常感谢您的帮助，谢谢

Answer 1

尝试将膨胀参数从[1,1,1,1]更改为[1,1] tensorflow，2个列表除外