Tensorflow 如何定位TensorRT不支持的操作

当我将tensorflow模型（另存为.pb文件）转换为uff文件时，错误日志如下：

Using output node final/lanenet_loss/instance_seg
Using output node final/lanenet_loss/binary_seg
Converting to UFF graph
Warning: No conversion function registered for layer: Slice yet.
Converting as custom op Slice final/lanenet_loss/Slice
name: "final/lanenet_loss/Slice"
op: "Slice"
input: "final/lanenet_loss/Shape_1"
input: "final/lanenet_loss/Slice/begin"
input: "final/lanenet_loss/Slice/size"
attr {
  key: "Index"
  value {
    type: DT_INT32
  }
}
attr {
  key: "T"
  value {
    type: DT_INT32
  }
}

Traceback (most recent call last):
  File "tfpb_to_uff.py", line 16, in <module>
    uff_model = uff.from_tensorflow(graphdef=output_graph_def, output_filename=output_path, output_nodes=["final/lanenet_loss/instance_seg", "final/lanenet_loss/binary_seg"], text=True)
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/conversion_helpers.py", line 75, in from_tensorflow
    name="main")
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py", line 64, in convert_tf2uff_graph
    uff_graph, input_replacements)
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py", line 51, in convert_tf2uff_node
    op, name, tf_node, inputs, uff_graph, tf_nodes=tf_nodes)
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py", line 28, in convert_layer
    fields = cls.parse_tf_attrs(tf_node.attr)
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py", line 177, in parse_tf_attrs
    for key, val in attrs.items()}
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py", line 177, in <dictcomp>
    for key, val in attrs.items()}
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py", line 172, in parse_tf_attr_value
    return cls.convert_tf2uff_field(code, val)
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py", line 146, in convert_tf2uff_field
    return TensorFlowToUFFConverter.convert_tf2numpy_dtype(val)
  File "/home/dream/.local/lib/python3.5/site-packages/uff/converters/tensorflow/converter.py", line 74, in convert_tf2numpy_dtype
    return np.dtype(dt[dtype])
TypeError: list indices must be integers or slices, not AttrValue

---

如何在代码行中找到“切片”层，以便通过TensorRT自定义层对其进行修改？

既然您是从Tensorflow进行解析，那么最好看看TensorRT支持哪些层。从TensorRT 4开始，支持以下层：

• 占位符
• 常数
• 加、分、多、分、最小和最大
• 比亚萨德
• 负片、Abs、Sqrt、Rsqrt、Pow、Exp和Log
• FusedBatchNorm
• 雷卢，谭，乙状结肠
• SoftMax
• 卑鄙
• ConcatV2
• 重塑
• 转置
• Conv2D
• DepthwiseConv2dNative
• ConvTranspose2D
• 马克斯普尔
• AvgPool
• 如果紧跟这些TensorFlow层之一，则支持Pad： Conv2D、depthwisecon2dnative、MaxPool和AvgPool

从我在您的日志中看到的情况来看，您正在尝试部署LaneNet，它是的LaneNet吗

如果是这样的话，它似乎是H-Net的一种变体，但据该报报道，它的体系结构如下：

所以我看到Convs、Relus、Maxpool和Linear，它们都是受支持的，我不知道BN，也许可以看看它指的是哪一层，如果它不在受支持的网络列表中，你就必须从头开始实现它。

---

祝你好运

我搜索了我所有的代码，甚至找不到一个名为“slice”的单词，代码行中没有名字的图形中是否隐含了一些tensorflow操作？

graph list name: "final/lanenet_loss/Slice"
op: "Slice"
input: "final/lanenet_loss/Shape_1"
input: "final/lanenet_loss/Slice/begin"
input: "final/lanenet_loss/Slice/size"
attr {
  key: "Index"
  value {
    type: DT_INT32
  }
}
attr {
  key: "T"
  value {
    type: DT_INT32
  }
}