sampleUffSSD conversion fails? (KeyError: 'NMS')

I am trying to convert model (.pb) to uff in my host PC to do inference on Jetson TX2. I tried converting it on TX2 also but received the same KeyError: 'NMS

Model: ssd_inception_v2_coco_2017_11_17
Tensorflow Version tried: 1.9 | 2.0 | 1.13 | 1.14
uff version: ‘0.2.0’


python3 --input-file frozen_inference_graph.pb -O NMS -p


Loading frozen_inference_graph.pb
    Using output node NMS
    Converting to UFF graph
    Traceback (most recent call last):
      File "", line 93, in <module>
      File "", line 89, in main
      File "/lib/python3.5/site-packages/uff/converters/tensorflow/", line 103, in from_tensorflow_frozen_model
        return from_tensorflow(graphdef, output_nodes, **kwargs)
      File "/lib/python3.5/site-packages/uff/converters/tensorflow/", line 75, in from_tensorflow
      File "/lib/python3.5/site-packages/uff/converters/tensorflow/", line 64, in convert_tf2uff_graph
        uff_graph, input_replacements)
      File "/lib/python3.5/site-packages/uff/converters/tensorflow/", line 42, in convert_tf2uff_node
        tf_node = tf_nodes[name]
    KeyError: 'NMS'

Any leads will be great. Thank you.


Could you share which do you use?
There is a for ssd_inception_v2_coco_2017_11_17 model in /usr/src/tensorrt/samples/sampleUffSSD/.

Would you mind to give it a try first?

Thank you it worked.
Actually previously also I was using the same config. present in /usr/src/tensorrt/samples/sampleUffSSD/.
But I was facing the reported issue maybe because I was trying conversion in a virtual environment.

Thanks for your feedback.
Good to know it works now.