convert tensorflow model use tf.nn.convolution have dilation_rate!=1 to uff out error

example code:

import uff

from tensorflow.keras.layers import Input, Conv2D
import tensorflow as tf
from tensorflow.keras import backend as K
import numpy as np
input_data = Input(name='fts_input', shape=(None,None,3), dtype='float32')
filter = np.ones((3,3,3,3), dtype='float32')
out = tf.nn.convolution(input_data,filter,'SAME',dilation_rate=[2,2])
out = tf.identity(out, name='out')

sess = K.get_session()
graphdef = sess.graph


log error:

Traceback (most recent call last):
  File "", line 34, in <module>
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/uff/converters/tensorflow/", line 112, in from_tensorflow
  File "/docker_environment/home/docker/anaconda3/lib/python3.6/site-packages/graphsurgeon/", line 32, in process_dilated_conv
    crops = dynamic_graph.find_node_inputs_by_name(chain[-1], "crops")[0]
IndexError: list index out of range

i get same error if graphdef use tensorflow.keras.layers.Conv2D have dilation_rate!=1

I have the same issue!

I meet the same issue when I try to convert a pre-trained mask_rcnn.pb to .uff

I experience the same issue when converting a ERFNet style model! Anyone know how to fix this?