Forums - Tensorflow conversion error

6 posts / 0 new
or Register
Last post
Tensorflow conversion error
jax79sg
Join Date: 10 Mar 18
Posts: 12
Posted: Mon, 2018-03-12 00:12
Top
Hi, tried converting a frozen tensorflow graph from https://www.github.com/ildoonet/tf-openpose and encountered the following error. Wasn't able to figure out what's wrong, have anyone encountered similar issues?
snpe-tensorflow-to-dlc --graph ~/qualcommTfpose/models/ildoonet.pb --input_dim "image" 320,176,3 --dlc ildoonet.dlc --out_node "Openpose/concat_stage7"
 
 
 [[Node: MobilenetV1/Conv2d_1_depthwise/depthwise = DepthwiseConv2dNative[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], _device="/job:localhost/replica:0/task:0/cpu:0"](MobilenetV1/Conv2d_0/Relu, MobilenetV1/Conv2d_1_depthwise/depthwise_weights/read)]]
2018-03-12 15:03:58,756 - 126 - ERROR - Encountered Error: list index out of range
Traceback (most recent call last):
  File "/home/user/snpe-sdk/bin/x86_64-linux-clang/snpe-tensorflow-to-dlc", line 120, in main
    converter.convert(args.dlc, args.model_version, converter_command)
  File "/home/user/snpe-sdk/lib/python/converters/tensorflow/converter.py", line 303, in convert
    self._convert_layers()
  File "/home/user/snpe-sdk/lib/python/converters/tensorflow/converter.py", line 353, in _convert_layers
    self._create_layers(descriptors)
  File "/home/user/snpe-sdk/lib/python/converters/tensorflow/converter.py", line 389, in _create_layers
    self._create_layer(layer_builder, descriptor)
  File "/home/user/snpe-sdk/lib/python/converters/tensorflow/converter.py", line 461, in _create_layer
    layer_builder.build_layer(self._context, descriptor, inputs, outputs)
  File "/home/user/snpe-sdk/lib/python/converters/tensorflow/layers/convolution.py", line 318, in build_layer
    descriptor.dilationX])
  File "/home/user/snpe-sdk/lib/python/converters/tensorflow/layers/convolution.py", line 345, in calculate_padding_size
    pad_y = max(((output_size[0] - 1) * strides[0] + filter_h - input_size[0]), 0)
IndexError: list index out of range
 
  • Up0
  • Down0
Re: Tensorflow conversion error
weiting_hsiao
Join Date: 2 May 18
Posts: 4
Posted: Tue, 2018-05-08 20:30
Top

Did you solve this problem?

I have same problem...

  • Up0
  • Down0
Re: Tensorflow conversion error
songchen7788
Join Date: 28 Jan 19
Posts: 1
Posted: Sun, 2019-06-09 12:06
Top

This is a bug when SNPE tries to merge two sequential 'concat' nodes.

Versions : 

tensorflow-gpu 1.6

cuda 9.0 cudnn 7.1.2

SNPE 1.25.0

 

Bug Position :

in 'converter.py' line 422  , function  'transform_layer'

After processing the 1st 'concat' node in 'transform_layer', the second 'concat' node's 'child_ops' of the 1st concat was set to null , causing 'index out of range' error.

 

  • Up0
  • Down0
Re: Tensorflow conversion error
nha.tuan84
Join Date: 25 Sep 19
Posts: 1
Posted: Thu, 2019-10-03 02:30
Top

it is more than one year but noone fix this. I have problem with yolov3.
 

  • Up0
  • Down0
Re: Tensorflow conversion error
frank.huang_1
Join Date: 22 Jul 20
Posts: 7
Posted: Tue, 2020-08-18 03:15
Top

Hi, so have you sovled this problem?

I have the same problem now on converting yolov3, but I have no idea about this problem.

Can you give me any advice?

Thanks

  • Up0
  • Down0
Re: Tensorflow conversion error
larryhems
Join Date: 8 Sep 20
Posts: 1
Posted: Tue, 2020-09-08 23:37
Top
This error basically means you are trying to access a value at a List index which is out of bounds i.e greater than the last index of the list or less than the least index in the list. So the first element is 0, second is 1, so on. So if there are n elements in a python list, the last element is n-1 . If you try to access the empty or None element by pointing available index of the list, then you will get the "List index out of range " error. To solve this error, you should make sure that you're not trying to access a non-existent item in a list.
 
 
  • Up0
  • Down0
or Register

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.