Error with sample model on raspbian jessie

[JRMeyer]

>>> fotiDim
[December 6, 2017, 8:45pm]

When trying to use the pre-trained model in Raspberry 3 with Raspbian
Jessie I get this error. I suspect I am running out of memory as the
error takes some time to appear while my memory consumption builds up.

I used the binary version of Tensorflow using the instructions
here.
The only change that I did was:

> python util/taskcluster.py slash --arch arm slash --target
> /path/to/destination/folder

where I used the

> --arch arm

to download the right architecture.

[This is an archived TTS discussion thread from discourse.mozilla.org/t/error-with-sample-model-on-raspbian-jessie]

[JRMeyer]

>>> lissyx
[December 6, 2017, 8:51pm]

Thanks!

Hm, two things:

arguments)
cause I guess

[Archived Post]

[JRMeyer]

>>> fotiDim
[December 9, 2017, 6:36pm]

I get a different error
without the arguments which seems to be OpKernel related. Any
suggestions?

19.30.37.png.filename}[2286×396 69.8

[Archived Post]

[JRMeyer]

>>> lissyx
[December 10, 2017, 10:49am]

Well, it looks like this broke when we switched from being tensorflow
slash ~r1.3-ish based to r1.4. So I will have to take some time to see why it
is broken, but I suspect that it's macro-related, and this is where
something is going wrong:
https://github.com/mozilla/tensorflow/blob/08894f64fc67b7a8031fc68cb838a27009c3e6e6/tensorflow/core/platform/platform.h#L46-L58

See the comment I made about DT_INT64
![:slight_smile:](

[Archived Post]

[JRMeyer]

>>> lissyx
[December 10, 2017, 10:58am]

It's not clear in your latest reply whether you tested with our binaries
or with yours. If it's yours, please re-test with ours. Those should be
with r1.3-based:
https://index.taskcluster.net/v1/task/project.deepspeech.deepspeech.native_client.master.234ff38f743c5591c3ea78404c8f17151f8c559e.arm/artifacts/public/native_client.tar.xz

[Archived Post]

[JRMeyer]

>>> lissyx
[December 10, 2017, 4:42pm]

[ slash fotiDim](
it's likely I did an error when handling the merge of r1.4 TensorFlow.
They use RASPBERRY_PI define to do the same as we did with
__ARM_RPI__. Our build does properly define __ARM_RPI__ but not
RASPBERRY_PI, and the check is against the absence of those defines.
So it means out builds are defining IS_MOBILE_PLATFORM while it should
not. Once tasks in
https://tools.taskcluster.net/groups/XmLsLKXdQ3OTfzfdDQPM3Q gets
completed we can retrigger a build against those artifacts and it should
solve the issue :). I'm on a flight right now between Paris and Boston,
and given the build time of TensorFlow (3h at least) it's likely I won't
be able to handle all of that before I do reach Austin.

[Archived Post]

[JRMeyer]

>>> lissyx
[December 11, 2017, 1:41am]

Okay [ slash fotiDim](
have been able to send a PR on DeepSpeech that uses those now artifacts.
Once
https://tools.taskcluster.net/groups/FbxT3V_YTua3qSRNEwqauQ/tasks/Wnpx0NPjS3G20t76jbl15Q/details
completes, you should be able to download native_client.tar.xz from
the 'Run artifacts' tab and it should work better.

[Archived Post]

[JRMeyer]

>>> lissyx
[December 11, 2017, 2:22am]

[ slash fotiDim](
the proper link
https://queue.taskcluster.net/v1/task/Wnpx0NPjS3G20t76jbl15Q/runs/0/artifacts/public/native_client.tar.xz

[Archived Post]

[JRMeyer]

>>> lissyx
[December 11, 2017, 6:05pm]

So, it looks like I will be able to merge that:

Reproducing your error with current bogus artifact:

piraspberrypi:~/nc_r1.3 $ ./deepspeech ~/tmp/output_graph.pb ~/wav/LDC93S1.wav /tmp/alphabet.txt
Invalid argument: No OpKernel was registered to support Op 'SparseToDense' with these attrs. Registered devices: [CPU], Registered kernels:
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT64]
device='CPU'; T in [DT_STRING]; Tindices in [DT_INT32]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT64]
device='CPU'; T in [DT_BOOL]; Tindices in [DT_INT32]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT64]
device='CPU'; T in [DT_FLOAT]; Tindices in [DT_INT32]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT64]
device='CPU'; T in [DT_INT32]; Tindices in [DT_INT32]

[[Node: SparseToDense = SparseToDense[T=DT_INT64, Tindices=DT_INT64, validate_indices=true](CTCBeamSearchDecoder, CTCBeamSearchDecoder:2, CTCBeamSearchDecoder:1, SparseToDense/default_value)]]
Segmentation fault

Using build I made:

piraspberrypi:/nc_r1.4 $ ./deepspeech ~/tmp/output_graph.pb ~/wav/LDC93S1.wav ~/tmp/alphabet.txt
she had your dark suit in greasy wash water all year

[Archived Post]

[JRMeyer]

>>> fotiDim
[December 11, 2017, 8:50pm]

with the latest binaries you
uploaded I am getting this error:

21.49.34.png.filename}[2862×226 51.9

[Archived Post]

[JRMeyer]

>>> lissyx
[December 11, 2017, 8:53pm]

Would you mind trying with a LDC93S1 sample model ?
https://queue.taskcluster.net/v1/task/HLIgJrzcSgGlMR1Xn3C8fw/runs/0/artifacts/public/output_graph.pb

[Archived Post]

[JRMeyer]

>>> fotiDim
[December 11, 2017, 9:09pm]

Boy you are fast! New error this time...

22.08.33.png.filename}[2122×166 41.5

[Archived Post]

[JRMeyer]

>>> lissyx
[December 11, 2017, 9:09pm]

You passed no model file, only the directory
![:slight_smile:](

[Archived Post]

[JRMeyer]

>>> fotiDim
[December 11, 2017, 9:19pm]

Ooops, my bad. That's what happens when it's late
So no errors this time! Recognition was not accurate though.

22.17.22.png.filename}[2286×148 35.3

[Archived Post]

[JRMeyer]

>>> lissyx
[December 11, 2017, 10:22pm]

Awesome, it decodes :). Bad results might have several causes, but it's
another topic
![:slight_smile:](

[Archived Post]

[JRMeyer]

>>> fotiDim
[December 14, 2017, 8:44am]

shall I open another
discussion for the accuracy or should I wait for the next release first?
Not that I only face the accuracy problem on the Raspberry Pi.

[Archived Post]

[JRMeyer]

>>> lissyx
[December 14, 2017, 2:43pm]

Yes, please open another thread so we do not pollute this one
![:slight_smile:](

[Archived Post]

[JRMeyer]

>>> fotiDim
[January 22, 2018, 9:26pm]



> https://queue.taskcluster.net/v1/task/Wnpx0NPjS3G20t76jbl15Q/runs/0/artifacts/public/native_client.tar.xz

I am giving it another go. I
made a clean install and installed everything from scratch. I am getting
the same error and your link for the updated
binaries
does not work anymore. Can re-upload or even better put them on Github?

[Archived Post]

[JRMeyer]

>>> lissyx
[January 22, 2018, 11:52pm]

This should be good:
https://index.taskcluster.net/v1/task/project.deepspeech.deepspeech.native_client.master.arm/artifacts/public/native_client.tar.xz



[DeepSpeech native client compilation for Asus
Thinkerboard

[Archived Post]

[JRMeyer]

>>> fotiDim
[January 24, 2018, 6:46pm]

I gave it another go with your files. I tried another power supply and I
had the same problems. There must be a fundamental difference with mine
and your setup. Is it possible to export the img from your SD card and I
burn onto my SD?

[next page
→

[Archived Post]