It might be possible that you have to rename to .gz and then gunzip before use.
No luck with this hack 
“no luck” is not really helpful: you report “issues”, refer to a filename that makes no sense, but you share no error at all. I don’t use macOS, I can’t help you if you don’t give more context.
(post withdrawn by author, will be automatically deleted in 24 hours unless flagged)
I just gave you the proper link above. It seems there’s a regression in the code and the url you report here is wrong. Hence 404.
1 Like
Issue resolved now,
The problem was with safari browser. Whenever I am opening your given URL “https://index.taskcluster.net/v1/task/project.deepspeech.tensorflow.pip.master.osx/artifacts/public/convert_graphdef_memmapped_format” in Safari it is downloading convert_graphdef_memmapped_format file in .dms format. Then I tried the same url into chrome browser and it is downloading convert_graphdef_memmapped_format file in the same format what I was expecting.
(deepspeech_env) Rahuls-MacBook-Pro-2:DeepSpeech-master rahulsharma$ ./convert_graphdef_memmapped_format --in_graph=/Users/rahulsharma/Documents/Tuple_Work/Speech/DeepSpeech-master/output_graph.pb --out_graph=/Users/rahulsharma/Documents/Tuple_Work/Speech/DeepSpeech-master/pbmm_file_generation/output_graph.pbmm
2019-06-14 22:23:45.413515: I tensorflow/contrib/util/convert_graphdef_memmapped_format_lib.cc:171] Converted 23 nodes
@lissyx Thank you so much for the help 
Weird. Could you file an issue for both problems? One for the invalid url and one for mentioning in the docs the safari’s behavior
1 Like
@lissyx I have raised below issue
How to download convert graphdef memmapped format binary file in safari broswer?
Well, I was more thinking about a Github issue …
this link gives me this on chrome:
{
“code”: “ResourceNotFound”,
“message”: “Indexed task not found\n\n—\n\n* method: findArtifactFromTask\n* errorCode: ResourceNotFound\n* statusCode: 404\n* time: 2019-09-29T20:32:01.249Z”,
“requestInfo”: {
“method”: “findArtifactFromTask”,
“params”: {
“0”: “public/convert_graphdef_memmapped_format”,
“indexPath”: “project.deepspeech.tensorflow.pip.master.cpu”,
“name”: “public/convert_graphdef_memmapped_format”
},
“payload”: {},
“time”: “2019-09-29T20:32:01.249Z”
}
}
Yes, it’s normal, it expired. I insist, you should read and use util/taskcluster.py with proper branch argument.
thank you very much for replying.
python util/taskcluster.py --branch v0.5.1 --source tensorflow --artifact convert_graphdef_memmapped_format --target native_client_bin
python util/taskcluster.py --branch r1.13 --source tensorflow --artifact convert_graphdef_memmapped_format --target native_client_bin
Both gives me HTTP Error 404: Not Found
What is wrong in my command?
Nothing, it’s just that artifacts expired.
As soon as https://tools.taskcluster.net/groups/QGJDilIzRnSuPWmKLNnKyw completes, you should be able to get them.
1 Like
thank you.
All tasks were completed in this link, but still couldn’t download convert_graphdef_memmapped_format artifact.
You need to be more specific, it works for me: https://index.taskcluster.net/v1/task/project.deepspeech.tensorflow.pip.r1.13.cpu/artifacts/public/convert_graphdef_memmapped_format
thank you, I was able to download it using the provided link.
this is the url that appears when I run:
python util/taskcluster.py --source "tensorflow" --branch "r1.13" --artifact "convert_graphdef_memmapped_format" --target native_client_bin
deepspeech.native_client instead of tensorflow.pip
1 Like
I think we fixed that bug, but if you reproduce with current master, do not hesitate to file an issue on Github.
1 Like
Hello,
I have successfully downloaded the convert_graphdef_memmapped_format. However, I am getting 0 nodes:
./convert_graphdef_memmapped_format --in_graph=/home/neha/Documents/DeepSpeech/test/export/output_graph.pb --out_graph=/home/neha/Documents/DeepSpeech/output_graph.pbmn
2020-11-07 16:43:40.497728: I tensorflow/contrib/util/convert_graphdef_memmapped_format_lib.cc:171] Converted 0 nodes
Can you please advise. I saw that model has to be frozen, please advise on how to proceed.
Please don’t hijack old posts, start a new one and post info according to: