Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

About the output after running completion task #14

Open
euzer opened this issue Aug 1, 2019 · 22 comments
Open

About the output after running completion task #14

euzer opened this issue Aug 1, 2019 · 22 comments

Comments

@euzer
Copy link

euzer commented Aug 1, 2019

Hello,
After i run the run_complete_scans_hierarchical.sh, in the vis folder i obtain some .obj files. I opened some of those .obj file with Meshlab, but in the visualisation the points are black :

Capture du 2019-08-01 11-54-39

While the run_complete_scans_hierarchical.sh is running, i got some error on count and count++ not found.

Any Ideas on that? HOw do you visualize the results ?
THank you !
@qiji77
Copy link

qiji77 commented Oct 24, 2019

Hello,
I have the same problem as yours about count.Do you have find a method for this?
And also , I have a problem at complete_scan.py lin325 (ValueError: Can't load save_path when it is None. )
Thank you!

@euzer
Copy link
Author

euzer commented Oct 24, 2019 •
edited
Loading

hi there,
@qiji77 I didn't find the way to solve that problem. Sorry :(
I still got black points

@qiji77
Copy link

qiji77 commented Oct 25, 2019

well,thank you for your reply.
And now,when I run this code complete_scan.py I only got this result(*********__0__pred.tfrecord),not a obj.what should I do to produce obj?
Best wishes！
Thank you!

@qiji77
Copy link

qiji77 commented Oct 25, 2019

Well,I found the cause of the problem.
Now,I can get the result of obj
my email address is [email protected]
I hope I can communicate with you if I can.

@santhu937
Copy link

Traceback (most recent call last):
File "complete_scan.py", line 395, in
tf.app.run(main)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 299, in run
_run_main(main, args)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 250, in _run_main
sys.exit(main(argv))
File "complete_scan.py", line 391, in main
target_semantics)
File "complete_scan.py", line 240, in export_prediction_to_mesh
[None, save_errors, save_errors], [None, save_pred_sem, save_target_sem],
UnboundLocalError: local variable 'save_pred_sem' referenced before assignment

@qiji77 Can u please help me with this problem

@qiji77
Copy link

qiji77 commented Feb 12, 2020 via email

@santhu937
Copy link

santhu937 commented Feb 12, 2020 via email

@santhu937
Copy link

santhu937 commented Apr 6, 2020 via email

@qiji77
Copy link

qiji77 commented Apr 6, 2020 via email

@santhu937
Copy link

santhu937 commented Apr 6, 2020 via email

@santhu937
Copy link

santhu937 commented Apr 6, 2020 via email

@qiji77
Copy link

qiji77 commented Apr 6, 2020 via email

@santhu937
Copy link

santhu937 commented Apr 6, 2020 via email

@qiji77
Copy link

qiji77 commented Apr 6, 2020 via email

@santhu937
Copy link

santhu937 commented Apr 7, 2020 via email

@qiji77
Copy link

qiji77 commented Apr 7, 2020 via email

@santhu937
Copy link

santhu937 commented Apr 7, 2020 via email

@euzer
Copy link
Author

euzer commented Apr 7, 2020

Hi there,
are there some black points somehow in the generated obj files?

@santhu937
Copy link

@euzer no I did not get the black points

@euzer
Copy link
Author

euzer commented Apr 9, 2020 •
edited
Loading

oh okay! thanks for your reply @santhu937
yeah few months ago during my intership, I used scanComplete, but I was getting bad ouput (black points, not enough points in the output point cloud).

@santhu937 Do you know how to create or own tfrecords based your own data?

@Aashish75
Copy link

@qiji77
I am able to run the test code on colab with TF version 1.3 and python2 runtime. I get .tfrecord file for level 3 and level 2 output folders but I am not getting the .obj files, could you please tell me what could be wrong?

@Aashish75
Copy link

This is my output after running the test code.

Processing hierarchy level 3, scene 1 of 1: /content/modelcolab/vox19/e5c91fa85ebb60073d89c6ed56e66593__0_.tfrecords.
2020-04-12 11:32:23.418637: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:32:23.418672: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:32:23.418682: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:32:23.418689: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:32:23.418699: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
sh: 1: matlab: not found
Processing hierarchy level 2, scene 1 of 1: /content/modelcolab/vox9/e5c91fa85ebb60073d89c6ed56e66593__0__.tfrecords.
2020-04-12 11:32:40.374343: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:32:40.374398: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:32:40.374409: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:32:40.374417: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:32:40.374429: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
tcmalloc: large alloc 1954471936 bytes == 0x55e24a902000 @ 0x7fd27223a1e7 0x7fd26698e23f 0x7fd267fc7e74 0x7fd267fd78a5 0x7fd267fd7d2c 0x7fd2680331fc 0x7fd268034225 0x7fd2680cc68c 0x7fd26809ca98 0x7fd26808c4c0 0x7fd268415e02 0x7fd268415092 0x7fd270d4ea50 0x7fd271bfe6db 0x7fd271f3788f
sh: 1: matlab: not found
Processing hierarchy level 1, scene 1 of 1: /content/modelcolab/vox5/e5c91fa85ebb60073d89c6ed56e66593__0__.tfrecords.
2020-04-12 11:34:42.664577: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:34:42.664622: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:34:42.664634: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:34:42.664643: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2020-04-12 11:34:42.664656: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
tcmalloc: large alloc 1266745344 bytes == 0x55bd440ea000 @ 0x7fa91c5d91e7 0x7fa910d2d23f 0x7fa912366e74 0x7fa9123768a5 0x7fa912376d2c 0x7fa9123d21fc 0x7fa9123d3225 0x7fa91246b68c 0x7fa91243ba98 0x7fa91242b4c0 0x7fa9127b4e02 0x7fa9127b4092 0x7fa91b0eda50 0x7fa91bf9d6db 0x7fa91c2d688f
tcmalloc: large alloc 1501388800 bytes == 0x55bd440ea000 @ 0x7fa91c5d91e7 0x7fa910d2d23f 0x7fa912366e74 0x7fa9123768a5 0x7fa912376d2c 0x7fa9123d21fc 0x7fa9123d3225 0x7fa91246b68c 0x7fa91243ba98 0x7fa91242b4c0 0x7fa9127b4e02 0x7fa9127b4092 0x7fa91b0eda50 0x7fa91bf9d6db 0x7fa91c2d688f
tcmalloc: large alloc 1501339648 bytes == 0x55bd9d8c0000 @ 0x7fa91c5d91e7 0x7fa910d2d23f 0x7fa912366e74 0x7fa9123768a5 0x7fa912376d2c 0x7fa9123d21fc 0x7fa9123d3225 0x7fa91246b68c 0x7fa91243ba98 0x7fa91242b4c0 0x7fa9127b4e02 0x7fa9127b4092 0x7fa91b0eda50 0x7fa91bf9d6db 0x7fa91c2d688f
tcmalloc: large alloc 15013167104 bytes == 0x55bd9d8c0000 @ 0x7fa91c5d91e7 0x7fa910d2d23f 0x7fa912366e74 0x7fa9123768a5 0x7fa912376d2c 0x7fa9123d21fc 0x7fa9123d3225 0x7fa91246b68c 0x7fa91243ba98 0x7fa91242b4c0 0x7fa9127b4e02 0x7fa9127b4092 0x7fa91b0eda50 0x7fa91bf9d6db 0x7fa91c2d688f
./run_complete_scans_hierarchical.sh: line 92: 2289 Killed python complete_scan.py --alsologtostderr --base_dir="${HIERARCHY_LEVEL_1_MODEL}" --output_dir_prev="${OUTPUT_FOLDER_2}" --height_input="${HEIGHT_INPUT}" --hierarchy_level="${HIERARCHY_LEVEL}" --num_total_hierarchy_levels="${NUM_HIERARCHY_LEVELS}" --is_base_level="${IS_BASE_LEVEL}" --predict_semantics="${PREDICT_SEMANTICS}" --output_folder="${OUTPUT_FOLDER_1}" --input_scene="${scene}"_

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@santhu937 @Aashish75 @qiji77 @euzer