Comments (13)
@DRosemei @Ailce8862 Can you please check if you have successfully loaded the data?
NO
from randla-net.
even iam trying to use pretrained model for S3DIS dataset
correct me if iam wrong
- if iam using pretrained model then i dont have to run these lines
sh jobs_6_fold_cv_s3dis.sh
python utils/6_fold_cv.py - i just run python utils/data_prepare_s3dis.py and i succeded
but when i run python -B main_S3DIS.py --gpu 0 --mode test --test_area 1
i got into below result
Area_1_office_31_KDTree.pkl 7.4 MB loaded in 0.0s
Area_1_hallway_4_KDTree.pkl 0.7 MB loaded in 0.0s
Area_1_office_15_KDTree.pkl 0.9 MB loaded in 0.0s
Preparing reprojected indices for testing
Area_1_hallway_2 done in 0.0s
Area_1_hallway_5 done in 0.0s
Area_1_office_16 done in 0.0s
Area_1_office_18 done in 0.0s
Area_1_office_28 done in 0.0s
Area_1_office_20 done in 0.0s
Area_1_office_22 done in 0.0s
Area_1_hallway_1 done in 0.0s
Area_1_office_1 done in 0.0s
Area_1_office_14 done in 0.0s
Area_1_office_30 done in 0.0s
Area_1_office_7 done in 0.0s
Area_1_office_3 done in 0.0s
Area_1_office_26 done in 0.0s
Area_1_office_13 done in 0.0s
Area_1_office_5 done in 0.0s
Area_1_pantry_1 done in 0.0s
Area_1_office_11 done in 0.0s
Area_1_office_2 done in 0.0s
Area_1_office_9 done in 0.0s
Area_1_office_21 done in 0.0s
Area_1_office_10 done in 0.0s
Area_1_hallway_8 done in 0.0s
Area_1_conferenceRoom_1 done in 0.0s
Area_1_conferenceRoom_2 done in 0.0s
Area_1_hallway_6 done in 0.1s
Area_1_office_19 done in 0.0s
Area_1_WC_1 done in 0.0s
Area_1_office_17 done in 0.0s
Area_1_hallway_3 done in 0.0s
Area_1_hallway_7 done in 0.0s
Area_1_office_12 done in 0.0s
Area_1_office_4 done in 0.0s
Area_1_office_29 done in 0.0s
Area_1_copyRoom_1 done in 0.0s
Area_1_office_23 done in 0.0s
Area_1_office_8 done in 0.0s
Area_1_office_25 done in 0.0s
Area_1_office_27 done in 0.0s
Area_1_office_6 done in 0.0s
Area_1_office_24 done in 0.0s
Area_1_office_31 done in 0.1s
Area_1_hallway_4 done in 0.0s
Area_1_office_15 done in 0.0s
Initiating input pipelines
WARNING:tensorflow:From /home/vikas/RandLA-Net/RandLANet.py:265: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Future major versions of TensorFlow will allow gradients to flow
into the labels input on backprop by default.
See tf.nn.softmax_cross_entropy_with_logits_v2
.
/home/vikas/anaconda3/envs/randlanet/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py:108: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
results/Log_2020-06-22_11-52-29/snapshots
Model restored from results/Log_2020-06-22_11-52-29/snapshots/snap-26001
Killed
process got killed
let me know anyone can help
from randla-net.
Hi @honggesmile, thanks for your interest in our work!
- sh jobs_6_fold_cv_s3dis.sh
But did not generate the test folder containing the ply file.so I can't continue to run the code.
The test folder will be created when you evaluate the performance of the trained model on a specific area, e.g.,
python -B main_S3DIS.py --gpu 0 --mode test --test_area 1
Can you please give me more details about your problem?
from randla-net.
@honggesmile I met the same problm with you. @QingyongHu Could you give some advice? I have generate these train_log, results and log*.txt.
from randla-net.
I have found that this line will create /test folder while it did not worked. It only created results/log*
from randla-net.
I have solved this problem.
I use python -B main_S3DIS.py --gpu 0 --mode test --test_area 1 --model_path results/Log_2020-03-31_07-53-08/snapshots/snap-33501
to test Area1 and test other areas respectively. But I still do not know why it did not work in "jobs_6_fold_cv_s3dis.sh"
from randla-net.
Hi @DRosemei, thanks for your interest in our work.
I have tried to run the code in my pc and it works very well. It is a little bit weird that it cannot generate the test
folder on your computer. I suppose it could be caused by the permissions, but anyway, you have already found the way to make it work.
Good luck!
from randla-net.
@honggesmile Have you generated model like below?
I found that your result path is so weird and it raised an error, "ValueError: attempt to get argmin of an empty sequence".
from randla-net.
@honggesmile Have you generated model like below?
I found that your result path is so weird and it raised an error, "ValueError: attempt to get argmin of an empty sequence".
My running results are the same, but I don’t know how to test the results.Can you tell me?
from randla-net.
@DRosemei @Ailce8862 Can you please check if you have successfully loaded the data?
from randla-net.
Hi, @honggesmile
I've encountered the same issue, my solution is to change:
Line 16 in 3aafa16
into
self.path='data/S3DIS'
, hope it helps:)
First thing is to check whether you have loaded the data successfully, if it has loaded the data, the console will print the following messages:
Preparing reprojected indices for testing
Area_1_office_1 done in 0.0s
Area_1_hallway_2 done in 0.0s
Area_1_office_24 done in 0.0s
Area_1_hallway_6 done in 0.1s
Area_1_office_2 done in 0.0s
Area_1_pantry_1 done in 0.0s
...
from randla-net.
hi @Vikas-Shetty this is warning, I've encountered, it is not the reason to kill your process
from randla-net.
hi @Vikas-Shetty ,i got the testing process killed when i test on semantickitti sequences 13,19 and 21.have you sloved this problem,could you give me some suggestions?
from randla-net.
Related Issues (20)
- s3dis数据集
- How to generate dataset for this?
- The number of the point cloud(.ply) file is double of the number of the .label file
- Best practices for training/validation/testing splits
- No module named 'numpy.distutils._msvccompiler' in numpy.distutils; trying from distutils
- NPM3D中三个测试场景的语义分割结果存在极大差距
- I want train model on custom data like semantic3d, I have .las file but i don't know how to annotated and save in format like semantic3d dataset? HOT 2
- iou=0
- Failed : work_element_count > 0 (0 vs. 0)
- s3dis area1 验证miou不到20% HOT 3
- How to train only with XYZ.
- GPU memory RTX3090 HOT 3
- Import Error
- IOU of some lables is 0.00
- AttributeError: module 'tensorflow' has no attribute 'pyfunc'
- Environment Error HOT 1
- 网络中参数的shape
- 如何分割自己的数据集 HOT 1
- Inquiry Regarding Inference on Unlabeled Data Using RandLA-Net
- Coordinate System for S3DIS
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from randla-net.