Comments (8)
Now you can download a trained version of the filter.
from ai-imu-dr.
Can you try it again to download data.zip, I slightly modify the files ?
If you still have this error, you can install the liegroups module, https://github.com/utiasSTARS/liegroups
from ai-imu-dr.
thanks for replying, we have addressed this issue by your suggestion. But another issue occurs............when we plot figures, something goes wrong....could u please solve this problem. we couldn't find a proper solution in internet to tackle this.......could u please modify the source code 'utils_plot.py' in a more general way.
maosongwang@T480s:~/work/ai-imu-dr/src$ python main_kitti.py
IEKF nets loaded
Test filter on sequence: 2011_09_30_drive_0028_extract
Execution time: 12.40 s (sequence time: 538.48 s)
Test filter on sequence: 2011_10_03_drive_0027_extract
Execution time: 10.67 s (sequence time: 471.54 s)
Test filter on sequence: 2011_09_30_drive_0018_extract
Execution time: 6.63 s (sequence time: 288.29 s)
Test filter on sequence: 2011_10_03_drive_0042_extract
Execution time: 2.80 s (sequence time: 121.92 s)
Test filter on sequence: 2011_09_30_drive_0034_extract
Execution time: 2.93 s (sequence time: 127.53 s)
Test filter on sequence: 2011_10_03_drive_0034_extract
Execution time: 10.97 s (sequence time: 484.11 s)
Test filter on sequence: 2011_09_30_drive_0027_extract
Execution time: 2.75 s (sequence time: 115.55 s)
Test filter on sequence: 2011_09_30_drive_0033_extract
Execution time: 3.78 s (sequence time: 165.98 s)
Test filter on sequence: 2011_09_30_drive_0016_extract
Execution time: 0.69 s (sequence time: 29.66 s)
Test filter on sequence: 2011_09_30_drive_0020_extract
Execution time: 2.61 s (sequence time: 115.35 s)
No result for 2011_09_26_drive_0070_extract
Results for: 2011_09_30_drive_0028_extract
Total sequence time: 538.48 s
Traceback (most recent call last):
File "main_kitti.py", line 483, in
launch(KITTIArgs)
File "main_kitti.py", line 34, in launch
results_filter(args, dataset)
File "/home/maosongwang/work/ai-imu-dr/src/utils_plot.py", line 204, in results_filter
fig.savefig(os.path.join(folder_path, fig_name + ".png"))
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/figure.py", line 1834, in savefig
self.canvas.print_figure(fname, **kwargs)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/backends/backend_qt5agg.py", line 185, in print_figure
super(FigureCanvasQTAggBase, self).print_figure(*args, **kwargs)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/backend_bases.py", line 2267, in print_figure
**kwargs)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/backends/backend_agg.py", line 507, in print_png
FigureCanvasAgg.draw(self)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/backends/backend_agg.py", line 430, in draw
self.figure.draw(self.renderer)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/artist.py", line 55, in draw_wrapper
return draw(artist, renderer, *args, **kwargs)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/figure.py", line 1299, in draw
renderer, self, artists, self.suppressComposite)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/image.py", line 138, in _draw_list_compositing_images
a.draw(renderer)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/artist.py", line 55, in draw_wrapper
return draw(artist, renderer, *args, **kwargs)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/axes/_base.py", line 2437, in draw
mimage._draw_list_compositing_images(renderer, self, artists)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/image.py", line 138, in _draw_list_compositing_images
a.draw(renderer)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/artist.py", line 55, in draw_wrapper
return draw(artist, renderer, *args, **kwargs)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/axis.py", line 1147, in draw
self.label.draw(renderer)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/artist.py", line 55, in draw_wrapper
return draw(artist, renderer, *args, **kwargs)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/text.py", line 715, in draw
bbox, info, descent = textobj._get_layout(renderer)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/text.py", line 308, in _get_layout
ismath=False)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/backends/backend_agg.py", line 226, in get_text_width_height_descent
s, fontsize, renderer=self)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/texmanager.py", line 602, in get_text_width_height_descent
dvifile = self.make_dvi(tex, fontsize)
File "/home/maosongwang/anaconda3/lib/python3.6/site-packages/matplotlib/texmanager.py", line 393, in make_dvi
stderr=subprocess.STDOUT)
File "/home/maosongwang/anaconda3/lib/python3.6/subprocess.py", line 336, in check_output
**kwargs).stdout
File "/home/maosongwang/anaconda3/lib/python3.6/subprocess.py", line 403, in run
with Popen(*popenargs, **kwargs) as process:
File "/home/maosongwang/anaconda3/lib/python3.6/subprocess.py", line 709, in init
restore_signals, start_new_session)
File "/home/maosongwang/anaconda3/lib/python3.6/subprocess.py", line 1344, in _execute_child
raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: 'latex': 'latex'
from ai-imu-dr.
It seems to be an error with font from latex. I modify the beginning of the file utils_plot.py
, that is now
import matplotlib
import os
from termcolor import cprint
import matplotlib.pyplot as plt
import numpy as np
from itertools import chain
from utils import *
from utils_torch_filter import TORCHIEKF
Can you try it ?
It is work, you will probably obtain good results with a possible not so trained filter (flat covariance curve). It is normal, I am waiting for updating the temp.zip file.
from ai-imu-dr.
thanks for your replying, we have addressed it by your instructions!! you guys really did an amazing work!
we are looking forward to the new and well trained filter.
from ai-imu-dr.
Can you try it again to download data.zip, I slightly modify the files ?
If you still have this error, you can install the liegroups module, https://github.com/utiasSTARS/liegroups
Having a little trouble importing liegroups into the src folder
from ai-imu-dr.
still have this problem, @mbrossar appreciate!
with data.zip updated, liegroups installed
pickle_dict = pickle.load(file_pi)
ModuleNotFoundError: No module named 'liegroups'
by pdb, I find this info:
${HOME}/anaconda2/envs/python3/lib/python3.6/site-packages/torch/_utils.py(141)_rebuild_tensor_v2()->tensor([[ 0.0...18, 0.1504]])
-> return tensor
(Pdb) n
--Call--
> <frozen importlib._bootstrap>(966)_find_and_load()
(Pdb) l
[EOF]
(Pdb) n
> <frozen importlib._bootstrap>(968)_find_and_load()
(Pdb) n
> <frozen importlib._bootstrap>(969)_find_and_load()
(Pdb)
> <frozen importlib._bootstrap>(970)_find_and_load()
(Pdb)
> <frozen importlib._bootstrap>(971)_find_and_load()
(Pdb)
ModuleNotFoundError: No module named 'liegroups'
> <frozen importlib._bootstrap>(971)_find_and_load()
from ai-imu-dr.
still have this problem, @mbrossar appreciate!
with data.zip updated, liegroups installedpickle_dict = pickle.load(file_pi) ModuleNotFoundError: No module named 'liegroups'
by pdb, I find this info:
${HOME}/anaconda2/envs/python3/lib/python3.6/site-packages/torch/_utils.py(141)_rebuild_tensor_v2()->tensor([[ 0.0...18, 0.1504]]) -> return tensor (Pdb) n --Call-- > <frozen importlib._bootstrap>(966)_find_and_load() (Pdb) l [EOF] (Pdb) n > <frozen importlib._bootstrap>(968)_find_and_load() (Pdb) n > <frozen importlib._bootstrap>(969)_find_and_load() (Pdb) > <frozen importlib._bootstrap>(970)_find_and_load() (Pdb) > <frozen importlib._bootstrap>(971)_find_and_load() (Pdb) ModuleNotFoundError: No module named 'liegroups' > <frozen importlib._bootstrap>(971)_find_and_load()
My fault,ignore this please
restall liegroups solved my trouble
thanks for your sharing!
from ai-imu-dr.
Related Issues (20)
- Issue on the ai-imu-dr with the compiling and running python main file. HOT 7
- Cannot access url for data and train parameters HOT 1
- train parameters size mismatch HOT 37
- Case 2011_10_03_drive_0027_extract - what happened?
- fixing the torch.gesv in utils_torch_filter.py HOT 3
- Train filter failure with error: TypeError: zeros() received an invalid combination of arguments - got (NoneType, int, int), HOT 6
- about sup.pdf HOT 5
- Code's equation not same with the paper HOT 21
- The checkpoint is not same with current model? Fail to load state_dict
- Reason for no end frame for some of the sequences
- Eq. 6 of Brossard's paper: Rotation matrix must be confined in x-y plane. HOT 6
- Issues with the comparison between the estimated position and ground-truth one
- Anyone knows what's the meaning of odometry_benchmark and odometry_benchmark_img? HOT 1
- Eq. 11 of the propagation step different from code (?) HOT 4
- unmatched iekfnets.p from dropbox HOT 5
- Asking for KITTI origin imu data(containing the origin timestamp file) of 09_30_0028
- IEKF nets NOT loaded
- Read data
- testing based on random weights also giving the same results as in paper HOT 9
- Training Loss of the network is fluctuating alot.
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 ai-imu-dr.