udacity / didi-competition Goto Github PK

all my files is correct, but problem

$ sudo ./run-bag_to_kitti.sh -i ~/Data/Didi/Didi-Release-2 -o ~/Data/Didi/output2

Running 'python /python/bag_to_kitti.py' with input dir '/home/elninowang/Data/Didi/Didi-Release-2', output dir '/home/elninowang/Data/Didi/output2', docker image 'udacity-sdc2017-reader'...
Extracting bag info /data/Data/2/1.bag
ERROR bag unindexed: /data/Data/2/1.bag. Run rosbag reindex.
Traceback (most recent call last):
File "/python/bag_to_kitti.py", line 471, in
main()
File "/python/bag_to_kitti.py", line 258, in main
bagsets = find_bagsets(indir, filter_topics=filter_topics, set_per_file=True, metadata_filename='metadata.csv')
File "/python/bag_utils.py", line 169, in find_bagsets
bag_set = BagSet(set_name, [f], filter_topics, metadata_path)
File "/python/bag_utils.py", line 81, in init
self._process_infos(filter_topics)
File "/python/bag_utils.py", line 91, in _process_infos
info = get_bag_info(f)
File "/python/bag_utils.py", line 28, in get_bag_info
if 'start' in info:
TypeError: argument of type 'NoneType' is not iterable

From https://discussions.udacity.com/t/kitti-to-bag-py-code-is-wrong/241269

Regarding bag_to_kitti.get_yaw()

A line between points with nearly equal x components is not parallel to the x-axis, so the early return is incorrect.

https://github.com/hengck23/didi-udacity-2017/

https://github.com/jokla/didi_challenge_ros

I use the script to transfer the data to Kitti.

When running bag_to_kitti.py to obtain the necessary groundtruth tracklets for training, this error is thrown:

1000 images, 1416 messages processed...
Writing done. 1873 images, 2607 messages processed.
Traceback (most recent call last):
File "bag_to_kitti.py", line 378, in
main()
File "bag_to_kitti.py", line 327, in main
cap_rear_gps_interp = interpolate_to_camera(camera_index_df, cap_rear_gps_df, filter_cols=gps_cols)
File "bag_to_kitti.py", line 125, in interpolate_to_camera
merged.interpolate(method='time', inplace=True, limit=100, limit_direction='both')
File "/usr/local/lib/python2.7/dist-packages/pandas/core/generic.py", line 3670, in interpolate
raise TypeError("Cannot interpolate with all NaNs.")
TypeError: Cannot interpolate with all NaNs.

This happens right after extracting all the bags in the input folder, while processing the first .bag file. It's been tested in all folders (1, 2 & 3) from Didi-Dataset 2.

Hello,
I'm writing a bachalor thesis about obstacle detection. I would like to run your code. However I cannot download calibration data. Could you share calibration.tar.gz ? Torrent doesn't work, because no seeders.
I would appreciate your help.
Thank you in advance
Regards
Robert Czwartosz

There appears to be a null byte at the end of the line in
https://github.com/udacity/didi-competition/blob/master/tracklets/python/parse_tracklet.py#L3
it's not showing up in github, but is in the file when I download and open it in sublime

in the file generate_tracklet.py, line 86:
class_id = obj.write_xml(f, class_id, tab_level)

However, the funtion write_xml has no return value,

I tried following the instructions here https://github.com/udacity/didi-competition/blob/master/docs/GettingStarted.md

As per the instructions I downloaded the Didi-Training-Release-1.tar.gz and ran rviz while playing 5mph.bag. In Rviz I could only select base_link or radar as the fixed frame, the instructions request selecting velodyne as the fixed frame, which was not an option. After selecting radar, I tried to add the velodyne point-cloud by topic. After doing this I received the error:

For frame [velodyne]: Frame [velodyne] does not exist

I get the same error if I select base_link as the fixed frame. I'm running ROS Kinetic on Ubuntu 16.04.