Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
typos
  • Loading branch information
Russell Buchanan authored Oct 1, 2020
1 parent d0aa4c6 commit bf1091c
Showing 1 changed file with 6 additions and 1 deletion.
7 changes: 6 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -47,14 +47,19 @@ The generation of `data.hdf5` is specified in `gen_fb_data.py`, which requires i

## File formats

### Dataset lists

`test.txt`, `train.txt` and `val.txt` are all the same. Each row is the name of a sequence to be used for one of the purposes of test, train or validate. The name should be the same of the sequence directory for example `seq1` and `seq22` as above.


### Used to generate `data.hdf5`
Timestamps (t) are in miliseconds. Each row corresponds to a single timestamp. All data is delimited by commas.

- `my_timestamps_p.txt` (single file with all timestamps)
- [ t ]
- Note: single column
- `imu_measurements.txt` (Data from IMU)
- [ t, ax_raw, ay_raw, az_raw, wz_raw, wy_raw, wz_raw, ax_calib, ay_calib, az_calib, wz_calib, wy_calib, wz_calib]
- [ t, ax_raw, ay_raw, az_raw, ax_calib, ay_calib, az_calib, wx_raw, wy_raw, wz_raw, wx_calib, wy_calib, wz_calib]
- `evolving_state.txt` (Data from VIO)
- [ t, qw, qx, qy, qz, x, y, z, vx, vy, vz]
- `calib_state.txt` (?)
Expand Down

0 comments on commit bf1091c

Please sign in to comment.