Cpt.Captain
52c9547d34
Modify syn data creation to use separate projector calibration data
3 years ago
Cpt.Captain
291cda7391
Update calibration results
3 years ago
Cpt.Captain
9ed0c264f5
Add wandb
3 years ago
Cpt.Captain
3da66347e7
Add wandb, more args, increase learning rate
3 years ago
Cpt.Captain
168516924e
general improvements
3 years ago
Cpt.Captain
7633990c81
Add wandb, make batch and image size configurable, fix some bugs
3 years ago
Cpt.Captain
e3303cf9d4
Add wandb, make batch and image size configurable, fix some bugs, improve supervised loss function, make use of some RL stuff just implemented
3 years ago
Cpt.Captain
b7dbc59c25
Add wandb, make batch and image size configurable, fix some bugs, improve supervised loss function
3 years ago
Cpt.Captain
cebf776714
Add real world dataset
3 years ago
Cpt.Captain
bcb1e2c6ff
Get image size from settings
3 years ago
Cpt.Captain
5202ddfbe9
Add options for batch size, double heads and irl data
3 years ago
Cpt.Captain
db0a8523e5
Remove useless stuf
3 years ago
Cpt.Captain
28ee9003a6
Remove useless stuf
3 years ago
CptCaptain
3f947c9dd2
WIP, buncha stuff that I didn't commit when I wrote it and now I'm afraid of losing something
3 years ago
CptCaptain
a673f807c5
Use pytorch photometric loss instead of old self-rolled
3 years ago
CptCaptain
f193f8d601
Remove unnecessary code from torchext
3 years ago
CptCaptain
efac1b4dea
Update calibration data and sampled pattern
3 years ago
CptCaptain
e0450a57b9
Fix incorrect parenthesis
3 years ago
CptCaptain
9325503b51
use InstanceNorm2d instead of LayerNorm
3 years ago
CptCaptain
1e91784a91
update procam calibration data and sampled pattern
3 years ago
CptCaptain
eb8b31623a
overwrite last found datapoint
...
Since the creation crashes, the data of the last point is often incomplete and causes errors later down the pipeline. Overwriting this should alleviate this issue at a reasonable cost.
3 years ago
CptCaptain
e7a1b59787
fix parenthesis
3 years ago
CptCaptain
0d18f71c6d
allow pickle, otherwise we can't load all data
3 years ago
CptCaptain
d63fedd297
fix off-by-one error
3 years ago
CptCaptain
2d26f7a9d0
update sampled kinect pattern
3 years ago
CptCaptain
8d7890679b
update calibration data
3 years ago
CptCaptain
7060bd5555
add LayerNorm to conv() for testing
3 years ago
CptCaptain
88e4a7e317
add xmltodict
3 years ago
CptCaptain
b250ab4814
update paths
3 years ago
CptCaptain
506a84e2d0
add .gitignore
3 years ago
CptCaptain
119110e125
add sampled pattern to repo
3 years ago
CptCaptain
ba7d63a7c8
Add code for rectification
...
very much wip and not working right as is
3 years ago
CptCaptain
83d202457a
Load camera parameters from calibration xml
3 years ago
CptCaptain
0c8529687b
Add procam calibration data
...
might require different handling once we start evaluating different tilts
3 years ago
CptCaptain
43df77fb9b
Reformat $EVERYTHING
3 years ago
CptCaptain
56f2aa7d5d
Add camera parameters
3 years ago
CptCaptain
42599ee465
Add support for starting syn data generation from specific point
3 years ago
Yiyi Liao
4617525f61
added validation set and pre-trained model; tested on pytorch1.8
4 years ago
Yiyi Liao
bdcc50a88f
fix
5 years ago
Yiyi Liao
14610a160b
Merge branch 'master' of https://github.com/autonomousvision/connecting_the_dots
5 years ago
Yiyi Liao
9ce06a8a0e
fix
5 years ago
Yiyi Liao
d4d5998fe6
Merge pull request #1 from barnjamin/patch-1
...
Update readme.md
5 years ago
Ben Guidarelli
236d6bbb8f
Update readme.md
5 years ago
Yiyi Liao
f5e5c4bd3f
init
6 years ago
Yiyi Liao
26157cbb80
Initial commit
6 years ago