Glenn Jocher
|
e5dc942fee
|
updates
|
2019-03-04 17:38:38 +01:00 |
Glenn Jocher
|
3bea4da604
|
updates
|
2019-03-04 17:34:53 +01:00 |
Glenn Jocher
|
65ed0d1122
|
updates
|
2019-03-04 15:46:25 +01:00 |
Glenn Jocher
|
90a20f93e5
|
updates
|
2019-02-26 02:53:11 +01:00 |
Glenn Jocher
|
9e60e97a6c
|
updates
|
2019-02-22 16:24:30 +01:00 |
Glenn Jocher
|
ac22a717f1
|
updates
|
2019-02-22 16:15:20 +01:00 |
Glenn Jocher
|
12e605165e
|
updates
|
2019-02-22 15:05:03 +01:00 |
Glenn Jocher
|
e62736f8a8
|
updates
|
2019-02-21 20:16:58 +01:00 |
Glenn Jocher
|
485321ecb1
|
updates
|
2019-02-21 16:18:11 +01:00 |
Glenn Jocher
|
af853f604c
|
updates
|
2019-02-21 15:57:18 +01:00 |
Glenn Jocher
|
0b971eddff
|
updates
|
2019-02-20 18:41:31 +01:00 |
Glenn Jocher
|
f8c675dbc0
|
updates
|
2019-02-20 17:44:41 +01:00 |
Glenn Jocher
|
a65a383d3a
|
updates
|
2019-02-20 13:00:39 +01:00 |
Glenn Jocher
|
15bba5a345
|
xy and wh losses respectively merged
|
2019-02-19 19:55:33 +01:00 |
Glenn Jocher
|
c828f5459f
|
select GPU0 if multiple available
|
2019-02-16 14:33:52 +01:00 |
Glenn Jocher
|
9706002b71
|
optimize imports
|
2019-02-12 18:05:58 +01:00 |
Glenn Jocher
|
e4e64a9ff6
|
updates
|
2019-02-12 13:50:43 +01:00 |
Glenn Jocher
|
9f145d2aa7
|
updates
|
2019-02-11 22:44:25 +01:00 |
Glenn Jocher
|
e23b1a3d73
|
webcam updates
|
2019-02-11 18:15:51 +01:00 |
Glenn Jocher
|
1ca352b328
|
class labeling corrections
|
2019-02-11 12:44:12 +01:00 |
Glenn Jocher
|
ab2ea5a2f9
|
updates
|
2019-02-10 22:02:55 +01:00 |
Glenn Jocher
|
22dc8c0ea6
|
updates
|
2019-02-10 22:01:53 +01:00 |
Glenn Jocher
|
715c4575bf
|
updates
|
2019-02-10 21:34:15 +01:00 |
Glenn Jocher
|
917f9dd248
|
updates
|
2019-02-10 21:28:27 +01:00 |
Glenn Jocher
|
6f0086103c
|
updates
|
2019-02-10 21:10:50 +01:00 |
Glenn Jocher
|
1cd907c59b
|
updates
|
2019-02-09 19:29:19 +01:00 |
Glenn Jocher
|
be934ba5a5
|
updates
|
2019-02-09 19:26:53 +01:00 |
Glenn Jocher
|
a701374014
|
updates
|
2019-02-09 19:24:51 +01:00 |
Glenn Jocher
|
c2436d8197
|
updates
|
2019-02-08 22:43:05 +01:00 |
Glenn Jocher
|
8b88e50f2f
|
updates
|
2019-02-08 16:50:48 +01:00 |
Glenn Jocher
|
eec0dc7b6c
|
ONNX compatibility updates
|
2018-12-28 20:09:06 +01:00 |
Glenn Jocher
|
bf23be9965
|
updates
|
2018-12-16 15:16:52 +01:00 |
Glenn Jocher
|
18ccd184bf
|
updates
|
2018-12-16 15:16:19 +01:00 |
Glenn Jocher
|
900851200e
|
updates
|
2018-12-15 20:52:35 +01:00 |
Glenn Jocher
|
3c95b5c104
|
updates
|
2018-12-12 17:26:46 +01:00 |
Glenn Jocher
|
b5a2747a6a
|
updates
|
2018-12-12 17:02:37 +01:00 |
Glenn Jocher
|
c591936446
|
updates
|
2018-12-11 21:49:56 +01:00 |
Glenn Jocher
|
3fe3951268
|
updates
|
2018-12-10 13:19:13 +01:00 |
Guillermo García
|
d03ce45da5
|
train.py freeze-darknet53 shortened to freeze and action store_true
Traing with freeze: python train.py --freeze
Train without freeze: python train.py
Note: in the actual version freeze is only for first epoche
|
2018-12-05 16:57:16 +01:00 |
Guillermo García
|
868a116750
|
train.py remove hardcoded weights/ path for weights.
If I want to store my weights in 'weights2' path:
python train.py --weights-path weights2
Default is the same: weights
|
2018-12-05 16:57:16 +01:00 |
Guillermo García
|
9c0c1f23ab
|
scripts: use data config defined class names
Shorten name of --data-config-path argument to --data-config
|
2018-12-05 16:57:16 +01:00 |
Guillermo García
|
89daa407e5
|
train.py report argument as store_true
Default is false: python train.py
If want the report: python train.py --report
|
2018-12-05 16:57:16 +01:00 |
Guillermo García
|
b1fb6fa33d
|
train.py resume argument as store_true
Default is false.
If want to resume, call train.py --resume
|
2018-12-05 16:57:16 +01:00 |
Guillermo García
|
c807c16b79
|
Fix argument parser bad practice
Keep parsing inside __main__ block and call methods with arguments
Add double -- for long argument names (- reserved for shortcuts)
|
2018-12-05 16:57:16 +01:00 |
Guillermo García
|
5a566454f5
|
Extract seed and cuda initialization utils
|
2018-12-05 11:55:27 +01:00 |
Glenn Jocher
|
fd6619d773
|
updates
|
2018-12-03 22:33:25 +01:00 |
Glenn Jocher
|
10cca39934
|
updates
|
2018-12-03 21:08:45 +01:00 |
Glenn Jocher
|
b64620cf75
|
updates
|
2018-12-03 14:12:46 +01:00 |
Glenn Jocher
|
40b536a426
|
updates
|
2018-12-03 14:08:59 +01:00 |
Glenn Jocher
|
5843c41dfc
|
add multi_scale support
|
2018-12-03 14:05:50 +01:00 |
Glenn Jocher
|
af0033c9e9
|
updates
|
2018-11-29 11:59:29 +01:00 |
Glenn Jocher
|
053566b174
|
updates
|
2018-11-28 10:27:55 +01:00 |
Glenn Jocher
|
cc419d88ea
|
updates
|
2018-11-28 10:25:00 +01:00 |
Glenn Jocher
|
5a0575af3a
|
updates
|
2018-11-27 18:43:46 +01:00 |
Glenn Jocher
|
b07ee41867
|
updates
|
2018-11-27 18:14:48 +01:00 |
Glenn Jocher
|
ab9ee6aa9a
|
updates
|
2018-11-23 19:45:39 +01:00 |
Glenn Jocher
|
887ab29c64
|
updates
|
2018-11-22 20:03:09 +01:00 |
Glenn Jocher
|
6f83c321c8
|
updates
|
2018-11-22 20:02:11 +01:00 |
Glenn Jocher
|
b9d87be318
|
updates
|
2018-11-22 14:54:52 +01:00 |
Glenn Jocher
|
db515a4535
|
updates
|
2018-11-22 14:14:19 +01:00 |
Glenn Jocher
|
809667404f
|
updates
|
2018-11-22 13:52:22 +01:00 |
Glenn Jocher
|
4e4b67b3c5
|
updates
|
2018-11-21 18:01:18 +01:00 |
Glenn Jocher
|
a021f97110
|
updates
|
2018-11-15 01:01:04 +01:00 |
Glenn Jocher
|
1ea87c49c4
|
updates
|
2018-11-15 00:57:15 +01:00 |
Glenn Jocher
|
45c5567723
|
mAP recorded during training
|
2018-11-14 15:14:41 +00:00 |
Glenn Jocher
|
4bae1d0f75
|
updates
|
2018-11-09 17:03:26 +01:00 |
Glenn Jocher
|
b1a2735338
|
updates
|
2018-11-09 16:58:32 +01:00 |
Glenn Jocher
|
5177f3e7a0
|
updates
|
2018-11-09 16:48:55 +01:00 |
Glenn Jocher
|
664cbaab09
|
Adam optimizer
|
2018-11-09 16:44:12 +01:00 |
Glenn Jocher
|
46a4de77cb
|
updates
|
2018-11-08 12:29:35 +01:00 |
Glenn Jocher
|
2463030d6c
|
updates
|
2018-11-08 12:28:19 +01:00 |
Glenn Jocher
|
c8e4a19879
|
updates
|
2018-11-08 12:27:14 +01:00 |
Glenn Jocher
|
a6d69cefe0
|
updates
|
2018-11-08 12:26:23 +01:00 |
Glenn Jocher
|
edfad8095d
|
updates
|
2018-11-05 23:34:26 +01:00 |
Glenn Jocher
|
6e5da1ce27
|
updates
|
2018-11-05 23:32:36 +01:00 |
Glenn Jocher
|
19ccb41eaf
|
updates
|
2018-11-05 23:28:10 +01:00 |
Glenn Jocher
|
0096bb4dd5
|
update multi-scale training
|
2018-11-05 23:20:21 +01:00 |
Glenn Jocher
|
77469a5268
|
update multi-scale training
|
2018-11-05 23:17:53 +01:00 |
Glenn Jocher
|
587097affb
|
update LR scheduler
|
2018-11-05 09:20:18 +01:00 |
Glenn Jocher
|
2ccf68cf96
|
add multi_scale train option to argparser
|
2018-11-05 09:08:48 +01:00 |
Glenn Jocher
|
dc7b58bb3c
|
add multi_scale train option to argparser
|
2018-11-05 09:07:15 +01:00 |
Glenn Jocher
|
741626c55b
|
initialize from darknet53
|
2018-10-30 15:20:52 +01:00 |
Glenn Jocher
|
26c52f9485
|
initialize from darknet53
|
2018-10-30 15:18:52 +01:00 |
Glenn Jocher
|
ed0390d0b5
|
initialize from darknet53
|
2018-10-30 14:58:56 +01:00 |
Glenn Jocher
|
332fe002b3
|
rename /checkpoints to /weights
|
2018-10-30 14:58:26 +01:00 |
Glenn Jocher
|
0ae90d0fb7
|
rename /checkpoints to /weights
|
2018-10-27 00:42:34 +02:00 |
Glenn Jocher
|
05f28ab02b
|
-batch_size from 12 to 16
|
2018-10-15 21:05:24 +02:00 |
Glenn Jocher
|
f79e7ffa76
|
updates
|
2018-10-10 16:16:17 +02:00 |
Glenn Jocher
|
d748bedb1d
|
clean up train.py
|
2018-10-09 19:32:42 +02:00 |
Glenn Jocher
|
e7cd5d01c4
|
cleanup train.py
|
2018-10-09 19:28:27 +02:00 |
Glenn Jocher
|
0cc8f2be01
|
clean up train.py
|
2018-10-09 19:22:33 +02:00 |
Glenn Jocher
|
c01b8e6b7c
|
updates
|
2018-10-05 16:38:59 +02:00 |
Glenn Jocher
|
0058431e2e
|
create step lr schedule
|
2018-09-28 14:26:46 +02:00 |
Glenn Jocher
|
208fd77fe4
|
create step lr schedule
|
2018-09-25 01:29:35 +02:00 |
Glenn Jocher
|
6528238953
|
align loss to darknet
|
2018-09-24 21:26:12 +02:00 |
Glenn Jocher
|
396a71001e
|
align loss to darknet
|
2018-09-24 21:25:17 +02:00 |
Glenn Jocher
|
750f528bfe
|
align loss to darknet
|
2018-09-24 03:34:12 +02:00 |
Glenn Jocher
|
313a3f6b0c
|
updates
|
2018-09-24 03:06:04 +02:00 |
Glenn Jocher
|
a722601ef6
|
Adam to SGD with burn-in
|
2018-09-20 18:03:19 +02:00 |
Glenn Jocher
|
1cfde4aba8
|
nGT to nT
|
2018-09-19 04:32:16 +02:00 |