e92a8afae1
updates
2019-07-21 01:05:45 +02:00
deb200f6bf
updates
2019-07-20 15:10:31 +02:00
39f63b7110
updates
2019-07-20 15:04:41 +02:00
4816969933
updates
2019-07-20 14:54:37 +02:00
44b340321f
updates
2019-07-20 13:20:01 +02:00
d6edefa8ab
updates
2019-07-20 01:28:29 +02:00
407a4c481d
updates
2019-07-17 14:16:21 +02:00
33838b558d
updates
2019-07-17 14:14:42 +02:00
153762dec0
updates
2019-07-16 18:58:49 +02:00
64b606a3cd
updates
2019-07-16 18:49:54 +02:00
51d7e460a3
updates
2019-07-16 18:18:08 +02:00
81540b80b9
updates
2019-07-16 18:06:24 +02:00
b459587cb0
updates
2019-07-16 17:56:39 +02:00
813024116b
updates
2019-07-16 17:50:41 +02:00
034d2949b9
updates
2019-07-16 17:43:01 +02:00
09b3670579
updates
2019-07-16 17:35:20 +02:00
8501aed49f
updates
2019-07-15 17:54:31 +02:00
96e25462e8
updates
2019-07-15 17:00:04 +02:00
6509d8e588
updates
2019-07-14 22:28:48 +02:00
9c776b8052
updates
2019-07-14 21:38:55 +02:00
3fc676b28a
updates
2019-07-14 11:29:07 +02:00
831b6e39b6
updates
2019-07-12 17:02:04 +02:00
03c6fe1ffe
updates
2019-07-12 16:10:37 +02:00
0aa9759a90
updates
2019-07-12 15:44:39 +02:00
bb38391342
updates
2019-07-12 14:28:46 +02:00
bd9789aa00
equal layer weights
2019-07-12 12:23:17 +02:00
5886200401
updates
2019-07-12 01:19:32 +02:00
a2909c59f8
updates
2019-07-11 11:57:10 +02:00
b005a17eff
updates
2019-07-11 11:56:46 +02:00
3373006d0e
updates
2019-07-10 22:11:48 +02:00
4f6ef59d92
updates
2019-07-10 20:47:05 +02:00
a9e42a16f1
updates
2019-07-10 19:48:29 +02:00
bb1e551150
updates
2019-07-08 19:26:46 +02:00
0bd763f528
updates
2019-07-08 18:32:31 +02:00
feeaf734f2
updates
2019-07-08 18:04:44 +02:00
da9ec7d12f
updates
2019-07-08 18:00:19 +02:00
60bc2c1fbd
updates
2019-07-08 15:43:46 +02:00
94669fb704
updates
2019-07-08 15:24:20 +02:00
291c3ec9c7
updates
2019-07-08 15:02:20 +02:00
70f6379601
GIoU to default
2019-07-07 23:24:34 +02:00
32a52dfb02
GIoU to default
2019-07-05 12:33:37 +02:00
429bd3b8a9
GIoU to default
2019-07-05 11:41:43 +02:00
b649a95c9a
GIoU to default
2019-07-05 00:36:37 +02:00
abf59f1565
updates
2019-07-04 22:10:46 +02:00
d0eace6cec
updates
2019-07-04 21:34:33 +02:00
109991198c
updates
2019-07-03 16:18:08 +02:00
1e62ee2152
updates
2019-07-03 16:17:46 +02:00
ab141fcc1f
updates
2019-07-03 15:37:04 +02:00
a8cf64af31
updates
2019-07-02 18:21:28 +02:00
ccf757b3ea
changed the criteria for the best weight file ( #356 )
...
* changed the criteria for the best weight file
changed the criteria for the best weight file from loss to mAP
I trained the model on my custom dataset. But I failed to get a good results when I load the weight file that has the lowest loss on test dataset.
I thought that the loss used in YOLO is not proper criteria for detection performance. So I changed the criteria from loss to mAP.
what do you think of this?
* Update train.py
2019-07-02 12:24:18 +02:00
Glenn Jocher
Yonghye Kwon