Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity
1,058 Commits 1 Branch 0 Tags 19 MiB
Commit Graph

1058 Commits

Author SHA1 Message Date
Glenn Jocher 7a353a9c70 updates 2019-07-04 14:03:13 +02:00
glenn-jocher 109991198c updates 2019-07-03 16:18:08 +02:00
glenn-jocher 1e62ee2152 updates 2019-07-03 16:17:46 +02:00
glenn-jocher ab141fcc1f updates 2019-07-03 15:37:04 +02:00
glenn-jocher 1d0a4a3ace updates 2019-07-03 14:42:11 +02:00
glenn-jocher a8cf64af31 updates 2019-07-02 18:21:28 +02:00
Yonghye Kwon 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 1fd871abd8 updates 2019-07-01 17:44:42 +02:00
glenn-jocher f43ee6ef94 updates 2019-07-01 17:17:29 +02:00
glenn-jocher cf51cf9c99 updates 2019-07-01 17:14:42 +02:00
glenn-jocher 05358accbb updates 2019-07-01 15:23:30 +02:00
glenn-jocher c4409aa2ed updates 2019-07-01 15:22:22 +02:00
glenn-jocher b0d62e5204 updates 2019-07-01 15:21:06 +02:00
glenn-jocher 5e2b802f68 updates 2019-07-01 14:48:44 +02:00
glenn-jocher 09d065711a updates 2019-07-01 01:27:32 +02:00
glenn-jocher 63036deeb7 updates 2019-07-01 00:41:13 +02:00
glenn-jocher 32f5ea955b updates 2019-06-30 17:47:10 +02:00
glenn-jocher db2674aa31 updates 2019-06-30 17:34:29 +02:00
glenn-jocher 5927d12aa7 Merge remote-tracking branch 'origin/master' 2019-06-30 15:24:43 +02:00
glenn-jocher 388b66dcd0 updates 2019-06-30 15:24:34 +02:00
Glenn Jocher 1990cd8013
Update README.md 2019-06-30 00:38:32 +02:00
Glenn Jocher eeae43c414 updates 2019-06-28 00:38:52 +02:00
Jeremy Hu b202baa31c update parse_model_cfg() (#350) 
Removing the two lines for adding batch_normalize key to convolutional layers causes the parsing of the model to break when parsing it in models.py
 2019-06-28 00:35:24 +02:00
Glenn Jocher c1bb037cbe Merge remote-tracking branch 'origin/master' 2019-06-26 11:28:06 +02:00
Glenn Jocher cbfc5a00e5 updates 2019-06-26 11:27:36 +02:00
Yonghye Kwon 37fe87ccd9 cleanup- delete a variable "yolo_layer_count" (#347) 2019-06-26 11:10:52 +02:00
Glenn Jocher 45540c787f updates 2019-06-25 19:36:11 +02:00
Glenn Jocher 1d76751e1f updates 2019-06-25 12:37:24 +02:00
Glenn Jocher e4cc830690 updates 2019-06-25 12:21:27 +02:00
Glenn Jocher 9a56d97059 updates 2019-06-25 11:54:19 +02:00
Glenn Jocher 2244c72a1b updates 2019-06-25 11:45:38 +02:00
Glenn Jocher 6b222df35d updates 2019-06-24 15:56:20 +02:00
Glenn Jocher d208f006a1 updates 2019-06-24 14:46:00 +02:00
Glenn Jocher a3fcf20385 updates 2019-06-24 14:19:20 +02:00
Glenn Jocher 1827b79647 updates 2019-06-24 14:13:16 +02:00
Glenn Jocher c56516ec11 updates 2019-06-24 13:51:54 +02:00
Glenn Jocher 0005823d1f updates 2019-06-24 13:43:17 +02:00
Glenn Jocher 57b616b8b1 updates 2019-06-23 22:01:11 +02:00
Glenn Jocher 0f2e136c05 updates 2019-06-22 19:21:05 +02:00
Glenn Jocher ef3e1343e2 updates 2019-06-22 15:52:27 +02:00
Glenn Jocher f501a0fc9d updates 2019-06-22 15:50:04 +02:00
Glenn Jocher 1a0385c77d updates 2019-06-21 23:11:24 +02:00
Glenn Jocher 4f7fee45ff updates 2019-06-21 21:27:50 +02:00
Glenn Jocher 5f6c2b3d12 updates 2019-06-21 13:19:23 +02:00
Glenn Jocher 1a9aa30efc updates 2019-06-21 11:57:26 +02:00
Glenn Jocher 3223c0171a updates 2019-06-21 10:58:12 +02:00
Glenn Jocher a7e21b4315 updates 2019-06-21 10:24:06 +02:00
Glenn Jocher 7d7d7a6332 updates 2019-06-21 10:17:29 +02:00
Glenn Jocher a40f421061 updates 2019-06-18 21:34:44 +02:00
Glenn Jocher c3526e0eff updates 2019-06-18 17:35:47 +02:00