6c1b87a42e
update google_utils import
2020-06-22 23:00:23 -07:00
7306dadf78
Update README.md
2020-06-22 15:16:10 -07:00
3804578b78
Update README.md
2020-06-22 14:33:47 -07:00
69ff486693
Update README.md
2020-06-22 14:32:05 -07:00
364fcfd7db
PANet update
2020-06-22 14:27:17 -07:00
ef58dac963
update Dockerfile
2020-06-22 10:24:56 -07:00
bbd12c7cfe
detect.py fast bug fix
2020-06-22 10:14:58 -07:00
fc171e2678
check_anchor_order() update
2020-06-21 14:08:59 -07:00
1f1917ef56
remove fast, add merge
2020-06-21 13:37:11 -07:00
e572bb0803
Add plot_results save location to log_dir
2020-06-21 09:36:28 -05:00
24dd150fbd
update torch>=1.4
2020-06-20 11:55:39 -07:00
ba340ed72d
Merge pull request #143 from Lornatang/Fix-multi-GPU-training-errors
...
Fix DDP bug in single process multiple device use cases
2020-06-20 11:10:40 -07:00
024a42f4fd
datasets.py vid_formats updated
2020-06-20 09:53:37 -07:00
5c2cd711df
vid_formats bug fix #146
2020-06-20 09:26:07 -07:00
899f1d4bde
Fix DDP bug in single process multiple device use cases
2020-06-20 13:00:03 +08:00
0a09882e4f
Update issue templates
2020-06-19 16:46:21 -07:00
cdf1eac9f7
Merge pull request #107 from Lornatang/fix-reference-bugs
...
fix refrence bug
2020-06-19 14:51:41 -07:00
458c4d0e0b
Update README.md
2020-06-19 12:14:06 -07:00
34ec87ecf9
Update README.md
2020-06-19 12:13:15 -07:00
d4c6674c98
speeds updated from FP32 to FP16
2020-06-19 12:05:10 -07:00
e249792c2f
update onnx_export.py usage
2020-06-19 10:15:08 -07:00
80b82e8bde
update yolo.py
2020-06-18 19:33:02 -07:00
245bd1d242
update README.md
2020-06-18 12:46:30 -07:00
a3ee0a8954
check_img_size() update
2020-06-18 11:46:04 -07:00
10145833c3
strip_optimizer() default to save FP16 model
2020-06-18 00:16:47 -07:00
cce95e744d
backbone as FP16, save default to FP32
2020-06-18 00:13:18 -07:00
d9b64c27c2
save ckpt in FP16 #119
2020-06-17 22:34:13 -07:00
9fdb0fbacf
AutoAnchor bug fix # 117
2020-06-17 19:51:15 -07:00
c8152c81a6
Syntax fixes
2020-06-17 16:32:13 -05:00
9b7386f603
Add save_dir arg to test.test, use arg as location for saving batch jpgs
2020-06-17 16:08:46 -05:00
945307beba
Add save_dir to plot_lr_scheduler and plot_labels
...
Set save_dir = log_dir in train.py
2020-06-17 16:03:18 -05:00
3b2b330872
Move results.txt from weights/ to log_dir
2020-06-17 15:55:45 -05:00
8b6f5826bc
update README.md
2020-06-17 12:58:01 -07:00
2bfd242fa1
Merge remote-tracking branch 'origin/master'
2020-06-17 12:57:03 -07:00
b7ac446d62
update README.md
2020-06-17 12:56:47 -07:00
ade023cff2
Fix hyp file read in and dict update.
...
Add example of hyp yaml
2020-06-17 10:59:20 -05:00
3263a204ea
Fix get_latest_run to search 'search_dir' recursivly
2020-06-17 10:34:37 -05:00
d34291733b
Fix get_latest_run() to search inside 'weights' subfolders
2020-06-17 10:26:55 -05:00
91de3381e1
Merge pull request #112 from imprashr/patch-1
...
onnx should be 1.6.0
2020-06-17 08:23:35 -07:00
0071b69994
onnx should be 1.6.0
...
for smoothly export model to onnx, onnx should be 1.6.0
2020-06-17 14:15:27 +05:30
2368603484
fix refrence bug
...
In torch==1.5, the import of the API has changed. Although it does not interrupt the operation of the program, it seems to me to be an implicit error and may throw an exception in later versions.
2020-06-17 09:56:26 +08:00
a557b7d924
check_img_size() update
2020-06-16 17:48:01 -07:00
034609414e
AutoAnchor fitness to screen
2020-06-16 17:08:45 -07:00
ef75f7313d
AutoAnchor n, imgsz bug fix
2020-06-16 16:48:01 -07:00
2daa412575
train with multi-gpu half test bug fix #99
2020-06-16 16:28:25 -07:00
d1e5716610
train with multi-gpu half test bug fix #99
2020-06-16 16:22:58 -07:00
1dfc28527f
AutoAnchor BPR to 4 significant figures
2020-06-16 16:19:58 -07:00
8db51c7002
tb_writer bug fix
2020-06-16 16:05:28 -07:00
4052603e1f
AutoAnchor update - improvement check
2020-06-16 15:54:20 -07:00
5f2eeba233
remove old print statements
2020-06-16 17:09:39 -05:00
Glenn Jocher
Alex Stoken
Lornatang
Prashant Rai