cce95e744d
backbone as FP16, save default to FP32
5 years ago
d9b64c27c2
save ckpt in FP16 #119
5 years ago
9fdb0fbacf
AutoAnchor bug fix # 117
5 years ago
c8152c81a6
Syntax fixes
5 years ago
9b7386f603
Add save_dir arg to test.test, use arg as location for saving batch jpgs
5 years ago
945307beba
Add save_dir to plot_lr_scheduler and plot_labels
...
Set save_dir = log_dir in train.py
5 years ago
3b2b330872
Move results.txt from weights/ to log_dir
5 years ago
8b6f5826bc
update README.md
5 years ago
2bfd242fa1
Merge remote-tracking branch 'origin/master'
5 years ago
b7ac446d62
update README.md
5 years ago
ade023cff2
Fix hyp file read in and dict update.
...
Add example of hyp yaml
5 years ago
3263a204ea
Fix get_latest_run to search 'search_dir' recursivly
5 years ago
d34291733b
Fix get_latest_run() to search inside 'weights' subfolders
5 years ago
91de3381e1
Merge pull request #112 from imprashr/patch-1
...
onnx should be 1.6.0
5 years ago
0071b69994
onnx should be 1.6.0
...
for smoothly export model to onnx, onnx should be 1.6.0
5 years ago
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.
5 years ago
a557b7d924
check_img_size() update
5 years ago
034609414e
AutoAnchor fitness to screen
5 years ago
ef75f7313d
AutoAnchor n, imgsz bug fix
5 years ago
2daa412575
train with multi-gpu half test bug fix #99
5 years ago
d1e5716610
train with multi-gpu half test bug fix #99
5 years ago
1dfc28527f
AutoAnchor BPR to 4 significant figures
5 years ago
8db51c7002
tb_writer bug fix
5 years ago
4052603e1f
AutoAnchor update - improvement check
5 years ago
5f2eeba233
remove old print statements
5 years ago
afe1df385b
dist.destroy_process_group() bug fix
5 years ago
72d06147b2
Multi-GPU disabled in test.py
5 years ago
333f678b37
add update default hyp dict with provided yaml
5 years ago
a448c3bcd7
add logic for resuming and getting hyp for resume run
5 years ago
bafbc65ee3
AutoAnchor bug fix
5 years ago
25e51bcec7
add util function to get most recent last.pt file
...
added logic in train.py __main__ to handle resuming from a run
5 years ago
490f1e7b9c
add save_dir arg to plot_lr_scheduler, default to current dir.
...
Uncomment plot_lr_scheduler in train() and pass log_dir as save location
5 years ago
57a0ae3350
AutoAnchor implementation
5 years ago
4418809cf5
change weights dir (wdir) to be unique to each run, under log_dir
5 years ago
d9f446cd81
add save yaml of opt and hyp to tensorboard log_dir in train()
5 years ago
a85e6d0fc0
add parser arg for hyp yaml file
5 years ago
95c46f7245
Merge pull request #79 from Lornatang/delete-redundant-thrid-party-library
...
Delete redundant thrid party library
5 years ago
5a50491fa1
check_anchors bug fix
5 years ago
05b8ee5ca4
check_anchors() bug fix #102
5 years ago
7c6fd4d670
--verbose bug fix #84
5 years ago
ec81c7b5f2
check_anchors() bug fix #90
5 years ago
e1e3399286
ONNX export bug fix #93
5 years ago
8b26e89006
AutoAnchor bug fix #72
5 years ago
8fa3724072
kmean_anchors() update
5 years ago
bdd9fee841
update fast mode
5 years ago
1c0b6236e3
update fast mode
5 years ago
8b8b792802
There is no need to download extra packages, official bring it with you
...
I submitted it once in your yolov3 project, you seem to accept it? I'm not sure. I'll submit PR again.
5 years ago
0c4b4b8817
Merge remote-tracking branch 'upstream/master'
5 years ago
09c1b96136
Merge branch 'fix-reference-bugs'
5 years ago
db2c3acd3a
updated testing settings, rebalanced towards FP16 latency
5 years ago
Glenn Jocher
Alex Stoken
Prashant Rai
Lornatang