b1d385a8de
yolov4-relu.cfg
2020-04-27 21:19:22 -07:00
02ae0e3bbd
reproduce results update
2020-04-27 21:05:19 -07:00
8521c3cff9
cleanup
2020-04-27 15:22:36 -07:00
e9d41bb566
Speed updated
2020-04-27 15:06:26 -07:00
2518868508
MemoryEfficientMish()
2020-04-27 13:51:21 -07:00
3aa347a321
add HardSwish()
2020-04-27 13:08:24 -07:00
692f945819
Merge remote-tracking branch 'origin/master'
2020-04-27 11:20:33 -07:00
f799c15611
result not updated from pycocotools
2020-04-27 11:20:27 -07:00
18702c9608
add tensorboard to requirements ( #1100 )
...
In a clean environment running training fails if tensorboard is not installed e.g.
```
Traceback (most recent call last):
File "/home/josh/miniconda3/envs/ultralytics/lib/python3.7/site-packages/torch/utils/tensorboard/__init__.py", line 2, in <module>
from tensorboard.summary.writer.record_writer import RecordWriter # noqa F401
ModuleNotFoundError: No module named 'tensorboard'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "train.py", line 6, in <module>
from torch.utils.tensorboard import SummaryWriter
File "/home/josh/miniconda3/envs/ultralytics/lib/python3.7/site-packages/torch/utils/tensorboard/__init__.py", line 4, in <module>
raise ImportError('TensorBoard logging requires TensorBoard with Python summary writer installed. '
ImportError: TensorBoard logging requires TensorBoard with Python summary writer installed. This should be available in 1.14 or above.
```
2020-04-27 09:21:34 -07:00
4a4bfb20de
FLOPS verbose=False
2020-04-26 16:31:57 -07:00
a0a3bab9e6
add Mish() support
2020-04-26 16:31:21 -07:00
18d4ebfd12
add Mish() support
2020-04-26 16:25:46 -07:00
11f228eb00
yolov4.cfg from alexeyab/darknet
2020-04-26 16:07:29 -07:00
55757421de
remove future
2020-04-26 14:09:12 -07:00
efbeb283c4
ONNX grid float
2020-04-26 14:01:20 -07:00
3bf0cb9c60
remove tb-nightly
2020-04-26 12:41:15 -07:00
daedfc5487
reduce merge limit to 3000
2020-04-26 11:22:29 -07:00
754a1b5bf8
reduce merge limit to 3000
2020-04-25 21:15:30 -07:00
3554ab07fb
anchor correction
2020-04-24 11:00:01 -07:00
5a8efa5c1d
auto --accumulate
2020-04-23 14:32:28 -07:00
b3dfd89878
scheduler resume bug fix
2020-04-23 10:35:08 -07:00
c29be7f85d
torch >= 1.5
2020-04-22 17:55:23 -07:00
aa854ecaa9
torch >= 1.5
2020-04-22 17:54:56 -07:00
dda0afa22e
onnx export IO layer names update
2020-04-22 16:00:20 -07:00
748f60baae
updated test default img_size 512
2020-04-22 14:32:51 -07:00
345d65d18f
updated train default img_size 320-640
2020-04-22 14:32:05 -07:00
82a12e2c8e
docker train update
2020-04-22 11:38:48 -07:00
7cbac5a3ea
train.py iou_t to 0.20
2020-04-22 11:34:34 -07:00
77b3829d56
check_git_status() to train.py
2020-04-22 11:02:09 -07:00
2f636d5740
.half() bug fix
2020-04-22 10:46:26 -07:00
03c6a2d6fa
cleanup
2020-04-21 12:31:37 -07:00
a5bd0fe567
tensorboard comment=opt.name
2020-04-21 12:19:29 -07:00
4c4f4f4dd4
Merge remote-tracking branch 'origin/master'
2020-04-21 09:14:15 -07:00
6aed6c5fd0
attempt_download() update for '' weights
2020-04-21 09:13:38 -07:00
22a6c441ce
Update README.md
2020-04-21 00:39:06 -07:00
8b45360e28
detect cleanup
2020-04-20 16:47:28 -07:00
cdb69d5929
cfg cleanup
2020-04-20 16:34:00 -07:00
be3f322375
Tensorboard out of try, iou_t to 0.10
2020-04-20 09:57:15 -07:00
accce6b565
git status check bug fix
2020-04-18 18:06:11 -07:00
693c06b26c
bug fix issues/1067
2020-04-18 12:07:44 -07:00
bf1061c146
cleanup
2020-04-16 16:12:23 -07:00
9ea856242f
Merge remote-tracking branch 'origin/master'
2020-04-15 22:03:55 -07:00
c3edf8daf4
move image size report
2020-04-15 22:03:51 -07:00
716e618a18
Update greetings.yml
2020-04-15 13:14:54 -07:00
6566f37cdc
Merge remote-tracking branch 'origin/master'
2020-04-15 12:55:00 -07:00
510eadcfa5
Apex and 'git pull' suggestions
2020-04-15 12:54:56 -07:00
20a094ccb9
Update README.md
2020-04-15 12:25:42 -07:00
b8c3644a18
ONNX export update
2020-04-15 12:12:59 -07:00
628028c617
bias init
2020-04-15 11:50:54 -07:00
a49ea80218
update initialize_weights()
2020-04-14 15:58:32 -07:00
Glenn Jocher
Josh Veitch-Michaelis