Glenn Jocher
5fac5ad165
Precision-Recall Curve Feature Addition ( #1107 )
* initial commit
* Update general.py
Indent update
* Update general.py
refactor duplicate code
* 200 dpi
4年前
Glenn Jocher
9eae82e3a3
Update stale.yml exempt-issue-labels bug fix ( #1098 )
4年前
NanoCode012
77940c3f42
Remove ignore for git files ( #1099 )
4年前
Frederik
d11504aee1
Remove image open on macos ( #1086 )
* added option to not open on save
* Update detect.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
4年前
Glenn Jocher
5b8cf247af
venv* ignore update
4年前
Glenn Jocher
124f0e8212
torchvision nms bug fix
4年前
Glenn Jocher
66676eb039
init_torch_seeds >> init_seeds bug fix
4年前
Glenn Jocher
883924d9dc
classifier, export, torch seed updates
4年前
Jiacong Fang
c5d2331897
Fix increment_dir to use run_xxx for logdir ( #1058 )
* Fix increment_dir to use run_xxx for logdir
Rerunning train.py with logdir in the form of `run_xxx` causes index slicing in
```
n = max([int(x[len(dir):x.find('_') if '_' in Path(x).name else None]) for x in d]) + 1 # increment
```
to underflow.
* Replace find with rfind
4年前
Glenn Jocher
35fe98543c
Update requirements.txt coremltools==4.0b4
4年前
Mingyu Wang
2d2371d2d1
Update get_voc.sh data download URLs ( #1077 )
4年前
Glenn Jocher
a12698f4c9
Update ci-testing.yml reflecting sys.path additions ( #869 )
* Update ci-testing.yml
* Update yolo.py
* Update ci-testing.yml
* Update export.py
* Update yolo.py
4年前
PetrDvoracek
d55c326dda
export.py folder sys.path addition ( #1052 )
4年前
haoyuefan
7220cee1d1
mosaic4 bottom left image fix ( #1021 )
fix a bug in load_mosaic
4年前
Guilhen
702c4fa53e
adding the configuration to deploy yolov5 in in app engine ( #964 )
* add the configuration to deploy yolov5 in a docker container in app engine on google cloud
* remove the duplicated requirements, place the google app engine files in utils
* remove the unused requirements
Co-authored-by: guilhembau <guilhem@6dbytes.com>
4年前
stone99
b8f656742d
feat: add rtmp support ( #1009 )
* feat: add rtmp support
* Update detect.py
pass tuple to source.startswith()
Co-authored-by: ryan.fu <ryan.fu@aylaasia.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
4年前
Glenn Jocher
4fce0096fa
model.add_nms() method
4年前
Glenn Jocher
2f77cf33f6
.fuse() additional error checking
4年前
Glenn Jocher
89655a84f2
.fuse() gradient introduction bug fix
4年前
Glenn Jocher
c4cb78570c
add NMS to pretrained pytorch hub models
4年前
Glenn Jocher
5a9c5c1d3b
add mosaic and warmup to hyperparameters ( #931 )
4年前
Glenn Jocher
f1c63e2784
add mosaic and warmup to hyperparameters ( #931 )
4年前
Glenn Jocher
806e75f2b1
self.label_files bug fix ( #958 )
4年前
Glenn Jocher
6062bb7dee
print self.yaml['nc'] override update
4年前
Glenn Jocher
a62a45b2dd
prevent testloader caching on --notest
4年前
tomguluson92
35dc935504
remove `nn.Conv2d` in default settings ( #949 )
4年前
Glenn Jocher
c54e39464c
check_file() assert unique
4年前
Glenn Jocher
720645d96a
LoadImagesAndLabels() /images/ to /labels/ fix ( #928 )
4年前
Glenn Jocher
d49c52eee3
_RepeatSampler outside of InfiniteDataLoader
4年前
Glenn Jocher
bb8872ea5f
Dockerfile sudo docker "kill all" bug fix
4年前
Glenn Jocher
cab36f72a8
add .git to .dockerignore
4年前
Glenn Jocher
9c0efdde9f
glob.glob(recursive=True) search ( #917 )
4年前
Glenn Jocher
c8e51812a5
hyp evolution force-autoanchor fix
4年前
Glenn Jocher
c687d5c129
reorganize train initialization steps
4年前
Glenn Jocher
bc1fd13a7a
gsutil cp hyp evolution bug fix ( #876 )
4年前
Glenn Jocher
44cdcc7e0b
hyp['anchors'] evolution update
4年前
Glenn Jocher
ffe9eb4238
remove if platform.system() == 'Darwin' checks
4年前
Glenn Jocher
23a7f29e2d
Update hyp.finetune.yaml on 306 VOC generations result
4年前
Glenn Jocher
0a0675da12
Merge remote-tracking branch 'origin/master'
4年前
Glenn Jocher
354a97e4ef
Create sotabench.py
4年前
NanoCode012
d8274d0434
Fix results_file not renaming ( #903 )
4年前
Glenn Jocher
281d78c105
Update train.py ( #902 )
* Update train.py with simplified ckpt names
* Return default hyps to hyp.scratch.yaml
Leave line commented for future use once mystery of best finetuning hyps to apply becomes clearer.
* Force test_batch*_pred.jpg replot on final epoch
This will allow you to see predictions final testing run after training completes in runs/exp0
4年前
Glenn Jocher
d68179953d
Update export.py
4年前
Naman Gupta
6f3db5e662
Remove autoanchor and class checks on resumed training ( #889 )
* Class frequency not calculated on resuming training
Calculation of class frequency is not needed when resuming training.
Anchors can still be recalculated whether resuming or not.
* Check rank for autoanchor
* Update train.py
no autoanchor checks on resume
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
4年前
tkianai
c5969f79f5
add support for DWConv fuse operation ( #898 )
* the value should be a list to unpacking
* filter the None labels
* update readme to remove apex dependency
* add support for DWConv fuse operation
4年前
Glenn Jocher
d3f9bf2bb7
Update datasets.py
4年前
NanoCode012
901243c780
Fix relative path for VOC download ( #880 )
Cleaned up code
4年前
Glenn Jocher
3e04d20c7d
Merge remote-tracking branch 'origin/master'
4年前
Glenn Jocher
f06e2d518c
opt.image_weights bug fix ( #885 )
4年前
NanoCode012
1e15aad6f9
Add InfiniteDataLoader class ( #876 )
* Add InfiniteDataLoader
Only initializes at first epoch. Saves time.
* Moved class to a better location
4年前