9b11f0c58b
PyTorch Hub models default to CUDA:0 if available ( #2472 )
* PyTorch Hub models default to CUDA:0 if available
* device as string bug fix
3 лет назад
38ff499b26
Update autosplit() with annotated_only option ( #2466 )
* Be able to create dataset from annotated images only
Add the ability to create a dataset/splits only with images that have an annotation file, i.e a .txt file, associated to it. As we talked about this, the absence of a txt file could mean two things:
* either the image wasn't yet labelled by someone,
* either there is no object to detect.
When it's easy to create small datasets, when you have to create datasets with thousands of images (and more coming), it's hard to track where you at and you don't want to wait to have all of them annotated before starting to train. Which means some images would lack txt files and annotations, resulting in label inconsistency as you say in #2313 . By adding the annotated_only argument to the function, people could create, if they want to, datasets/splits only with images that were labelled, for sure.
* Cleanup and update print()
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 лет назад
cd8ed3521d
image weights compatible faster random index generator v2 for mosaic augmentation ( #2383 )
image weights compatible faster random index generator v2 for mosaic augmentation
3 лет назад
a82dce7faa
Fix labels being missed when image extension appears twice in filename ( #2300 )
3 лет назад
7b833e37bf
LoadStreams() frame loss bug fix ( #2222 )
3 лет назад
bdd88e1ed7
YOLOv5 Segmentation Dataloader Updates ( #2188 )
* Update C3 module
* Update C3 module
* Update C3 module
* Update C3 module
* update
* update
* update
* update
* update
* update
* update
* update
* update
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update datasets
* update
* update
* update
* update attempt_downlaod()
* merge
* merge
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* parameterize eps
* comments
* gs-multiple
* update
* max_nms implemented
* Create one_cycle() function
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* GitHub API rate limit fix
* update
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* astuple
* epochs
* update
* update
* ComputeLoss()
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* merge
* merge
* merge
* merge
* update
* update
* update
* update
* commit=tag == tags[-1]
* Update cudnn.benchmark
* update
* update
* update
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* update
* mosaic9
* update
* update
* update
* update
* update
* update
* institute cache versioning
* only display on existing cache
* reverse cache exists booleans
3 лет назад
c9bda112ae
Update utils/datasets.py to support .webp files ( #2174 )
Simply added 'webp' as an image format to the img_formats array so that webp image files can be used as training data.
3 лет назад
e9b3de463a
Unique *.cache filenames fix ( #2134 )
* fix #2121
* Update test.py
* Update train.py
* Update autoanchor.py
* Update datasets.py
* Update log_dataset.py
* Update datasets.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 лет назад
4bdc5a397e
LoadImages() pathlib update ( #2140 )
3 лет назад
73a0669930
Start setup for improved W&B integration ( #1948 )
* Add helper functions for wandb and artifacts
* cleanup
* Reorganize files
* Update wandb_utils.py
* Update log_dataset.py
We can remove this code, as the giou hyp has been deprecated for a while now.
* Reorganize and update dataloader call
* yaml.SafeLoader
* PEP8 reformat
* remove redundant checks
* Add helper functions for wandb and artifacts
* cleanup
* Reorganize files
* Update wandb_utils.py
* Update log_dataset.py
We can remove this code, as the giou hyp has been deprecated for a while now.
* Reorganize and update dataloader call
* yaml.SafeLoader
* PEP8 reformat
* remove redundant checks
* Update util files
* Update wandb_utils.py
* Remove word size
* Change path of labels.zip
* remove unused imports
* remove --rect
* log_dataset.py cleanup
* log_dataset.py cleanup2
* wandb_utils.py cleanup
* remove redundant id_count
* wandb_utils.py cleanup2
* rename cls
* use pathlib for zip
* rename dataloader to dataset
* Change import order
* Remove redundant code
* remove unused import
* remove unused imports
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 лет назад
a18efc3a73
Add variable-stride inference support ( #2091 )
3 лет назад
08d3119e09
Add histogram equalization fcn ( #2049 )
3 лет назад
8fcbe43423
Check im.format during dataset caching ( #2042 )
* Check im.format during dataset caching
* Update datasets.py
3 лет назад
d9212140b3
Add xywhn2xyxy() ( #1983 )
3 лет назад
dd03b20ba5
colorstr() updates ( #1909 )
* W&B ImportError message fix
* colorstr() updates
* colorstr() updates
* colorstr() default to 'blue', 'bold'
* train: magenta
* train: blue
3 лет назад
69be8e738f
YOLOv5 v4.0 Release ( #1837 )
* Update C3 module
* Update C3 module
* Update C3 module
* Update C3 module
* update
* update
* update
* update
* update
* update
* update
* update
* update
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update datasets
* update
* update
* update
* update attempt_downlaod()
* merge
* merge
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* parameterize eps
* comments
* gs-multiple
* update
* max_nms implemented
* Create one_cycle() function
* update
* update
* update
* update
* update
* update
* update
* update study.png
* update study.png
* Update datasets.py
3 лет назад
d5289b54c4
clean_str() function addition ( #1674 )
* clean_str() function addition
* cleanup
* add euro symbol €
* add closing exclamation (spanish)
* cleanup
3 лет назад
54043a9fa4
Streaming --save-txt bug fix ( #1672 )
* Streaming --save-txt bug fix
* cleanup
3 лет назад
cff9263490
f.read().strip() ( #1551 )
4 лет назад
9fa7f9f598
f.read().strip()
4 лет назад
12499f1c01
--image_weights bug fix ( #1524 )
4 лет назад
9728e2b8ae
--image_weights bug fix ( #1524 )
4 лет назад
e9a0ae6f19
Cache bug fix ( #1513 )
* Caching bug fix #1508
* np.zeros((0,5)) x2
4 лет назад
2026d4c5eb
Update caching ( #1496 )
4 лет назад
bde5d9aaaa
Update caching ( #1496 )
4 лет назад
0822cda781
Update caching ( #1496 )
4 лет назад
89c7a5b8dc
Update caching ( #1496 )
4 лет назад
44f42b1589
changed prints to logging in utils/datasets ( #1315 )
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
4 лет назад
354109c54c
Autosplit ( #1488 )
4 лет назад
4798e66fdf
Autosplit ( #1488 )
4 лет назад
8d2d6d2349
Update img2label_paths() ( #1414 )
4 лет назад
548a98a391
Recursive directories dataset capability ( #1408 )
* Recursive directories dataset capability
* x.split('.')[-1]
* f += glob.glob(f"{p}{os.sep}**.*", recursive=True)
* f += glob.glob(str(p / '**.*'), recursive=True)
* remove . from image and vid formats
* .txt to txt
* str(p / '**' / '*.*')
4 лет назад
fe341fa44d
Utils reorganization ( #1392 )
* Utils reorganization
* Add new utils files
* cleanup
* simplify
* reduce datasets.py
* remove evolve.sh
* loadWebcam cleanup
4 лет назад
19e2482458
PyTorch version to screen and cleanup ( #1325 )
* Create flatten_recursive() helper function
* cleanup
* print torch version
4 лет назад
d3e7778151
imap bug fix
4 лет назад
194f16844e
Multi-threaded image caching
4 лет назад
481d46cffb
Improved corruption handling during scan and cache ( #999 )
4 лет назад
d61930e017
Improved corruption handling during scan and cache ( #999 )
4 лет назад
9291daa6f7
fix padding for rectangular inference ( #1165 )
Co-authored-by: swsong <swsong@stratosphere.mobi>
4 лет назад
3b57cb5641
Simplified inference ( #1153 )
4 лет назад
7220cee1d1
mosaic4 bottom left image fix ( #1021 )
fix a bug in load_mosaic
4 лет назад
f1c63e2784
add mosaic and warmup to hyperparameters ( #931 )
4 лет назад
806e75f2b1
self.label_files bug fix ( #958 )
4 лет назад
720645d96a
LoadImagesAndLabels() /images/ to /labels/ fix ( #928 )
4 лет назад
d49c52eee3
_RepeatSampler outside of InfiniteDataLoader
4 лет назад
9c0efdde9f
glob.glob(recursive=True) search ( #917 )
4 лет назад
d3f9bf2bb7
Update datasets.py
4 лет назад
1e15aad6f9
Add InfiniteDataLoader class ( #876 )
* Add InfiniteDataLoader
Only initializes at first epoch. Saves time.
* Moved class to a better location
4 лет назад
82ed33a052
generalize webcam detection with opt.source.isnumeric() (yolov3 #1462 )
4 лет назад
f5da528d28
reformat code
4 лет назад
Glenn Jocher
Yann Defretin
Yonghye Kwon
Iden Craven
Transigent
train255
Ayush Chaurasia
igornishka
Jacobsolawetz
Shiwei Song
haoyuefan
NanoCode012