ketan-b and Glenn Jocher
9d86b54eb3
Add multi-stream saving feature ( #3864 )
...
* Added the recording feature for multiple streams
Thanks for the very cool repo!!
I was trying to record multiple feeds at the same time, but the current version of the detector only had one video writer and one vid_path!
So the streams were not being saved and only were initialized with one frame and this process didn't record the whole thing.
Fix:
I made a list of `vid_writer` and `vid_path` and the `i` from the loop over the `pred` took care of the writer which need to work!
I hope this helps, Thanks!
* Cleanup list lengths
* batch size variable
* Update datasets.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-07-04 12:55:57 +02:00
Valentin Aliferov and Glenn Jocher
831773f5a2
Add EXIF rotation to YOLOv5 Hub inference ( #3852 )
...
* rotating an image according to its exif tag
* Update common.py
* Update datasets.py
* Update datasets.py
faster
* delete extraneous gpg file
* Update common.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-07-02 13:25:54 +02:00
Glenn Jocher
c6c88dc601
Copy-Paste augmentation for YOLOv5 ( #3845 )
...
* Copy-paste augmentation initial commit
* if any segments
* Add obscuration rejection
* Add copy_paste hyperparameter
* Update comments
2021-07-01 00:35:04 +02:00
Feras Oughali and Glenn Jocher
7d6af69638
Fix LoadStreams() dataloader frame skip issue ( #3833 )
...
* Update datasets.py to read every 4th frame of streams
* Update datasets.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-06-30 12:11:29 +02:00
Glenn Jocher
3213d8713f
Fix for dataset_stats() with updated data.yaml ( #3819 )
...
@KalenMike
2021-06-29 12:44:59 +02:00
Glenn Jocher
f89941711c
NGA xView 2018 Dataset Auto-Download ( #3775 )
...
* update clip_coords for numpy
* uncomment
* cleanup
* Add autosplits
* fix
* cleanup
2021-06-26 00:49:05 +02:00
Yonghye Kwon and Glenn Jocher
374957317a
Add xyxy2xywhn() ( #3765 )
...
* Edit Comments for numpy2torch tensor process
Edit Comments for numpy2torch tensor process
* add xyxy2xywhn
add xyxy2xywhn
* add xyxy2xywhn
* formatting
* pass arguments
pass arguments
* edit comment for xyxy2xywhn()
edit comment for xyxy2xywhn()
* cleanup datasets.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-06-25 11:47:46 +02:00
Yonghye Kwon
417a2f425c
Edit comment ( #3759 )
...
edit comment
2021-06-24 15:57:27 +02:00
Glenn Jocher
9ac7d388a9
Backwards compatible cache version checks ( #3730 )
2021-06-22 13:50:47 +02:00
Glenn Jocher
b83e1a4adc
Fix img2label_paths() order ( #3720 )
...
* Fix `img2label_paths()` order
* fix, 1
2021-06-21 22:50:56 +02:00
Glenn Jocher
fad27c0046
Update DDP for torch.distributed.run with gloo backend ( #3680 )
...
* Update DDP for `torch.distributed.run`
* Add LOCAL_RANK
* remove opt.local_rank
* backend="gloo|nccl"
* print
* print
* debug
* debug
* os.getenv
* gloo
* gloo
* gloo
* cleanup
* fix getenv
* cleanup
* cleanup destroy
* try nccl
* return opt
* add --local_rank
* add timeout
* add init_method
* gloo
* move destroy
* move destroy
* move print(opt) under if RANK
* destroy only RANK 0
* move destroy inside train()
* restore destroy outside train()
* update print(opt)
* cleanup
* nccl
* gloo with 60 second timeout
* update namespace printing
2021-06-19 16:30:25 +02:00
Mai Thanh Minh and Glenn Jocher
bf209f6fe9
Skip HSV augmentation when hyperparameters are [0, 0, 0] ( #3686 )
...
* Create shortcircuit in augment_hsv when hyperparameter are zero
* implement faster opt-in
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-06-19 11:51:21 +02:00
Glenn Jocher
814806c61d
Update cache check ( #3691 )
...
Swapped order of operations for faster first per https://github.com/ultralytics/yolov5/commit/f527704cd32c42bc0bba9cce04601783b8563204#r52362419
2021-06-19 11:22:09 +02:00
Glenn Jocher
f527704cd3
Cache v0.3: improved corrupt image/label reporting ( #3676 )
...
* Cache v0.3: improved corrupt image/label reporting
Fix for https://github.com/ultralytics/yolov5/issues/3656#issuecomment-863660899
* cleanup
2021-06-18 10:21:47 +02:00
Glenn Jocher
9b6dba6207
Update dataset_stats() to list of dicts ( #3657 )
...
* Update `dataset_stats()` to list of dicts
@KalenMike
* Update datasets.py
2021-06-17 13:59:52 +02:00
xiaowk5516 and Glenn Jocher
d808855f77
Assert non-premature end of JPEG images ( #3638 )
...
* premature end of JPEG images
* PEP8 reformat
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-06-16 13:31:26 +02:00
Glenn Jocher
6c0e1d9fd7
Update verify_image_label() ( #3635 )
2021-06-16 11:12:15 +02:00
Glenn Jocher
7d3686a686
Update check_file() ( #3622 )
...
* Update `check_file()`
* Update datasets.py
2021-06-15 13:21:04 +02:00
Glenn Jocher
7a565f130a
Update dataset_stats() ( #3593 )
...
@KalenMike this is a PR to add image filenames and labels to our stats dictionary and to save the dictionary to JSON. Save location is next to the train labels.cache file. The single JSON contains all stats for entire dataset.
Usage example:
```python
from utils.datasets import *
dataset_stats('coco128.yaml', verbose=True)
```
2021-06-12 13:26:41 +02:00
Glenn Jocher
958ab92dc1
Remove opt from create_dataloader()` ( #3552 )
2021-06-09 13:14:56 +02:00
Glenn Jocher
1b5edb6f8e
Update dataset_stats() for HUB ( #3536 )
...
* Update `dataset_stats()` for HUB
Cleanup of b6fdd2e
2021-06-09 10:56:11 +02:00
Glenn Jocher
b6fdd2e5e5
Create dataset_stats() for HUB
2021-06-08 23:09:45 +02:00
Glenn Jocher
8d52c1c5c5
Update datasets.py ( #3531 )
...
Minor updates to https://github.com/ultralytics/yolov5/pull/3505 , inplace accumulation.
2021-06-08 18:36:40 +02:00
Dean Mark and Glenn Jocher
28bff22df8
Use multi-threading in cache_labels ( #3505 )
...
* Use multi threading in cache_labels
* PEP8 reformat
* Add num_threads
* changed ThreadPool.imap_unordered to Pool.imap_unordered
* Remove inplace additions
* Update datasets.py
refactor initial desc
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-06-08 18:00:21 +02:00
Yonghye Kwon
c37f072ba7
Faster HSV augmentation ( #3462 )
...
remove datatype conversion process that can be skipped
2021-06-04 20:02:20 +02:00
Glenn Jocher
8e3b4a0bf3
Update MixUp augmentation alpha=beta=32.0 ( #3455 )
...
Per VOC empirical results https://github.com/ultralytics/yolov5/issues/3380#issuecomment-853001307 by @developer0hye
2021-06-04 12:47:53 +02:00
Glenn Jocher
fdbe527dc0
Revert "cv2.imread(img, -1) for IMREAD_UNCHANGED ( #3379 )" ( #3395 )
...
This reverts commit 21a9607e00
2021-05-31 10:39:00 +02:00
tudoulei and Glenn Jocher
21a9607e00
cv2.imread(img, -1) for IMREAD_UNCHANGED (#3379 )
...
* Update datasets.py
* comment
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-05-29 21:12:01 +02:00
Glenn Jocher
4d4a2b0520
Ignore blank lines in *.txt labels ( #3366 )
...
Fix for https://github.com/ultralytics/yolov5/issues/958#issuecomment-849512083
2021-05-27 14:31:26 +02:00
Glenn Jocher
c6b5bfca85
Updated cache v0.2 with hashlib ( #3350 )
...
* Update cache v0.2 to include parent hash
Possible fix for https://github.com/ultralytics/yolov5/issues/3349
* Update datasets.py
2021-05-26 14:26:52 +02:00
Glenn Jocher
0e2f2cbb51
Update LoadStreams init fallbacks ( #3295 )
2021-05-23 14:55:42 +02:00
Glenn Jocher
683cefead4
YouTube stream ending fix ( #3277 )
...
* YouTube stream ending fix
Properly terminates YouTube streams on video end. Should resolve issues #2769 and #3220 .
* Update datasets.py
2021-05-21 16:51:07 +02:00
Glenn Jocher
13a1c72699
Update datasets.py ( #3216 )
2021-05-17 22:24:26 +02:00
Glenn Jocher
36b0a9e7d0
Add CAP_PROP_FRAME_COUNT for YouTube sources ( #3193 )
2021-05-17 12:27:40 +02:00
Glenn Jocher
abfcf9eb79
Replace print() with logging.info() in trainloader ( #3103 )
...
Might indirectly help #3095 by providing better visibility on source of corruption.
2021-05-10 17:07:16 +02:00
Glenn Jocher
955eea8b96
Make cache saving optional ( #2977 )
2021-04-30 00:56:44 +02:00
JoshSong and Glenn Jocher
5f7d39fede
Cleanup load_image() ( #2871 )
...
* don't resize up in load_image if augmenting
* cleanup
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-04-21 15:50:28 +02:00
Glenn Jocher
aff03be35a
YouTube Bug Fix ( #2818 )
...
Fix for #2810
```shell
python detect.py --source 0
```
introduced by YouTube Livestream Detection PR #2752
2021-04-16 17:58:28 +02:00
Ben Milanko and Glenn Jocher
e2b7bc0b32
YouTube Livestream Detection ( #2752 )
...
* Youtube livestream detection
* dependancy update to auto install pafy
* Remove print
* include youtube_dl in deps
* PEP8 reformat
* youtube url check fix
* reduce lines
* add comment
* update check_requirements
* stream framerate fix
* Update README.md
* cleanup
* PEP8
* remove cap.retrieve() failure code
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com >
2021-04-11 18:53:40 +02:00
zzttqu
1e8ab3f5f2
Add tqdm pbar.close() ( #2644 )
...
When using tqdm, sometimes it can't print in one line and roll to next line.
2021-03-29 12:21:25 +02:00
maxupp and Max Uppenkamp
196bf10603
Add '*.mpo' to supported image formats ( #2615 )
...
Co-authored-by: Max Uppenkamp <max.uppenkamp@inform-software.com >
2021-03-26 12:45:22 +01:00
Glenn Jocher
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
2021-03-14 23:16:17 -07:00
Yann Defretin and Glenn Jocher
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 >
2021-03-14 17:11:27 -07:00
Yonghye Kwon
cd8ed3521d
image weights compatible faster random index generator v2 for mosaic augmentation ( #2383 )
...
image weights compatible faster random index generator v2 for mosaic augmentation
2021-03-05 22:58:26 -08:00
Iden Craven
a82dce7faa
Fix labels being missed when image extension appears twice in filename ( #2300 )
2021-02-25 18:05:38 -08:00
Glenn Jocher
7b833e37bf
LoadStreams() frame loss bug fix ( #2222 )
2021-02-15 11:02:20 -08:00
Glenn Jocher
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
2021-02-11 21:22:45 -08:00
Transigent
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.
2021-02-10 00:16:38 -08:00
train255 and Glenn Jocher
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 >
2021-02-05 11:12:43 -08:00
Glenn Jocher
4bdc5a397e
LoadImages() pathlib update ( #2140 )
2021-02-05 09:06:23 -08:00
