Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

pull updates from original repo (release v5) + reimplement UI #21

Merged
merged 257 commits into from
May 17, 2021
Merged

pull updates from original repo (release v5) + reimplement UI #21

merged 257 commits into from
May 17, 2021
This pull request is big! We’re only showing the most recent 250 commits.

Commits on Jan 18, 2021

  1. Update yolo.py with yaml.SafeLoader (ultralytics#1970)

    @Anon-Artist
    Anon-Artist authored Jan 18, 2021
    Configuration menu
    Copy the full SHA
    4501169 View commit details
    Browse the repository at this point in the history

  2. Update autoanchor.py with yaml.SafeLoader (ultralytics#1971)

    @Anon-Artist
    Anon-Artist authored Jan 18, 2021
    Configuration menu
    Copy the full SHA
    17751b9 View commit details
    Browse the repository at this point in the history

  3. Update train.py with yaml.SafeLoader (ultralytics#1972)

    @Anon-Artist
    Anon-Artist authored Jan 18, 2021
    Configuration menu
    Copy the full SHA
    e9941d5 View commit details
    Browse the repository at this point in the history

  4. check_git_status() asserts (ultralytics#1977)

    @glenn-jocher
    glenn-jocher authored Jan 18, 2021
    Configuration menu
    Copy the full SHA
    b1cf25d View commit details
    Browse the repository at this point in the history

Commits on Jan 19, 2021

  1. Update Dockerfile (ultralytics#1982)

    @glenn-jocher
    glenn-jocher authored Jan 19, 2021
    Configuration menu
    Copy the full SHA
    1ca2d26 View commit details
    Browse the repository at this point in the history

  2. Add xywhn2xyxy() (ultralytics#1983)

    @glenn-jocher
    glenn-jocher authored Jan 19, 2021
    Configuration menu
    Copy the full SHA
    d921214 View commit details
    Browse the repository at this point in the history

Commits on Jan 21, 2021

  1. verbose on final_epoch (ultralytics#1997)

    @glenn-jocher
    glenn-jocher authored Jan 21, 2021
    Configuration menu
    Copy the full SHA
    046c37e View commit details
    Browse the repository at this point in the history

Commits on Jan 22, 2021

  1. check_git_status() Windows fix (ultralytics#2015) 

    * check_git_status() Windows fix

* Update general.py

* Update general.py

* Update general.py

* Update general.py

* Update general.py

* Update general.py
    @glenn-jocher
    glenn-jocher authored Jan 22, 2021
    Configuration menu
    Copy the full SHA
    1445ab2 View commit details
    Browse the repository at this point in the history

  2. Update Dockerfile (ultralytics#2016)

    @glenn-jocher
    glenn-jocher authored Jan 22, 2021
    Configuration menu
    Copy the full SHA
    8dc68fc View commit details
    Browse the repository at this point in the history

  3. Update google_utils.py (ultralytics#2017)

    @glenn-jocher
    glenn-jocher authored Jan 22, 2021
    Configuration menu
    Copy the full SHA
    77fd832 View commit details
    Browse the repository at this point in the history

  4. Update ci-testing.yml (ultralytics#2018)

    @glenn-jocher
    glenn-jocher authored Jan 22, 2021
    Configuration menu
    Copy the full SHA
    85b75d6 View commit details
    Browse the repository at this point in the history

  5. Update inference multiple-counting (ultralytics#2019) 

    * Update inference multiple-counting

* update github check
    @glenn-jocher
    glenn-jocher authored Jan 22, 2021
    Configuration menu
    Copy the full SHA
    aac33f8 View commit details
    Browse the repository at this point in the history

  6. Update general.py check_git_status() fix (ultralytics#2020)

    @glenn-jocher
    glenn-jocher authored Jan 22, 2021
    Configuration menu
    Copy the full SHA
    3b7feea View commit details
    Browse the repository at this point in the history

Commits on Jan 23, 2021

  1. Update autoshape .print() and .save() (ultralytics#2022)

    @glenn-jocher
    glenn-jocher authored Jan 23, 2021
    Configuration menu
    Copy the full SHA
    2fc4760 View commit details
    Browse the repository at this point in the history

  2. Update requirements.txt (ultralytics#2021) 

    * Update requirements.txt

* Update ci-testing.yml

* Update hubconf.py
    @glenn-jocher
    glenn-jocher authored Jan 23, 2021
    Configuration menu
    Copy the full SHA
    9a3da79 View commit details
    Browse the repository at this point in the history

Commits on Jan 24, 2021

  1. PyYAML==5.4.1 (ultralytics#2030)

    @glenn-jocher
    glenn-jocher authored Jan 24, 2021
    Configuration menu
    Copy the full SHA
    c76c607 View commit details
    Browse the repository at this point in the history

  2. Docker pyYAML>=5.3.1 fix (ultralytics#2031)

    @glenn-jocher
    glenn-jocher authored Jan 24, 2021
    Configuration menu
    Copy the full SHA
    3551b07 View commit details
    Browse the repository at this point in the history

Commits on Jan 25, 2021

  1. data-autodownload background tasks (ultralytics#2034)

    @glenn-jocher
    glenn-jocher authored Jan 25, 2021
    Configuration menu
    Copy the full SHA
    a41d910 View commit details
    Browse the repository at this point in the history

Commits on Jan 26, 2021

  1. Check im.format during dataset caching (ultralytics#2042) 

    * Check im.format during dataset caching

* Update datasets.py
    @glenn-jocher
    glenn-jocher authored Jan 26, 2021
    Configuration menu
    Copy the full SHA
    8fcbe43 View commit details
    Browse the repository at this point in the history

  2. Confusion matrix native image-space fix (ultralytics#2046) 

    Make sure the labels and predictions are equally scaled on confusion_matrix.process_batch
    @ramonhollands
    ramonhollands authored Jan 26, 2021
    Configuration menu
    Copy the full SHA
    d68afed View commit details
    Browse the repository at this point in the history

Commits on Jan 27, 2021

  1. Add histogram equalization fcn (ultralytics#2049)

    @glenn-jocher
    glenn-jocher authored Jan 27, 2021
    Configuration menu
    Copy the full SHA
    08d3119 View commit details
    Browse the repository at this point in the history

  2. W&B log epoch (ultralytics#1946) 

    * W&B log epoch

* capitalize

* W&B log epoch

* capitalize

* Update train.py

New try using https://docs.wandb.ai/library/log#incremental-logging

* Update train.py

* Update test.py

* Update train.py

* Update plots.py

* Update train.py

* Update train.py

* label plot step -1

* update

* update

* update

* update

* update

* update

* Update train.py

* Update train.py
    @glenn-jocher
    glenn-jocher authored Jan 27, 2021
    Configuration menu
    Copy the full SHA
    59c21c7 View commit details
    Browse the repository at this point in the history

  3. Add 'exclude' tuple to check_requirements() (ultralytics#2041)

    @glenn-jocher
    glenn-jocher authored Jan 27, 2021
    Configuration menu
    Copy the full SHA
    f59f801 View commit details
    Browse the repository at this point in the history

Commits on Jan 28, 2021

  1. Update run-once lines (ultralytics#2058)

    @glenn-jocher
    glenn-jocher authored Jan 28, 2021
    Configuration menu
    Copy the full SHA
    2a835c7 View commit details
    Browse the repository at this point in the history

  2. Metric-Confidence plots feature addition (ultralytics#2057) 

    * Metric-Confidence plots feature addition

* cleanup

* Metric-Confidence plots feature addition

* cleanup

* Update run-once lines

* cleanup

* save all 4 curves to wandb
    @glenn-jocher
    glenn-jocher authored Jan 28, 2021
    Configuration menu
    Copy the full SHA
    f639e14 View commit details
    Browse the repository at this point in the history

  3. Update to colors.TABLEAU_COLORS (ultralytics#2069)

    @glenn-jocher
    glenn-jocher authored Jan 28, 2021
    Configuration menu
    Copy the full SHA
    630ec06 View commit details
    Browse the repository at this point in the history

Commits on Jan 29, 2021

  1. W&B epoch logging update (ultralytics#2073)

    @glenn-jocher
    glenn-jocher authored Jan 29, 2021
    Configuration menu
    Copy the full SHA
    2acbe96 View commit details
    Browse the repository at this point in the history

  2. GhostConv update (ultralytics#2082)

    @glenn-jocher
    glenn-jocher authored Jan 29, 2021
    Configuration menu
    Copy the full SHA
    6bfa9c2 View commit details
    Browse the repository at this point in the history

  3. Add YOLOv5-P6 models (ultralytics#2083)

    @glenn-jocher
    glenn-jocher authored Jan 29, 2021
    Configuration menu
    Copy the full SHA
    6e6f77b View commit details
    Browse the repository at this point in the history

  4. Update tutorial.ipynb

    @glenn-jocher
    glenn-jocher authored Jan 29, 2021
    Configuration menu
    Copy the full SHA
    64628d6 View commit details
    Browse the repository at this point in the history

  5. Add Amazon Deep Learning AMI environment (ultralytics#2085) 

    * Update greetings.yml

* Update README.md
    @glenn-jocher
    glenn-jocher authored Jan 29, 2021
    Configuration menu
    Copy the full SHA
    170d12e View commit details
    Browse the repository at this point in the history

Commits on Jan 30, 2021

  1. Add Kaggle badge (ultralytics#2090) 

    * Update README.md

* Update greetings.yml

* Created using Colaboratory
    @glenn-jocher
    glenn-jocher authored Jan 30, 2021
    Configuration menu
    Copy the full SHA
    eeb2bbf View commit details
    Browse the repository at this point in the history

  2. Add Kaggle badge (ultralytics#2090)

    @glenn-jocher
    glenn-jocher authored Jan 30, 2021
    Configuration menu
    Copy the full SHA
    aa02b94 View commit details
    Browse the repository at this point in the history

  3. Add variable-stride inference support (ultralytics#2091)

    @glenn-jocher
    glenn-jocher authored Jan 30, 2021
    Configuration menu
    Copy the full SHA
    a18efc3 View commit details
    Browse the repository at this point in the history

Commits on Jan 31, 2021

  1. Update test.py --task speed and study (ultralytics#2099) 

    * Add --speed benchmark

* test range 256 - 1536

* update

* update

* update

* update
    @glenn-jocher
    glenn-jocher authored Jan 31, 2021
    Configuration menu
    Copy the full SHA
    be9edff View commit details
    Browse the repository at this point in the history

Commits on Feb 1, 2021

  1. Update plot_study() (ultralytics#2112)

    @glenn-jocher
    glenn-jocher authored Feb 1, 2021
    Configuration menu
    Copy the full SHA
    9646ca4 View commit details
    Browse the repository at this point in the history

Commits on Feb 2, 2021

  1. Start setup for improved W&B integration (ultralytics#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>
    @AyushExel @glenn-jocher
    AyushExel and glenn-jocher authored Feb 2, 2021
    Configuration menu
    Copy the full SHA
    73a0669 View commit details
    Browse the repository at this point in the history

Commits on Feb 5, 2021

  1. LoadImages() pathlib update (ultralytics#2140)

    @glenn-jocher
    glenn-jocher authored Feb 5, 2021
    Configuration menu
    Copy the full SHA
    4bdc5a3 View commit details
    Browse the repository at this point in the history

  2. Unique *.cache filenames fix (ultralytics#2134) 

    * fix ultralytics#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>
    @train255 @glenn-jocher
    train255 and glenn-jocher authored Feb 5, 2021
    Configuration menu
    Copy the full SHA
    e9b3de4 View commit details
    Browse the repository at this point in the history

Commits on Feb 6, 2021

  1. Update train.py test batch_size (ultralytics#2148) 

    * Update train.py

* Update loss.py
    @glenn-jocher
    glenn-jocher authored Feb 6, 2021
    Configuration menu
    Copy the full SHA
    86897e3 View commit details
    Browse the repository at this point in the history

  2. Update train.py (ultralytics#2149)

    @glenn-jocher
    glenn-jocher authored Feb 6, 2021
    Configuration menu
    Copy the full SHA
    ad839ed View commit details
    Browse the repository at this point in the history

  3. Linear LR scheduler option (ultralytics#2150) 

    * Linear LR scheduler option

* Update train.py
    @glenn-jocher
    glenn-jocher authored Feb 6, 2021
    Configuration menu
    Copy the full SHA
    6b634c6 View commit details
    Browse the repository at this point in the history

Commits on Feb 7, 2021

  1. Update data-autodownload background tasks (ultralytics#2154) 

    * Update get_coco.sh

* Update get_voc.sh
    @glenn-jocher
    glenn-jocher authored Feb 7, 2021
    Configuration menu
    Copy the full SHA
    a5359f6 View commit details
    Browse the repository at this point in the history

Commits on Feb 9, 2021

  1. Update detect.py (ultralytics#2167) 

    Without this cv2.imshow opens a window but nothing is visible
    @ab-101
    ab-101 authored Feb 9, 2021
    Configuration menu
    Copy the full SHA
    c32b0af View commit details
    Browse the repository at this point in the history

Commits on Feb 10, 2021

  1. Update requirements.txt (ultralytics#2173)

    @glenn-jocher
    glenn-jocher authored Feb 10, 2021
    Configuration menu
    Copy the full SHA
    ace3e02 View commit details
    Browse the repository at this point in the history

  2. Update utils/datasets.py to support .webp files (ultralytics#2174) 

    Simply added 'webp' as an image format to the img_formats array so that webp image files can be used as training data.
    @Transigent
    Transigent authored Feb 10, 2021
    Configuration menu
    Copy the full SHA
    c9bda11 View commit details
    Browse the repository at this point in the history

  3. Changed socket port and added timeout (ultralytics#2176)

    @NanoCode012
    NanoCode012 authored Feb 10, 2021
    Configuration menu
    Copy the full SHA
    a5d5f92 View commit details
    Browse the repository at this point in the history

Commits on Feb 11, 2021

  1. PyTorch Hub results.save('path/to/dir') (ultralytics#2179)

    @glenn-jocher
    glenn-jocher authored Feb 11, 2021
    Configuration menu
    Copy the full SHA
    404749a View commit details
    Browse the repository at this point in the history

Commits on Feb 12, 2021

  1. YOLOv5 Segmentation Dataloader Updates (ultralytics#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
    @glenn-jocher
    glenn-jocher authored Feb 12, 2021
    Configuration menu
    Copy the full SHA
    bdd88e1 View commit details
    Browse the repository at this point in the history

  2. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Feb 12, 2021
    Configuration menu
    Copy the full SHA
    17ac94b View commit details
    Browse the repository at this point in the history

  3. YOLOv5 PyTorch Hub results.save() method retains filenames (ultralyti… 

    …cs#2194)

* save results with name

* debug

* save original imgs names

* Update common.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @dan0nchik @glenn-jocher
    dan0nchik and glenn-jocher authored Feb 12, 2021
    Configuration menu
    Copy the full SHA
    3e560e2 View commit details
    Browse the repository at this point in the history

Commits on Feb 15, 2021

  1. TTA augument boxes one pixel shifted in de-flip ud and lr (ultralytic… 

    …s#2219)

* TTA augument boxes one pixel shifted in de-flip ud and lr

* PEP8 reformat

Co-authored-by: Jaap van de Loosdrecht <jaap.van.de.loosdrecht@nhlstenden.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @VdLMV @glenn-jocher
    3 people authored Feb 15, 2021
    Configuration menu
    Copy the full SHA
    3ff783c View commit details
    Browse the repository at this point in the history

  2. LoadStreams() frame loss bug fix (ultralytics#2222)

    @glenn-jocher
    glenn-jocher authored Feb 15, 2021
    Configuration menu
    Copy the full SHA
    7b833e3 View commit details
    Browse the repository at this point in the history

Commits on Feb 16, 2021

  1. Update yolo.py channel array (ultralytics#2223)

    @glenn-jocher
    glenn-jocher authored Feb 16, 2021
    Configuration menu
    Copy the full SHA
    f8464b4 View commit details
    Browse the repository at this point in the history

  2. Add check_imshow() (ultralytics#2231) 

    * Add check_imshow()

* Update general.py

* Update general.py
    @glenn-jocher
    glenn-jocher authored Feb 16, 2021
    Configuration menu
    Copy the full SHA
    26c2e54 View commit details
    Browse the repository at this point in the history

  3. Update CI badge (ultralytics#2230)

    @glenn-jocher
    glenn-jocher authored Feb 16, 2021
    Configuration menu
    Copy the full SHA
    5a40ce6 View commit details
    Browse the repository at this point in the history

  4. Add isdocker() (ultralytics#2232) 

    * Add isdocker()

* Update general.py

* Update general.py
    @glenn-jocher
    glenn-jocher authored Feb 16, 2021
    Configuration menu
    Copy the full SHA
    d2e754b View commit details
    Browse the repository at this point in the history

Commits on Feb 19, 2021

  1. YOLOv5 Hub URL inference bug fix (ultralytics#2250) 

    * Update common.py

* Update common.py

* Update common.py
    @glenn-jocher
    glenn-jocher authored Feb 19, 2021
    Configuration menu
    Copy the full SHA
    9d87307 View commit details
    Browse the repository at this point in the history

  2. Improved hubconf.py CI tests (ultralytics#2251)

    @glenn-jocher
    glenn-jocher authored Feb 19, 2021
    Configuration menu
    Copy the full SHA
    db28ce6 View commit details
    Browse the repository at this point in the history

  3. Unified hub and detect.py box and labels plotting (ultralytics#2243)

    @kinoute
    kinoute authored Feb 19, 2021
    Configuration menu
    Copy the full SHA
    5f42643 View commit details
    Browse the repository at this point in the history

  4. reset head

    @glenn-jocher
    glenn-jocher committed Feb 19, 2021
    Configuration menu
    Copy the full SHA
    47faf95 View commit details
    Browse the repository at this point in the history

  5. Merge remote-tracking branch 'origin/master'

    @glenn-jocher
    glenn-jocher committed Feb 19, 2021
    Configuration menu
    Copy the full SHA
    ab2da5e View commit details
    Browse the repository at this point in the history

  6. Update inference default to multi_label=False (ultralytics#2252) 

    * Update inference default to multi_label=False

* bug fix

* Update plots.py

* Update plots.py
    @glenn-jocher
    glenn-jocher authored Feb 19, 2021
    Configuration menu
    Copy the full SHA
    c09964c View commit details
    Browse the repository at this point in the history

Commits on Feb 20, 2021

  1. Robust objectness loss balancing (ultralytics#2256)

    @glenn-jocher
    glenn-jocher authored Feb 20, 2021
    Configuration menu
    Copy the full SHA
    6f5d6fc View commit details
    Browse the repository at this point in the history

  2. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Feb 20, 2021
    Configuration menu
    Copy the full SHA
    095d2c1 View commit details
    Browse the repository at this point in the history

Commits on Feb 22, 2021

  1. Update minimum stride to 32 (ultralytics#2266)

    @glenn-jocher
    glenn-jocher authored Feb 22, 2021
    Configuration menu
    Copy the full SHA
    e27ca0d View commit details
    Browse the repository at this point in the history

  2. Dynamic ONNX engine generation (ultralytics#2208) 

    * add: dynamic onnx export

* delete: test onnx inference

* fix dynamic output axis

* Code reduction

* fix: dynamic output axes, dynamic input naming

* Remove fixed axes

Co-authored-by: Shivam Swanrkar <ss8464@nyu.edu>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @aditya-dl @shivamswarnkar @glenn-jocher
    3 people authored Feb 22, 2021
    Configuration menu
    Copy the full SHA
    95aefea View commit details
    Browse the repository at this point in the history

Commits on Feb 23, 2021

  1. Update greetings.yml for auto-rebase on PR (ultralytics#2272)

    @glenn-jocher
    glenn-jocher authored Feb 23, 2021
    Configuration menu
    Copy the full SHA
    32dd161 View commit details
    Browse the repository at this point in the history

  2. Update Dockerfile with apt install zip (ultralytics#2274)

    @glenn-jocher
    glenn-jocher authored Feb 23, 2021
    Configuration menu
    Copy the full SHA
    cc79f3a View commit details
    Browse the repository at this point in the history

  3. FLOPS min stride 32 (ultralytics#2276) 

    Signed-off-by: xiaowo1996 <429740343@qq.com>
    @Radleye
    Radleye authored Feb 23, 2021
    Configuration menu
    Copy the full SHA
    83dc1b4 View commit details
    Browse the repository at this point in the history

  4. Update README.md

    @glenn-jocher
    glenn-jocher authored Feb 23, 2021
    Configuration menu
    Copy the full SHA
    7a6870b View commit details
    Browse the repository at this point in the history

Commits on Feb 24, 2021

  1. Amazon AWS EC2 startup and re-startup scripts (ultralytics#2185) 

    * Amazon AWS EC2 startup and re-startup scripts

* Create resume.py

* cleanup
    @glenn-jocher
    glenn-jocher authored Feb 24, 2021
    Configuration menu
    Copy the full SHA
    d5d275b View commit details
    Browse the repository at this point in the history

  2. Amazon AWS EC2 startup and re-startup scripts (ultralytics#2282)

    @glenn-jocher
    glenn-jocher authored Feb 24, 2021
    Configuration menu
    Copy the full SHA
    0070995 View commit details
    Browse the repository at this point in the history

  3. Update train.py (ultralytics#2290) 

    * Update train.py

* Update train.py

* Update train.py

* Update train.py

* Create train.py
    @glenn-jocher
    glenn-jocher authored Feb 24, 2021
    Configuration menu
    Copy the full SHA
    ca5b10b View commit details
    Browse the repository at this point in the history

Commits on Feb 25, 2021

  1. Improved model+EMA checkpointing (ultralytics#2292) 

    * Enhanced model+EMA checkpointing

* update

* bug fix

* bug fix 2

* always save optimizer

* ema half

* remove model.float()

* model half

* carry ema/model in fp32

* rm model.float()

* both to float always

* cleanup

* cleanup
    @glenn-jocher
    glenn-jocher authored Feb 25, 2021
    Configuration menu
    Copy the full SHA
    ec1d849 View commit details
    Browse the repository at this point in the history

  2. Improved model+EMA checkpointing 2 (ultralytics#2295)

    @glenn-jocher
    glenn-jocher authored Feb 25, 2021
    Configuration menu
    Copy the full SHA
    71dd276 View commit details
    Browse the repository at this point in the history

Commits on Feb 26, 2021

  1. Fix labels being missed when image extension appears twice in filename ( 

    ultralytics#2300)
    @idenc
    idenc authored Feb 26, 2021
    Configuration menu
    Copy the full SHA
    a82dce7 View commit details
    Browse the repository at this point in the history

  2. W&B entity support (ultralytics#2298) 

    * W&B entity support

* shorten wandb_entity to entity

Co-authored-by: Jan Hajek <jan.hajek@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @toretak @glenn-jocher
    3 people authored Feb 26, 2021
    Configuration menu
    Copy the full SHA
    efa4946 View commit details
    Browse the repository at this point in the history

  3. Update yolo.py (ultralytics#2120) 

    * Avoid mutable state in Detect

* LoadImages() pathlib update (ultralytics#2140)

* Unique *.cache filenames fix (ultralytics#2134)

* fix ultralytics#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>

* Update train.py test batch_size (ultralytics#2148)

* Update train.py

* Update loss.py

* Update train.py (ultralytics#2149)

* Linear LR scheduler option (ultralytics#2150)

* Linear LR scheduler option

* Update train.py

* Update data-autodownload background tasks (ultralytics#2154)

* Update get_coco.sh

* Update get_voc.sh

* Update detect.py (ultralytics#2167)

Without this cv2.imshow opens a window but nothing is visible

* Update requirements.txt (ultralytics#2173)

* Update utils/datasets.py to support .webp files (ultralytics#2174)

Simply added 'webp' as an image format to the img_formats array so that webp image files can be used as training data.

* Changed socket port and added timeout (ultralytics#2176)

* PyTorch Hub results.save('path/to/dir') (ultralytics#2179)

* YOLOv5 Segmentation Dataloader Updates (ultralytics#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

* Created using Colaboratory

* YOLOv5 PyTorch Hub results.save() method retains filenames (ultralytics#2194)

* save results with name

* debug

* save original imgs names

* Update common.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* TTA augument boxes one pixel shifted in de-flip ud and lr (ultralytics#2219)

* TTA augument boxes one pixel shifted in de-flip ud and lr

* PEP8 reformat

Co-authored-by: Jaap van de Loosdrecht <jaap.van.de.loosdrecht@nhlstenden.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* LoadStreams() frame loss bug fix (ultralytics#2222)

* Update yolo.py channel array (ultralytics#2223)

* Add check_imshow() (ultralytics#2231)

* Add check_imshow()

* Update general.py

* Update general.py

* Update CI badge (ultralytics#2230)

* Add isdocker() (ultralytics#2232)

* Add isdocker()

* Update general.py

* Update general.py

* YOLOv5 Hub URL inference bug fix (ultralytics#2250)

* Update common.py

* Update common.py

* Update common.py

* Improved hubconf.py CI tests (ultralytics#2251)

* Unified hub and detect.py box and labels plotting (ultralytics#2243)

* reset head

* Update inference default to multi_label=False (ultralytics#2252)

* Update inference default to multi_label=False

* bug fix

* Update plots.py

* Update plots.py

* Robust objectness loss balancing (ultralytics#2256)

* Created using Colaboratory

* Update minimum stride to 32 (ultralytics#2266)

* Dynamic ONNX engine generation (ultralytics#2208)

* add: dynamic onnx export

* delete: test onnx inference

* fix dynamic output axis

* Code reduction

* fix: dynamic output axes, dynamic input naming

* Remove fixed axes

Co-authored-by: Shivam Swanrkar <ss8464@nyu.edu>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Update greetings.yml for auto-rebase on PR (ultralytics#2272)

* Update Dockerfile with apt install zip (ultralytics#2274)

* FLOPS min stride 32 (ultralytics#2276)

Signed-off-by: xiaowo1996 <429740343@qq.com>

* Update README.md

* Amazon AWS EC2 startup and re-startup scripts (ultralytics#2185)

* Amazon AWS EC2 startup and re-startup scripts

* Create resume.py

* cleanup

* Amazon AWS EC2 startup and re-startup scripts (ultralytics#2282)

* Update train.py (ultralytics#2290)

* Update train.py

* Update train.py

* Update train.py

* Update train.py

* Create train.py

* Improved model+EMA checkpointing (ultralytics#2292)

* Enhanced model+EMA checkpointing

* update

* bug fix

* bug fix 2

* always save optimizer

* ema half

* remove model.float()

* model half

* carry ema/model in fp32

* rm model.float()

* both to float always

* cleanup

* cleanup

* Improved model+EMA checkpointing 2 (ultralytics#2295)

* Fix labels being missed when image extension appears twice in filename (ultralytics#2300)

* W&B entity support (ultralytics#2298)

* W&B entity support

* shorten wandb_entity to entity

Co-authored-by: Jan Hajek <jan.hajek@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Avoid mutable state in Detect

* Update yolo and remove .to(device)

Co-authored-by: Oleg Boiko <oboiko@chegg.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: train255 <thanhdd.it@gmail.com>
Co-authored-by: ab-101 <56578530+ab-101@users.noreply.github.com>
Co-authored-by: Transigent <wbdsmith@optusnet.com.au>
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
Co-authored-by: Daniel Khromov <danielkhromov@gmail.com>
Co-authored-by: VdLMV <jaap@vdlmv.nl>
Co-authored-by: Jaap van de Loosdrecht <jaap.van.de.loosdrecht@nhlstenden.com>
Co-authored-by: Yann Defretin <kinoute@gmail.com>
Co-authored-by: Aditya Lohia <64709773+aditya-dl@users.noreply.github.com>
Co-authored-by: Shivam Swanrkar <ss8464@nyu.edu>
Co-authored-by: xiaowo1996 <429740343@qq.com>
Co-authored-by: Iden Craven <iden.craven@gmail.com>
Co-authored-by: Jan Hajek <toretak@users.noreply.github.com>
Co-authored-by: Jan Hajek <jan.hajek@gmail.com>
    @olehb @glenn-jocher
    @train255 @ab-101 @Transigent @NanoCode012 @dan0nchik @VdLMV @kinoute @aditya-dl @shivamswarnkar @Radleye @idenc @toretak
    17 people authored Feb 26, 2021
    Configuration menu
    Copy the full SHA
    cbd55da View commit details
    Browse the repository at this point in the history

Commits on Feb 27, 2021

  1. final_epoch EMA bug fix (ultralytics#2317)

    @glenn-jocher
    glenn-jocher authored Feb 27, 2021
    Configuration menu
    Copy the full SHA
    dfeec19 View commit details
    Browse the repository at this point in the history

  2. Update test.py (ultralytics#2319)

    @glenn-jocher
    glenn-jocher authored Feb 27, 2021
    Configuration menu
    Copy the full SHA
    cd30d83 View commit details
    Browse the repository at this point in the history

  3. Update Dockerfile install htop (ultralytics#2320)

    @glenn-jocher
    glenn-jocher authored Feb 27, 2021
    Configuration menu
    Copy the full SHA
    c2026a5 View commit details
    Browse the repository at this point in the history

Commits on Mar 1, 2021

  1. remove TTA 1 pixel offset (ultralytics#2325)

    @glenn-jocher
    glenn-jocher authored Mar 1, 2021
    Configuration menu
    Copy the full SHA
    fd96810 View commit details
    Browse the repository at this point in the history

Commits on Mar 2, 2021

  1. EMA bug fix 2 (ultralytics#2330) 

    * EMA bug fix 2

* update
    @glenn-jocher
    glenn-jocher authored Mar 2, 2021
    Configuration menu
    Copy the full SHA
    fab5085 View commit details
    Browse the repository at this point in the history

  2. FROM nvcr.io/nvidia/pytorch:21.02-py3 (ultralytics#2341)

    @glenn-jocher
    glenn-jocher authored Mar 2, 2021
    Configuration menu
    Copy the full SHA
    ab86cec View commit details
    Browse the repository at this point in the history

Commits on Mar 3, 2021

  1. Confusion matrix background axis swap (ultralytics#2114)

    @rbavery
    rbavery authored Mar 3, 2021
    Configuration menu
    Copy the full SHA
    2c56ad5 View commit details
    Browse the repository at this point in the history

  2. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Mar 3, 2021
    Configuration menu
    Copy the full SHA
    fe6ebb9 View commit details
    Browse the repository at this point in the history

  3. Anchor override (ultralytics#2350)

    @glenn-jocher
    glenn-jocher authored Mar 3, 2021
    Configuration menu
    Copy the full SHA
    a3ecf0f View commit details
    Browse the repository at this point in the history

Commits on Mar 4, 2021

  1. Resume with custom anchors fix (ultralytics#2361) 

    * Resume with custom anchors fix

* Update train.py
    @glenn-jocher
    glenn-jocher authored Mar 4, 2021
    Configuration menu
    Copy the full SHA
    e931b9d View commit details
    Browse the repository at this point in the history

Commits on Mar 5, 2021

  1. Faster random index generator for mosaic augmentation (ultralytics#2345) 

    * faster random index generator for mosaic augementation

We don't need to access list to generate random index

It makes augmentation slower.

* Update datasets.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @developer0hye @glenn-jocher
    developer0hye and glenn-jocher authored Mar 5, 2021
    Configuration menu
    Copy the full SHA
    300d518 View commit details
    Browse the repository at this point in the history

  2. --no-cache notebook (ultralytics#2381)

    @glenn-jocher
    glenn-jocher authored Mar 5, 2021
    Configuration menu
    Copy the full SHA
    692e1f3 View commit details
    Browse the repository at this point in the history

  3. ENV HOME=/usr/src/app (ultralytics#2382) 

    Set HOME environment variable per Binder requirements. 
https://github.com/binder-examples/minimal-dockerfile
    @glenn-jocher
    glenn-jocher authored Mar 5, 2021
    Configuration menu
    Copy the full SHA
    c64fe21 View commit details
    Browse the repository at this point in the history

Commits on Mar 6, 2021

  1. image weights compatible faster random index generator v2 for mosaic … 

    …augmentation (ultralytics#2383)

image weights compatible faster random index generator v2 for mosaic augmentation
    @developer0hye
    developer0hye authored Mar 6, 2021
    Configuration menu
    Copy the full SHA
    cd8ed35 View commit details
    Browse the repository at this point in the history

  2. GPU export options (ultralytics#2297) 

    * option for skip last layer and cuda export support

* added parameter device

* fix import

* cleanup 1

* cleanup 2

* opt-in grid

--grid will export with grid computation, default export will skip grid (same as current)

* default --device cpu

GPU export causes ONNX and CoreML errors.

Co-authored-by: Jan Hajek <jan.hajek@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @toretak @glenn-jocher
    3 people authored Mar 6, 2021
    Configuration menu
    Copy the full SHA
    7a0a81f View commit details
    Browse the repository at this point in the history

  3. bbox_iou() stability and speed improvements (ultralytics#2385)

    @glenn-jocher
    glenn-jocher authored Mar 6, 2021
    Configuration menu
    Copy the full SHA
    ba18528 View commit details
    Browse the repository at this point in the history

Commits on Mar 8, 2021

  1. AWS wait && echo "All tasks done." (ultralytics#2391)

    @glenn-jocher
    glenn-jocher authored Mar 8, 2021
    Configuration menu
    Copy the full SHA
    7c2c957 View commit details
    Browse the repository at this point in the history

  2. GCP sudo docker userdata.sh (ultralytics#2393) 

    * GCP sudo docker

* cleanup
    @glenn-jocher
    glenn-jocher authored Mar 8, 2021
    Configuration menu
    Copy the full SHA
    e8a2b83 View commit details
    Browse the repository at this point in the history

Commits on Mar 10, 2021

  1. CVPR 2021 Argoverse-HD dataset autodownload support (ultralytics#2400) 

    * added argoverse-download ability

* bugfix

* add support for Argoverse dataset

* Refactored code

* renamed to argoverse-HD

* unzip -q and YOLOv5

small cleanup items

* add image counts

Co-authored-by: Kartikeya Sharma <kartikes@trinity.vision.cs.cmu.edu>
Co-authored-by: Kartikeya Sharma <kartikes@trinity-0-32.eth>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @karthiksharma98 @glenn-jocher
    4 people authored Mar 10, 2021
    Configuration menu
    Copy the full SHA
    c51dfec View commit details
    Browse the repository at this point in the history

  2. CVPR 2021 Argoverse-HD autodownload fix (ultralytics#2418)

    @glenn-jocher
    glenn-jocher authored Mar 10, 2021
    Configuration menu
    Copy the full SHA
    d5ca8ca View commit details
    Browse the repository at this point in the history

  3. DDP after autoanchor reorder (ultralytics#2421)

    @glenn-jocher
    glenn-jocher authored Mar 10, 2021
    Configuration menu
    Copy the full SHA
    886f1c0 View commit details
    Browse the repository at this point in the history

Commits on Mar 12, 2021

  1. Integer printout (ultralytics#2450) 

    * Integer printout

* test.py 'Labels'

* Update train.py
    @glenn-jocher
    glenn-jocher authored Mar 12, 2021
    Configuration menu
    Copy the full SHA
    f01f322 View commit details
    Browse the repository at this point in the history

Commits on Mar 13, 2021

  1. Update test.py --task train val study (ultralytics#2453) 

    * Update test.py --task train val study

* update argparser --task
    @glenn-jocher
    glenn-jocher authored Mar 13, 2021
    Configuration menu
    Copy the full SHA
    f419721 View commit details
    Browse the repository at this point in the history

  2. labels.jpg class names (ultralytics#2454) 

    * labels.png class names

* fontsize=10
    @glenn-jocher
    glenn-jocher authored Mar 13, 2021
    Configuration menu
    Copy the full SHA
    08d4918 View commit details
    Browse the repository at this point in the history

  3. CVPR 2021 Argoverse-HD autodownload curl (ultralytics#2455) 

    curl preferred over wget for slightly better cross platform compatibility (i.e. out of the box macos compatible).
    @glenn-jocher
    glenn-jocher authored Mar 13, 2021
    Configuration menu
    Copy the full SHA
    747c265 View commit details
    Browse the repository at this point in the history

Commits on Mar 14, 2021

  1. Add autoShape() speed profiling (ultralytics#2459) 

    * Add autoShape() speed profiling

* Update common.py

* Create README.md

* Update hubconf.py

* cleanuip
    @glenn-jocher
    glenn-jocher authored Mar 14, 2021
    Configuration menu
    Copy the full SHA
    569757e View commit details
    Browse the repository at this point in the history

  2. autoShape() speed profiling update (ultralytics#2460)

    @glenn-jocher
    glenn-jocher authored Mar 14, 2021
    Configuration menu
    Copy the full SHA
    f813f6d View commit details
    Browse the repository at this point in the history

  3. Update tutorial.ipynb

    @glenn-jocher
    glenn-jocher authored Mar 14, 2021
    Configuration menu
    Copy the full SHA
    20d879d View commit details
    Browse the repository at this point in the history

  4. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Mar 14, 2021
    Configuration menu
    Copy the full SHA
    6f718ce View commit details
    Browse the repository at this point in the history

Commits on Mar 15, 2021

  1. Update autosplit() with annotated_only option (ultralytics#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 ultralytics#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>
    @kinoute @glenn-jocher
    kinoute and glenn-jocher authored Mar 15, 2021
    Configuration menu
    Copy the full SHA
    38ff499 View commit details
    Browse the repository at this point in the history

  2. Scipy kmeans-robust autoanchor update (ultralytics#2470) 

    Fix for ultralytics#2394
    @glenn-jocher
    glenn-jocher authored Mar 15, 2021
    Configuration menu
    Copy the full SHA
    2d41e70 View commit details
    Browse the repository at this point in the history

  3. PyTorch Hub models default to CUDA:0 if available (ultralytics#2472) 

    * PyTorch Hub models default to CUDA:0 if available

* device as string bug fix
    @glenn-jocher
    glenn-jocher authored Mar 15, 2021
    Configuration menu
    Copy the full SHA
    9b11f0c View commit details
    Browse the repository at this point in the history

  4. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Mar 15, 2021
    Configuration menu
    Copy the full SHA
    ed2c742 View commit details
    Browse the repository at this point in the history

Commits on Mar 22, 2021

  1. Improved W&B integration (ultralytics#2125) 

    * Init Commit

* new wandb integration

* Update

* Use data_dict in test

* Updates

* Update: scope of log_img

* Update: scope of log_img

* Update

* Update: Fix logging conditions

* Add tqdm bar, support for .txt dataset format

* Improve Result table Logger

* Init Commit

* new wandb integration

* Update

* Use data_dict in test

* Updates

* Update: scope of log_img

* Update: scope of log_img

* Update

* Update: Fix logging conditions

* Add tqdm bar, support for .txt dataset format

* Improve Result table Logger

* Add dataset creation in training script

* Change scope: self.wandb_run

* Add wandb-artifact:// natively

you can now use --resume with wandb run links

* Add suuport for logging dataset while training

* Cleanup

* Fix: Merge conflict

* Fix: CI tests

* Automatically use wandb config

* Fix: Resume

* Fix: CI

* Enhance: Using val_table

* More resume enhancement

* FIX : CI

* Add alias

* Get useful opt config data

* train.py cleanup

* Cleanup train.py

* more cleanup

* Cleanup| CI fix

* Reformat using PEP8

* FIX:CI

* rebase

* remove uneccesary changes

* remove uneccesary changes

* remove uneccesary changes

* remove unecessary chage from test.py

* FIX: resume from local checkpoint

* FIX:resume

* FIX:resume

* Reformat

* Performance improvement

* Fix local resume

* Fix local resume

* FIX:CI

* Fix: CI

* Imporve image logging

* (:(:Redo CI tests:):)

* Remember epochs when resuming

* Remember epochs when resuming

* Update DDP location

Potential fix for ultralytics#2405

* PEP8 reformat

* 0.25 confidence threshold

* reset train.py plots syntax to previous

* reset epochs completed syntax to previous

* reset space to previous

* remove brackets

* reset comment to previous

* Update: is_coco check, remove unused code

* Remove redundant print statement

* Remove wandb imports

* remove dsviz logger from test.py

* Remove redundant change from test.py

* remove redundant changes from train.py

* reformat and improvements

* Fix typo

* Add tqdm tqdm progress when scanning files, naming improvements

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @AyushExel @glenn-jocher
    AyushExel and glenn-jocher authored Mar 22, 2021
    Configuration menu
    Copy the full SHA
    e8fc97a View commit details
    Browse the repository at this point in the history

Commits on Mar 23, 2021

  1. Update Detections() times=None (ultralytics#2570) 

    Fix for results.tolist() method breaking after YOLOv5 Hub profiling PRshttps://github.com/ultralytics/pull/2460 ultralytics#2459 and
    @glenn-jocher
    glenn-jocher authored Mar 23, 2021
    Configuration menu
    Copy the full SHA
    1c132a1 View commit details
    Browse the repository at this point in the history

  2. check_requirements() exclude pycocotools, thop (ultralytics#2571) 

    Exclude non-critical packages from dependency checks in detect.py. pycocotools and thop in particular are not required for inference.

Issue first raised in ultralytics#1944 and also raised in ultralytics#2556
    @glenn-jocher
    glenn-jocher authored Mar 23, 2021
    Configuration menu
    Copy the full SHA
    0d891c6 View commit details
    Browse the repository at this point in the history

  3. W&B DDP fix (ultralytics#2574)

    @AyushExel
    AyushExel authored Mar 23, 2021
    Configuration menu
    Copy the full SHA
    1bf9365 View commit details
    Browse the repository at this point in the history

Commits on Mar 24, 2021

  1. Enhanced check_requirements() with auto-install (ultralytics#2575) 

    * Update check_requirements() with auto-install

This PR builds on an idea I had to automatically install missing dependencies rather than simply report an error message. 

YOLOv5 should now 1) display all dependency issues and not simply display the first missing dependency, and 2) attempt to install/update each missing/VersionConflict package.

* cleanup

* cleanup 2

* Check requirements.txt file exists

* cleanup 3
    @glenn-jocher
    glenn-jocher authored Mar 24, 2021
    Configuration menu
    Copy the full SHA
    2b329b0 View commit details
    Browse the repository at this point in the history

  2. Update tensorboard>=2.4.1 (ultralytics#2576) 

    * Update tensorboard>=2.4.1 

Update tensorboard version to attempt to address ultralytics#2573 (tensorboard logging fail in Docker image).

* cleanup
    @glenn-jocher
    glenn-jocher authored Mar 24, 2021
    Configuration menu
    Copy the full SHA
    e5b0200 View commit details
    Browse the repository at this point in the history

  3. YOLOv5 PyTorch Hub models >> check_requirements() (ultralytics#2577) 

    * Update hubconf.py with check_requirements()

Dependency checks have been missing from YOLOv5 PyTorch Hub model loading, causing errors in some cases when users are attempting to import hub models in unsupported environments. This should examine the YOLOv5 requirements.txt file and pip install any missing or version-conflict packages encountered. 

This is highly experimental (!), please let us know if this creates problems in your custom workflows.

* Update hubconf.py
    @glenn-jocher
    glenn-jocher authored Mar 24, 2021
    Configuration menu
    Copy the full SHA
    2bcc89d View commit details
    Browse the repository at this point in the history

  4. W&B DDP fix 2 (ultralytics#2587) 

    Revert unintentional change to test batch sizes caused by PR ultralytics#2125
    @glenn-jocher
    glenn-jocher authored Mar 24, 2021
    Configuration menu
    Copy the full SHA
    9f98201 View commit details
    Browse the repository at this point in the history

  5. YOLOv5 PyTorch Hub models >> check_requirements() (ultralytics#2588) 

    * YOLOv5 PyTorch Hub models >> check_requirements()

Update YOLOv5 PyTorch Hub requirements.txt path to cache path.

* Update hubconf.py
    @glenn-jocher
    glenn-jocher authored Mar 24, 2021
    Configuration menu
    Copy the full SHA
    8ace1b1 View commit details
    Browse the repository at this point in the history

  6. YOLOv5 PyTorch Hub models >> check_requirements() (ultralytics#2591) 

    Prints 'Please restart runtime or rerun command for update to take effect.' following package auto-install to inform users to restart/rerun.
    @glenn-jocher
    glenn-jocher authored Mar 24, 2021
    Configuration menu
    Copy the full SHA
    75feeb7 View commit details
    Browse the repository at this point in the history

  7. YOLOv5 PyTorch Hub models >> check_requirements() (ultralytics#2592) 

    Improved user-feedback following requirements auto-update.
    @glenn-jocher
    glenn-jocher authored Mar 24, 2021
    Configuration menu
    Copy the full SHA
    333ccc5 View commit details
    Browse the repository at this point in the history

  8. Supervisely Ecosystem (ultralytics#2519) 

    guide describes YOLOv5 apps collection in Supervisely Ecosystem
    @mkolomeychenko
    mkolomeychenko authored Mar 24, 2021
    Configuration menu
    Copy the full SHA
    1620669 View commit details
    Browse the repository at this point in the history

Commits on Mar 25, 2021

  1. Save webcam results, add --nosave option (ultralytics#2598) 

    This updates the default detect.py behavior to automatically save all inference images/videos/webcams unless the new argument --nosave is used (python detect.py --nosave) or unless a list of streaming sources is passed (python detect.py --source streams.txt)
    @glenn-jocher
    glenn-jocher authored Mar 25, 2021
    Configuration menu
    Copy the full SHA
    ad05e37 View commit details
    Browse the repository at this point in the history

  2. Update segment2box() comment (ultralytics#2600)

    @glenn-jocher
    glenn-jocher authored Mar 25, 2021
    Configuration menu
    Copy the full SHA
    d4456e4 View commit details
    Browse the repository at this point in the history

  3. resume.py typo (ultralytics#2603)

    @glenn-jocher
    glenn-jocher authored Mar 25, 2021
    Configuration menu
    Copy the full SHA
    3bb4148 View commit details
    Browse the repository at this point in the history

  4. Remove Cython from requirements.txt (ultralytics#2604) 

    Cython should be a dependency of the remaining packages in requirements.txt, so should be installed anyway even if not a direct requirement.
    @glenn-jocher
    glenn-jocher authored Mar 25, 2021
    Configuration menu
    Copy the full SHA
    fca16dc View commit details
    Browse the repository at this point in the history

Commits on Mar 26, 2021

  1. Update git_describe() for remote dir usage (ultralytics#2606)

    @glenn-jocher
    glenn-jocher authored Mar 26, 2021
    Configuration menu
    Copy the full SHA
    77415a4 View commit details
    Browse the repository at this point in the history

  2. Add '*.mpo' to supported image formats (ultralytics#2615) 

    Co-authored-by: Max Uppenkamp <max.uppenkamp@inform-software.com>
    @maxupp
    maxupp and maxupp authored Mar 26, 2021
    Configuration menu
    Copy the full SHA
    196bf10 View commit details
    Browse the repository at this point in the history

  3. Create date_modified() (ultralytics#2616) 

    Updated device selection string with fallback for non-git directories.
```python
def select_device(device='', batch_size=None):
    # device = 'cpu' or '0' or '0,1,2,3'
    s = f'YOLOv5 🚀 {git_describe() or date_modified()} torch {torch.__version__} '  # string
...
```
    @glenn-jocher
    glenn-jocher authored Mar 26, 2021
    Configuration menu
    Copy the full SHA
    0ff5aec View commit details
    Browse the repository at this point in the history

  4. Update detections() self.t = tuple() (ultralytics#2617) 

    * Update detections() self.t = tuple()

Fix multiple results.print() bug.

* Update experimental.py

* Update yolo.py
    @glenn-jocher
    glenn-jocher authored Mar 26, 2021
    Configuration menu
    Copy the full SHA
    a57f23d View commit details
    Browse the repository at this point in the history

  5. Fix Indentation in test.py (ultralytics#2614) 

    * Fix Indentation in test.py

* CI fix

* Comply with PEP8: 80 characters per line
    @AyushExel
    AyushExel authored Mar 26, 2021
    Configuration menu
    Copy the full SHA
    8f6e447 View commit details
    Browse the repository at this point in the history

  6. Update Detections() self.n comment (ultralytics#2620) 

    ```python
        self.n = len(self.pred)  # number of images (batch size)
```
    @glenn-jocher
    glenn-jocher authored Mar 26, 2021
    Configuration menu
    Copy the full SHA
    005d7a8 View commit details
    Browse the repository at this point in the history

Commits on Mar 27, 2021

  1. Remove conflicting nvidia-tensorboard package (ultralytics#2622) 

    Attempt to resolve tensorboard Docker error in ultralytics#2573
    @glenn-jocher
    glenn-jocher authored Mar 27, 2021
    Configuration menu
    Copy the full SHA
    2dfe320 View commit details
    Browse the repository at this point in the history

  2. FROM nvcr.io/nvidia/pytorch:21.03-py3 (ultralytics#2623) 

    Update Docker FROM nvcr.io/nvidia/pytorch:21.03-py3
    @glenn-jocher
    glenn-jocher authored Mar 27, 2021
    Configuration menu
    Copy the full SHA
    9b92d3e View commit details
    Browse the repository at this point in the history

Commits on Mar 28, 2021

  1. Improve git_describe() (ultralytics#2633) 

    Catch 'fatal: not a git repository' returns and return '' instead (observed in GCP Hub checks).
    @glenn-jocher
    glenn-jocher authored Mar 28, 2021
    Configuration menu
    Copy the full SHA
    6e8c5b7 View commit details
    Browse the repository at this point in the history

  2. Fix: evolve with wandb (ultralytics#2634)

    @AyushExel
    AyushExel authored Mar 28, 2021
    Configuration menu
    Copy the full SHA
    dc51e80 View commit details
    Browse the repository at this point in the history

  3. W&B resume ddp from run link fix (ultralytics#2579) 

    * W&B resume ddp from run link fix

* Native DDP W&B support for training, resuming
    @AyushExel
    AyushExel authored Mar 28, 2021
    Configuration menu
    Copy the full SHA
    518c095 View commit details
    Browse the repository at this point in the history

  4. Improve git_describe() fix 1 (ultralytics#2635) 

    Add stderr=subprocess.STDOUT to catch error messages.
    @glenn-jocher
    glenn-jocher authored Mar 28, 2021
    Configuration menu
    Copy the full SHA
    2e95cf3 View commit details
    Browse the repository at this point in the history

  5. PyTorch Hub custom model to CUDA device fix (ultralytics#2636) 

    Fix for ultralytics#2630 raised by @Pro100rus32
    @glenn-jocher
    glenn-jocher authored Mar 28, 2021
    Configuration menu
    Copy the full SHA
    ee16983 View commit details
    Browse the repository at this point in the history

  6. PyTorch Hub amp.autocast() inference (ultralytics#2641) 

    I think this should help speed up CUDA inference, as currently models may be running in FP32 inference mode on CUDA devices unnecesarily.
    @glenn-jocher
    glenn-jocher authored Mar 28, 2021
    Configuration menu
    Copy the full SHA
    2bf34f5 View commit details
    Browse the repository at this point in the history

Commits on Mar 29, 2021

  1. Add tqdm pbar.close() (ultralytics#2644) 

    When using tqdm, sometimes it can't print in one line and roll to next line.
    @zzttqu
    zzttqu authored Mar 29, 2021
    Configuration menu
    Copy the full SHA
    1e8ab3f View commit details
    Browse the repository at this point in the history

  2. Speed profiling improvements (ultralytics#2648) 

    * Speed profiling improvements

* Update torch_utils.py

deepcopy() required to avoid adding elements to model.

* Update torch_utils.py
    @glenn-jocher
    glenn-jocher authored Mar 29, 2021
    Configuration menu
    Copy the full SHA
    866bc7d View commit details
    Browse the repository at this point in the history

  3. Created using Colaboratory (ultralytics#2649)

    @glenn-jocher
    glenn-jocher committed Mar 29, 2021
    Configuration menu
    Copy the full SHA
    1b100cd View commit details
    Browse the repository at this point in the history

  4. Update requirements.txt (ultralytics#2564) 

    * Add opencv-contrib-python to requirements.txt

* Update requirements.txt

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @youngjinshin @glenn-jocher
    youngjinshin and glenn-jocher authored Mar 29, 2021
    Configuration menu
    Copy the full SHA
    7cdc516 View commit details
    Browse the repository at this point in the history

  5. add option to disable half precision in test.py (ultralytics#2507) 

    Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @bfineran @glenn-jocher
    bfineran and glenn-jocher authored Mar 29, 2021
    Configuration menu
    Copy the full SHA
    fd16799 View commit details
    Browse the repository at this point in the history

  6. Add --label-smoothing eps argument to train.py (default 0.0) (ultraly… 

    …tics#2344)

* Add label smoothing option

* Correct data type

* add_log

* Remove log

* Add log

* Update loss.py

remove comment (too versbose)

Co-authored-by: phattran <phat.tranhoang@cyberlogitec.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @ptran1203 @glenn-jocher
    3 people authored Mar 29, 2021
    Configuration menu
    Copy the full SHA
    9c803f2 View commit details
    Browse the repository at this point in the history

Commits on Mar 30, 2021

  1. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Mar 30, 2021
    Configuration menu
    Copy the full SHA
    1b475c1 View commit details
    Browse the repository at this point in the history

Commits on Mar 31, 2021

  1. Set resume flag to false (ultralytics#2657)

    @AyushExel
    AyushExel authored Mar 31, 2021
    Configuration menu
    Copy the full SHA
    2a28ef3 View commit details
    Browse the repository at this point in the history

Commits on Apr 1, 2021

  1. Update README.md

    @glenn-jocher
    glenn-jocher authored Apr 1, 2021
    Configuration menu
    Copy the full SHA
    51cc096 View commit details
    Browse the repository at this point in the history

  2. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Apr 1, 2021
    Configuration menu
    Copy the full SHA
    877b826 View commit details
    Browse the repository at this point in the history

  3. Update README with Tips for Best Results tutorial (ultralytics#2682) 

    * Update README with Tips for Best Results tutorial

* Update README.md
    @glenn-jocher
    glenn-jocher authored Apr 1, 2021
    Configuration menu
    Copy the full SHA
    b8b8629 View commit details
    Browse the repository at this point in the history

  4. Add TransformerLayer, TransformerBlock, C3TR modules (ultralytics#2333) 

    * yolotr

* transformer block

* Remove bias in Transformer

* Remove C3T

* Remove a deprecated class

* put the 2nd LayerNorm into the 2nd residual block

* move example model to models/hub, rename to -transformer

* Add module comments and TODOs

* Remove LN in Transformer

* Add comments for Transformer

* Solve the problem of MA with DDP

* cleanup

* cleanup find_unused_parameters

* PEP8 reformat

Co-authored-by: DingYiwei <846414640@qq.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @dingyiwei @glenn-jocher
    3 people authored Apr 1, 2021
    Configuration menu
    Copy the full SHA
    1148e2e View commit details
    Browse the repository at this point in the history

Commits on Apr 2, 2021

  1. Fix: ultralytics#2674 (ultralytics#2683) 

    * Set resume flag to false

* Check existance of val dataset
    @AyushExel
    AyushExel authored Apr 2, 2021
    Configuration menu
    Copy the full SHA
    514ebcd View commit details
    Browse the repository at this point in the history

  2. PyTorch Hub model.save() increment as runs/hub/exp (ultralytics#2684) 

    * PyTorch Hub model.save() increment as runs/hub/exp

This chane will align PyTorch Hub results saving with the existing unified results saving directory structure of

runs/
  /train
  /detect
  /test
  /hub
    /exp
    /exp2
    ...

* cleanup
    @glenn-jocher
    glenn-jocher authored Apr 2, 2021
    Configuration menu
    Copy the full SHA
    2af059c View commit details
    Browse the repository at this point in the history

  3. autoShape forward im = np.asarray(im) # to numpy (ultralytics#2689) 

    Slight speedup.
    @glenn-jocher
    glenn-jocher authored Apr 2, 2021
    Configuration menu
    Copy the full SHA
    17300a4 View commit details
    Browse the repository at this point in the history

  4. pip install coremltools onnx (ultralytics#2690) 

    Requested in ultralytics#2686
    @glenn-jocher
    glenn-jocher authored Apr 2, 2021
    Configuration menu
    Copy the full SHA
    9ccfa85 View commit details
    Browse the repository at this point in the history

Commits on Apr 5, 2021

  1. Updated filename attributes for YOLOv5 Hub results (ultralytics#2708) 

    Proposed fix for 'Model predict with forward will fail if PIL image does not have filename attribute' ultralytics#2702
    @glenn-jocher
    glenn-jocher authored Apr 5, 2021
    Configuration menu
    Copy the full SHA
    74276d5 View commit details
    Browse the repository at this point in the history

Commits on Apr 6, 2021

  1. Updated filename attributes for YOLOv5 Hub BytesIO (ultralytics#2718) 

    Fix 2 for 'Model predict with forward will fail if PIL image does not have filename attribute' ultralytics#2702
    @glenn-jocher
    glenn-jocher authored Apr 6, 2021
    Configuration menu
    Copy the full SHA
    ec8979f View commit details
    Browse the repository at this point in the history

  2. Add support for list-of-directory data format for wandb (ultralytics#… 

    …2719)
    @AyushExel
    AyushExel authored Apr 6, 2021
    Configuration menu
    Copy the full SHA
    3067429 View commit details
    Browse the repository at this point in the history

  3. Update README with collapsable notes (ultralytics#2721) 

    * Update README with collapsable notes.

* cleanup

* center table
    @glenn-jocher
    glenn-jocher authored Apr 6, 2021
    Configuration menu
    Copy the full SHA
    c8c8da6 View commit details
    Browse the repository at this point in the history

Commits on Apr 7, 2021

  1. Add Hub results.pandas() method (ultralytics#2725) 

    * Add Hub results.pandas() method

New method converts results from torch tensors to pandas DataFrames with column names.

This PR may partially resolve issue ultralytics#2703

```python
results = model(imgs)

print(results.pandas().xyxy[0])
         xmin        ymin        xmax        ymax  confidence  class    name
0   57.068970  391.770599  241.383545  905.797852    0.868964      0  person
1  667.661255  399.303589  810.000000  881.396667    0.851888      0  person
2  222.878387  414.774231  343.804474  857.825073    0.838376      0  person
3    4.205386  234.447678  803.739136  750.023376    0.658006      5     bus
4    0.000000  550.596008   76.681190  878.669922    0.450596      0  person
```

* Update comments 

torch example input now shown resized to size=640 and also now a multiple of P6 stride 64 (see ultralytics#2722 (comment))

* apply decorators

* PEP8

* Update common.py

* pd.options.display.max_columns = 10

* Update common.py
    @glenn-jocher
    glenn-jocher authored Apr 7, 2021
    Configuration menu
    Copy the full SHA
    c03d590 View commit details
    Browse the repository at this point in the history

Commits on Apr 9, 2021

  1. autocast enable=torch.cuda.is_available() (ultralytics#2748)

    @glenn-jocher
    glenn-jocher authored Apr 9, 2021
    Configuration menu
    Copy the full SHA
    fca5e2a View commit details
    Browse the repository at this point in the history

  2. torch.cuda.amp bug fix (ultralytics#2750) 

    PR ultralytics#2725 introduced a very specific bug that only affects multi-GPU trainings. Apparently the cause was using the torch.cuda.amp decorator in the autoShape forward method. I've implemented amp more traditionally in this PR, and the bug is resolved.
    @glenn-jocher
    glenn-jocher authored Apr 9, 2021
    Configuration menu
    Copy the full SHA
    b5de52c View commit details
    Browse the repository at this point in the history

Commits on Apr 10, 2021

  1. utils/wandb_logging PEP8 reformat (ultralytics#2755) 

    * wandb_logging PEP8 reformat

* Update wandb_utils.py
    @glenn-jocher
    glenn-jocher authored Apr 10, 2021
    Configuration menu
    Copy the full SHA
    0cae757 View commit details
    Browse the repository at this point in the history

  2. Tensorboard model visualization bug fix (ultralytics#2758) 

    This fix should allow for visualizing YOLOv5 model graphs correctly in Tensorboard by uncommenting line 335 in train.py:
```python
                    if tb_writer:
                        tb_writer.add_graph(torch.jit.trace(model, imgs, strict=False), [])  # add model graph
```

The problem was that the detect() layer checks the input size to adapt the grid if required, and tracing does not seem to like this shape check (even if the shape is fine and no grid recomputation is required). The following will warn:
https://github.com/ultralytics/yolov5/blob/0cae7576a9241110157cd154fc2237e703c2719e/train.py#L335

Solution is below. This is a YOLOv5s model displayed in TensorBoard. You can see the Detect() layer merging the 3 layers into a single output for example, and everything appears to work and visualize correctly.
```python
tb_writer.add_graph(torch.jit.trace(model, imgs, strict=False), [])
```
<img width="893" alt="Screenshot 2021-04-11 at 01 10 09" src="https://user-images.githubusercontent.com/26833433/114286928-349bd600-9a63-11eb-941f-7139ee6cd602.png">
    @glenn-jocher
    glenn-jocher authored Apr 10, 2021
    Configuration menu
    Copy the full SHA
    6dd1083 View commit details
    Browse the repository at this point in the history

Commits on Apr 11, 2021

  1. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Apr 11, 2021
    Configuration menu
    Copy the full SHA
    9029759 View commit details
    Browse the repository at this point in the history

  2. YouTube Livestream Detection (ultralytics#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>
    @glenn-jocher
    Ben Milanko and glenn-jocher authored Apr 11, 2021
    Configuration menu
    Copy the full SHA
    e2b7bc0 View commit details
    Browse the repository at this point in the history

  3. YOLOv5 v5.0 Release (ultralytics#2762)

    @glenn-jocher
    glenn-jocher authored Apr 11, 2021
    Configuration menu
    Copy the full SHA
    f5b8f7d View commit details
    Browse the repository at this point in the history

  4. YOLOv5 v5.0 Release patch 1 (ultralytics#2764) 

    * torch.jit.trace(model, img, strict=False)

* Update check_file()

* Update hubconf.py

* Update README.md
    @glenn-jocher
    glenn-jocher authored Apr 11, 2021
    Configuration menu
    Copy the full SHA
    0f395b3 View commit details
    Browse the repository at this point in the history

Commits on Apr 12, 2021

  1. Update tutorial.ipynb

    @glenn-jocher
    glenn-jocher authored Apr 12, 2021
    Configuration menu
    Copy the full SHA
    54d6516 View commit details
    Browse the repository at this point in the history

  2. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Apr 12, 2021
    Configuration menu
    Copy the full SHA
    6b718e9 View commit details
    Browse the repository at this point in the history

  3. Update tutorial.ipynb

    @glenn-jocher
    glenn-jocher authored Apr 12, 2021
    Configuration menu
    Copy the full SHA
    2eab46e View commit details
    Browse the repository at this point in the history

  4. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Apr 12, 2021
    Configuration menu
    Copy the full SHA
    cac8a76 View commit details
    Browse the repository at this point in the history

  5. Created using Colaboratory

    @glenn-jocher
    glenn-jocher committed Apr 12, 2021
    Configuration menu
    Copy the full SHA
    860ca98 View commit details
    Browse the repository at this point in the history

  6. Update README.md

    @glenn-jocher
    glenn-jocher authored Apr 12, 2021
    Configuration menu
    Copy the full SHA
    1487bc8 View commit details
    Browse the repository at this point in the history

Commits on Apr 15, 2021

  1. Flask REST API Example (ultralytics#2732) 

    * add files

* Update README.md

* Update README.md

* Update restapi.py

pretrained=True and model.eval() are used by default when loading a model now, so no need to call them manually.

* PEP8 reformat

* PEP8 reformat

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @robmarkcole @glenn-jocher
    robmarkcole and glenn-jocher authored Apr 15, 2021
    Configuration menu
    Copy the full SHA
    1479737 View commit details
    Browse the repository at this point in the history

  2. Update README.md

    @glenn-jocher
    glenn-jocher authored Apr 15, 2021
    Configuration menu
    Copy the full SHA
    e5d7122 View commit details
    Browse the repository at this point in the history

Commits on Apr 16, 2021

  1. ONNX Simplifier (ultralytics#2815) 

    * ONNX Simplifier

Add ONNX Simplifier to ONNX export pipeline in export.py. Will auto-install onnx-simplifier if onnx is installed but onnx-simplifier is not.

* Update general.py
    @glenn-jocher
    glenn-jocher authored Apr 16, 2021
    Configuration menu
    Copy the full SHA
    1f3e482 View commit details
    Browse the repository at this point in the history

  2. YouTube Bug Fix (ultralytics#2818) 

    Fix for ultralytics#2810
```shell
python detect.py --source 0
```
introduced by YouTube Livestream Detection PR ultralytics#2752
    @glenn-jocher
    glenn-jocher authored Apr 16, 2021
    Configuration menu
    Copy the full SHA
    aff03be View commit details
    Browse the repository at this point in the history

Commits on Apr 18, 2021

  1. PyTorch Hub cv2 .save() .show() bug fix (ultralytics#2831) 

    * PyTorch Hub cv2 .save() .show() bug fix

cv2.rectangle() was failing on non-contiguous np array inputs. This checks for contiguous arrays and applies is necessary:
```python
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
```

* Update plots.py

```python
assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to plot_on_box() input image.'
```

* Update hubconf.py

Expand CI tests to OpenCV image.
    @glenn-jocher
    glenn-jocher authored Apr 18, 2021
    Configuration menu
    Copy the full SHA
    c15e25c View commit details
    Browse the repository at this point in the history

  2. Create FUNDING.yml (ultralytics#2832)

    @glenn-jocher
    glenn-jocher authored Apr 18, 2021
    Configuration menu
    Copy the full SHA
    803f51b View commit details
    Browse the repository at this point in the history

  3. Update FUNDING.yml (ultralytics#2833) 

    * Update FUNDING.yml

* move FUNDING.yml to ./github
    @glenn-jocher
    glenn-jocher authored Apr 18, 2021
    Configuration menu
    Copy the full SHA
    238583b View commit details
    Browse the repository at this point in the history

Commits on Apr 20, 2021

  1. Fix ONNX dynamic axes export support with onnx simplifier, make onnx … 

    …simplifier optional (ultralytics#2856)

* Ensure dynamic export works succesfully, onnx simplifier optional

* Update export.py

* add dashes

Co-authored-by: Tim <tim.stokman@hal24k.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @timstokman @glenn-jocher
    3 people authored Apr 20, 2021
    Configuration menu
    Copy the full SHA
    1df8c6c View commit details
    Browse the repository at this point in the history

  2. Update increment_path() to handle file paths (ultralytics#2867)

    @glenn-jocher
    glenn-jocher authored Apr 20, 2021
    Configuration menu
    Copy the full SHA
    c5c647e View commit details
    Browse the repository at this point in the history

  3. Detection cropping+saving feature addition for detect.py and PyTorch … 

    …Hub (ultralytics#2827)

* Update detect.py

* Update detect.py

* Update greetings.yml

* Update cropping

* cleanup

* Update increment_path()

* Update common.py

* Update detect.py

* Update detect.py

* Update detect.py

* Update common.py

* cleanup

* Update detect.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @burhr2 @glenn-jocher
    burhr2 and glenn-jocher authored Apr 20, 2021
    Configuration menu
    Copy the full SHA
    c949fc8 View commit details
    Browse the repository at this point in the history

Commits on Apr 21, 2021

  1. Implement yaml.safe_load() (ultralytics#2876) 

    * Implement yaml.safe_load()

* yaml.safe_dump()
    @glenn-jocher
    glenn-jocher authored Apr 21, 2021
    Configuration menu
    Copy the full SHA
    f7bc685 View commit details
    Browse the repository at this point in the history

  2. Cleanup load_image() (ultralytics#2871) 

    * don't resize up in load_image if augmenting

* cleanup

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @JoshSong @glenn-jocher
    JoshSong and glenn-jocher authored Apr 21, 2021
    Configuration menu
    Copy the full SHA
    5f7d39f View commit details
    Browse the repository at this point in the history

  3. bug fix: switched rows and cols for correct detections in confusion m… 

    …atrix (ultralytics#2883)
    @MichHeilig
    MichHeilig authored Apr 21, 2021
    Configuration menu
    Copy the full SHA
    d48a34d View commit details
    Browse the repository at this point in the history

Commits on Apr 22, 2021

  1. VisDrone2019-DET Dataset Auto-Download (ultralytics#2882) 

    * VisDrone Dataset Auto-Download

* add visdrone.yaml

* cleanup

* add VisDrone2019-DET-test-dev

* cleanup VOC
    @glenn-jocher
    glenn-jocher authored Apr 22, 2021
    Configuration menu
    Copy the full SHA
    78fd077 View commit details
    Browse the repository at this point in the history

  2. Uppercase model filenames enabled (ultralytics#2890)

    @r-blmnr
    r-blmnr authored Apr 22, 2021
    Configuration menu
    Copy the full SHA
    0395e39 View commit details
    Browse the repository at this point in the history

  3. ACON activation function (ultralytics#2893) 

    * ACON Activation Function

## 🚀 Feature

There is a new activation function [ACON (CVPR 2021)](https://arxiv.org/pdf/2009.04759.pdf) that unifies ReLU and Swish. 
ACON is simple but very effective, code is here: https://github.com/nmaac/acon/blob/main/acon.py#L19

![image](https://user-images.githubusercontent.com/5032208/115676962-a38dfe80-a382-11eb-9883-61fa3216e3e6.png)

The improvements are very significant:
![image](https://user-images.githubusercontent.com/5032208/115680180-eac9be80-a385-11eb-9c7a-8643db552c69.png)

## Alternatives

It also has an enhanced version meta-ACON that uses a small network to learn beta explicitly, which may influence the speed a bit.

## Additional context

[Code](https://github.com/nmaac/acon) and [paper](https://arxiv.org/pdf/2009.04759.pdf).

* Update activations.py
    @glenn-jocher
    glenn-jocher authored Apr 22, 2021
    Configuration menu
    Copy the full SHA
    264d860 View commit details
    Browse the repository at this point in the history

  4. Explicit opt function arguments (ultralytics#2817) 

    * more explicit function arguments

* fix typo in detect.py

* revert import order

* revert import order

* remove default value
    @fcakyon
    fcakyon authored Apr 22, 2021
    Configuration menu
    Copy the full SHA
    b40dd99 View commit details
    Browse the repository at this point in the history

  5. Update yolo.py (ultralytics#2899)

    @glenn-jocher
    glenn-jocher authored Apr 22, 2021
    Configuration menu
    Copy the full SHA
    cdb678f View commit details
    Browse the repository at this point in the history

  6. Update google_utils.py (ultralytics#2900)

    @glenn-jocher
    glenn-jocher authored Apr 22, 2021
    Configuration menu
    Copy the full SHA
    14d2d2d View commit details
    Browse the repository at this point in the history

Commits on Apr 23, 2021

  1. Add detect.py --hide-conf --hide-labels --line-thickness options (ult… 

    …ralytics#2658)

* command line option for line thickness and hiding labels

* command line option for line thickness and hiding labels

* command line option for line thickness and hiding labels

* command line option for line thickness and hiding labels

* command line option for line thickness and hiding labels

* command line option for hiding confidence values

* Update detect.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @Ashafix @glenn-jocher
    Ashafix and glenn-jocher authored Apr 23, 2021
    Configuration menu
    Copy the full SHA
    f662c18 View commit details
    Browse the repository at this point in the history

  2. Default optimize_for_mobile() on TorchScript models (ultralytics#2908) 

    Per https://pytorch.org/tutorials/recipes/script_optimized.html this should improve performance on torchscript models (and maybe coreml models also since coremltools operates on a torchscript model input, though this still requires testing).
    @glenn-jocher
    glenn-jocher authored Apr 23, 2021
    Configuration menu
    Copy the full SHA
    28db237 View commit details
    Browse the repository at this point in the history

  3. Update export.py (ultralytics#2909)

    @glenn-jocher
    glenn-jocher authored Apr 23, 2021
    Configuration menu
    Copy the full SHA
    a2a514d View commit details
    Browse the repository at this point in the history

  4. Update export.py for 2 dry runs (ultralytics#2910) 

    * Update export.py for 2 dry runs

* Update export.py
    @glenn-jocher
    glenn-jocher authored Apr 23, 2021
    Configuration menu
    Copy the full SHA
    646386f View commit details
    Browse the repository at this point in the history

  5. Add file_size() function (ultralytics#2911) 

    * Add file_size() function

* Update export.py
    @glenn-jocher
    glenn-jocher authored Apr 23, 2021
    Configuration menu
    Copy the full SHA
    1b1ab4c View commit details
    Browse the repository at this point in the history

Commits on Apr 24, 2021

  1. Update download() for tar.gz files (ultralytics#2919) 

    * Update download() for tar.gz files

* Update general.py
    @glenn-jocher
    glenn-jocher authored Apr 24, 2021
    Configuration menu
    Copy the full SHA
    45632b2 View commit details
    Browse the repository at this point in the history

  2. Update visdrone.yaml (ultralytics#2921)

    @glenn-jocher
    glenn-jocher authored Apr 24, 2021
    Configuration menu
    Copy the full SHA
    de19d39 View commit details
    Browse the repository at this point in the history

  3. Change default value of hide label argument to False (ultralytics#2923)

    @albinxavi
    albinxavi authored Apr 24, 2021
    Configuration menu
    Copy the full SHA
    eae28a9 View commit details
    Browse the repository at this point in the history

Commits on Apr 25, 2021

  1. Change default value of hide-conf argument to false (ultralytics#2925)

    @albinxavi
    albinxavi authored Apr 25, 2021
    Configuration menu
    Copy the full SHA
    aa78069 View commit details
    Browse the repository at this point in the history

  2. test.py native --single-cls (ultralytics#2928)

    @glenn-jocher
    glenn-jocher authored Apr 25, 2021
    Configuration menu
    Copy the full SHA
    3665c0f View commit details
    Browse the repository at this point in the history

  3. Add verbose option to pytorch hub models (ultralytics#2926) 

    * Add verbose and update print to logging

* Fix positonal param

* Revert auto formatting changes

* Update hubconf.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @NanoCode012 @glenn-jocher
    NanoCode012 and glenn-jocher authored Apr 25, 2021
    Configuration menu
    Copy the full SHA
    c0d3f80 View commit details
    Browse the repository at this point in the history

  4. ACON Activation batch-size 1 bug patch (ultralytics#2901) 

    * ACON Activation batch-size 1 bug path

This is not a great solution to nmaac/acon#4 but it's all I could think of at the moment.

WARNING: YOLOv5 models with MetaAconC() activations are incapable of running inference at batch-size 1 properly due to a known bug in nmaac/acon#4 with no known solution.

* Update activations.py

* Update activations.py

* Update activations.py

* Update activations.py
    @glenn-jocher
    glenn-jocher authored Apr 25, 2021
    Configuration menu
    Copy the full SHA
    9c7bb5a View commit details
    Browse the repository at this point in the history

  5. Check_requirements() enclosing apostrophe bug fix (ultralytics#2929) 

    This fixes a bug where the '>' symbol in python package requirements was not running correctly with subprocess.check_output() commands.
    @glenn-jocher
    glenn-jocher authored Apr 25, 2021
    Configuration menu
    Copy the full SHA
    1849916 View commit details
    Browse the repository at this point in the history

Commits on Apr 26, 2021

  1. Update README.md (ultralytics#2934) 

    * Update README.md

dependencies:
ImportError: libGL.so.1: cannot open shared object file: No such file or directory
ImportError: libgthread-2.0.so.0: cannot open shared object file: No such file or directory
ImportError: libSM.so.6: cannot open shared object file: No such file or directory
ImportError: libXrender.so.1: cannot open shared object file: No such file or directory

* replace older apt-get with apt

Code commented for now until a better understanding of the issue, and also code is not cross-platform compatible.

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
    @glenn-jocher
    BZFYS and glenn-jocher authored Apr 26, 2021
    Configuration menu
    Copy the full SHA
    6c1290f View commit details
    Browse the repository at this point in the history

  2. Improved yolo.py profiling (ultralytics#2940) 

    * Improved yolo.py profiling

Improved column order and labelling.

* Update yolo.py
    @glenn-jocher
    glenn-jocher authored Apr 26, 2021
    Configuration menu
    Copy the full SHA
    4890499 View commit details
    Browse the repository at this point in the history

Commits on Apr 27, 2021

  1. Add yolov5/ to sys.path() for *.py subdir exec (ultralytics#2949) 

    * Add yolov5/ to sys.path() for *.py subdir exec

* Update export.py
    @glenn-jocher
    glenn-jocher authored Apr 27, 2021
    Configuration menu
    Copy the full SHA
    4200674 View commit details
    Browse the repository at this point in the history

Commits on Apr 28, 2021

  1. merge latest version done, not tested

    @mkolomeychenko
    mkolomeychenko committed Apr 28, 2021
    Configuration menu
    Copy the full SHA
    b37531b View commit details
    Browse the repository at this point in the history

Commits on May 7, 2021

  1. update UI + latest yolov5 sources (#15) 

    * merge latest version done, not tested

* split tabs with radio buttons

* models table -wip

* models table -wip

* start split html template to parts

* ui refactoring

* compile-template wip - paths confusion

* compile wip

* train/val splits

* keep/ignore unlabeled images

* models table

* training hyperparameters

* UI templates - done

* unlabeled count in UI

* add adam optimizer

* convert_project to detection - works

* start train/val splits

* splits wip

* splits done, only simple tests

* splits validation

* data preprocessing - not tested

* download weights - wip

* init_script_arguments - not tested

* init_script_arguments - not tested

* prepare weights - wip

* not tested

* add metrics period

* set output

* artifacts dirs

* train_batches_uploaded flag

* pre-release for debug

* update config
    @mkolomeychenko
    mkolomeychenko authored May 7, 2021
    Configuration menu
    Copy the full SHA
    cb425b0 View commit details
    Browse the repository at this point in the history

  2. update SDK version

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    fb5235a View commit details
    Browse the repository at this point in the history

  3. fix imports

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    3c5350a View commit details
    Browse the repository at this point in the history

  4. change imports

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    07872fc View commit details
    Browse the repository at this point in the history

  5. change imports

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    6a8599e View commit details
    Browse the repository at this point in the history

  6. add UI sources directory to sys.path

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    da24644 View commit details
    Browse the repository at this point in the history

  7. new SDK version

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    9407b98 View commit details
    Browse the repository at this point in the history

  8. new SDK version

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    14dbc34 View commit details
    Browse the repository at this point in the history

  9. fix GIoU smoothing

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    78d9bec View commit details
    Browse the repository at this point in the history

  10. update smoothing

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    ef0e0d7 View commit details
    Browse the repository at this point in the history

  11. send metrics for the last epoch

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    9f34e7e View commit details
    Browse the repository at this point in the history

  12. save link to app UI

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    381d431 View commit details
    Browse the repository at this point in the history

  13. todo

    @mkolomeychenko
    mkolomeychenko committed May 7, 2021
    Configuration menu
    Copy the full SHA
    1394349 View commit details
    Browse the repository at this point in the history

Commits on May 11, 2021

  1. log train/val size

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    d207aac View commit details
    Browse the repository at this point in the history

  2. sly-to-yolov5 format: fix same names in different datasets

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    a55ee16 View commit details
    Browse the repository at this point in the history

  3. fix inference

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    e036c79 View commit details
    Browse the repository at this point in the history

  4. serve not tested

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    72cb08f View commit details
    Browse the repository at this point in the history

  5. [serve] modal table stat

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    152b906 View commit details
    Browse the repository at this point in the history

  6. [serve] modal tabs

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    86a634d View commit details
    Browse the repository at this point in the history

  7. [serve] modal tabs

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    bf3180f View commit details
    Browse the repository at this point in the history

  8. [serve] modal width

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    63e011f View commit details
    Browse the repository at this point in the history

  9. [serve] modal tabs style

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    111485f View commit details
    Browse the repository at this point in the history

  10. [serve] fix pretrained weights URL

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    2086939 View commit details
    Browse the repository at this point in the history

  11. [serve] add stride to serv

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    fb5eeed View commit details
    Browse the repository at this point in the history

  12. [train] readme wip

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    8c7a8ba View commit details
    Browse the repository at this point in the history

  13. [train] readme wip

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    48d4eeb View commit details
    Browse the repository at this point in the history

  14. [train] readme wip

    @mkolomeychenko
    mkolomeychenko committed May 11, 2021
    Configuration menu
    Copy the full SHA
    16b5c20 View commit details
    Browse the repository at this point in the history

Commits on May 13, 2021

  1. [serve] change inference_image_id to work with remote storages (s3, a… 

    …zure, ...)
    @mkolomeychenko
    mkolomeychenko committed May 13, 2021
    Configuration menu
    Copy the full SHA
    7c0e7c7 View commit details
    Browse the repository at this point in the history

  2. [serve] fix stride initialization

    @mkolomeychenko
    mkolomeychenko committed May 13, 2021
    Configuration menu
    Copy the full SHA
    1ac6bed View commit details
    Browse the repository at this point in the history

  3. [serve] yolov5 serve - fixed

    @mkolomeychenko
    mkolomeychenko committed May 13, 2021
    Configuration menu
    Copy the full SHA
    f92ed93 View commit details
    Browse the repository at this point in the history

Commits on May 14, 2021

  1. add additional info logs

    @mkolomeychenko
    mkolomeychenko committed May 14, 2021
    Configuration menu
    Copy the full SHA
    7603c86 View commit details
    Browse the repository at this point in the history

  2. add additional info logs

    @mkolomeychenko
    mkolomeychenko committed May 14, 2021
    Configuration menu
    Copy the full SHA
    70dc0c2 View commit details
    Browse the repository at this point in the history

Commits on May 17, 2021

  1. [serve] todo

    @mkolomeychenko
    mkolomeychenko committed May 17, 2021
    Configuration menu
    Copy the full SHA
    e7955d8 View commit details
    Browse the repository at this point in the history

  2. [train] splits - hide notice1

    @mkolomeychenko
    mkolomeychenko committed May 17, 2021
    Configuration menu
    Copy the full SHA
    22d48c2 View commit details
    Browse the repository at this point in the history

  3. fix collections readme

    @mkolomeychenko
    mkolomeychenko committed May 17, 2021
    Configuration menu
    Copy the full SHA
    e16acdb View commit details
    Browse the repository at this point in the history

  4. train readme - new screenshot

    @mkolomeychenko
    mkolomeychenko committed May 17, 2021
    Configuration menu
    Copy the full SHA
    6318b1c View commit details
    Browse the repository at this point in the history

  5. train readme

    @mkolomeychenko
    mkolomeychenko committed May 17, 2021
    Configuration menu
    Copy the full SHA
    aa60ea4 View commit details
    Browse the repository at this point in the history