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

How do you find optimal parameters for mixup augmentation? #3380

Closed
developer0hye opened this issue May 29, 2021 · 10 comments · Fixed by #3455
Closed

How do you find optimal parameters for mixup augmentation? #3380

developer0hye opened this issue May 29, 2021 · 10 comments · Fixed by #3455
Assignees
@developer0hye

Comments

@developer0hye
Copy link
Contributor

yolov5/utils/datasets.py

Lines 536 to 540 in ba6f3f9

if random.random() < hyp['mixup']:
img2, labels2 = load_mosaic(self, random.randint(0, self.n - 1))
r = np.random.beta(8.0, 8.0) # mixup ratio, alpha=beta=8.0
img = (img * r + img2 * (1 - r)).astype(np.uint8)
labels = np.concatenate((labels, labels2), 0)

@glenn-jocher

Hi, jocher!

How do you find optimal parameters for mixup augmentation?

r = np.random.beta(8.0, 8.0)

why are the values of alpha and beta 8?
@glenn-jocher
Copy link
Member

@developer0hye this controls the ratio of mixing between img1 and img2. You can see the distribution of r here:

import numpy as np
import matplotlib.pyplot as plt

x = np.random.beta(8.0, 8.0, 1000000)
plt.hist(x,500)

Figure_1

The main issue discussing the mixup ratios and implementation for this repo is here:
#357. The current values of 8.0 are used to implement a roughly 50/50 mixup with noise, i.e. maybe 0.2-0.8 3-sigma. I arrived at the 8.0 number after testing different betas, 0.5, 1.0, 2.0, 4.0, 8.0, and observed better results at higher betas.

@developer0hye
Copy link
Contributor Author

@glenn-jocher
Thanks for your reply!

@developer0hye
Copy link
Contributor Author

developer0hye commented Jun 2, 2021 •
edited
Loading

@glenn-jocher

Hi, jocher!

I recommend you do training with higher alpha and beta values like 32.0.

I got higher mAP with higher alpha and beta values on VOC dataset.

https://github.com/developer0hye/Simple-CenterNet

@glenn-jocher
Copy link
Member

@developer0hye oh interesting! Higher beta values will tighten the mixing ratio close to 0.5. Do you have VOC mAP values vs beta?

@developer0hye
Copy link
Contributor Author

developer0hye commented Jun 2, 2021 •
edited
Loading

@glenn-jocher

It's my results.

alpha beta 8.0, mAP: 77.1
alpha beta 16.0 , mAP: 77.4
alpha beta 32.0, mAP: 77.6

@glenn-jocher
Copy link
Member

@developer0hye oh awesome!! Yeah it seems I should increase the default beta then...
TODO: investigate increasing mixup betas.

@developer0hye
Copy link
Contributor Author

developer0hye commented Jun 2, 2021 •
edited
Loading

@glenn-jocher

I hope the graph of yolov5 be the below figure!

image

@glenn-jocher
Copy link
Member

@developer0hye haha, we'll add that graphic to the README on the next release.

glenn-jocher added a commit that referenced this issue Jun 4, 2021
@glenn-jocher
Update MixUp augmentation alpha=beta=32.0
a5ffd22 
Per VOC empirical results #3380 (comment) by @developer0hye
@glenn-jocher glenn-jocher mentioned this issue Jun 4, 2021
Merged
@glenn-jocher glenn-jocher reopened this Jun 4, 2021
@glenn-jocher glenn-jocher linked a pull request Jun 4, 2021 that will close this issue
Update MixUp augmentation alpha=beta=32.0 #3455
Merged
glenn-jocher added a commit that referenced this issue Jun 4, 2021
@glenn-jocher
Update MixUp augmentation alpha=beta=32.0 (#3455)
8e3b4a0 
Per VOC empirical results #3380 (comment) by @developer0hye
@glenn-jocher glenn-jocher removed the TODO label Jun 4, 2021
@glenn-jocher
Copy link
Member

@developer0hye we don't have much opportunity to test, but I'll assume your VOC results are accurate and generalize well to other datasets, so I've implemented this update in #3455. Thank you for your contributions!

@developer0hye
Copy link
Contributor Author

@glenn-jocher
Thanks! But... I'm a little worried that it might harm the performance of yolov5 on coco dataset.

glenn-jocher added a commit that referenced this issue Jun 8, 2021
@glenn-jocher @SkalskiP
@pizzaz93 @tudoulei @chocosaj @developer0hye @SamSamhuns @PresageBoat
Merge develop branch into master (#3518)
f3c3d2c 
* update ci-testing.yml (#3322)

* update ci-testing.yml

* update greetings.yml

* bring back os matrix

* update ci-testing.yml (#3322)

* update ci-testing.yml

* update greetings.yml

* bring back os matrix

* Enable direct `--weights URL` definition (#3373)

* Enable direct `--weights URL` definition

@kalenmike this PR will enable direct --weights URL definition. Example use case:
```
python train.py --weights https://storage.googleapis.com/bucket/dir/model.pt
```

* cleanup

* bug fixes

* weights = attempt_download(weights)

* Update experimental.py

* Update hubconf.py

* return bug fix

* comment mirror

* min_bytes

* Update tutorial.ipynb (#3368)

add Open in Kaggle badge

* `cv2.imread(img, -1)` for IMREAD_UNCHANGED (#3379)

* Update datasets.py

* comment

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

* COCO evolution fix (#3388)

* COCO evolution fix

* cleanup

* update print

* print fix

* Create `is_pip()` function (#3391)

Returns `True` if file is part of pip package. Useful for contextual behavior modification.

```python
def is_pip():
    # Is file in a pip package?
    return 'site-packages' in Path(__file__).absolute().parts
```

* Revert "`cv2.imread(img, -1)` for IMREAD_UNCHANGED (#3379)" (#3395)

This reverts commit 21a9607.

* Update FLOPs description (#3422)

* Update README.md

* Changing FLOPS to FLOPs.

Co-authored-by: BuildTools <unconfigured@null.spigotmc.org>

* Parse URL authentication (#3424)

* Parse URL authentication

* urllib.parse.unquote()

* improved error handling

* improved error handling

* remove %3F

* update check_file()

* Add FLOPs title to table (#3453)

* Suppress jit trace warning + graph once (#3454)

* Suppress jit trace warning + graph once

Suppress harmless jit trace warning on TensorBoard add_graph call. Also fix multiple add_graph() calls bug, now only on batch 0.

* Update train.py

* Update MixUp augmentation `alpha=beta=32.0` (#3455)

Per VOC empirical results #3380 (comment) by @developer0hye

* Add `timeout()` class (#3460)

* Add `timeout()` class

* rearrange order

* Faster HSV augmentation (#3462)

remove datatype conversion process that can be skipped

* Add `check_git_status()` 5 second timeout (#3464)

* Add check_git_status() 5 second timeout

This should prevent the SSH Git bug that we were discussing @kalenmike

* cleanup

* replace timeout with check_output built-in timeout

* Improved `check_requirements()` offline-handling (#3466)

Improve robustness of `check_requirements()` function to offline environments (do not attempt pip installs when offline).

* Add `output_names` argument for ONNX export with dynamic axes (#3456)

* Add output names & dynamic axes for onnx export

Add output_names and dynamic_axes names for all outputs in torch.onnx.export. The first four outputs of the model will have names output0, output1, output2, output3

* use first output only + cleanup

Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Revert FP16 `test.py` and `detect.py` inference to FP32 default (#3423)

* fixed inference bug ,while use half precision

* replace --use-half with --half

* replace space and PEP8 in detect.py

* PEP8 detect.py

* update --half help comment

* Update test.py

* revert space

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

* Add additional links/resources to stale.yml message (#3467)

* Update stale.yml

* cleanup

* Update stale.yml

* reformat

* Update stale.yml HUB URL (#3468)

* Stale `github.actor` bug fix (#3483)

* Explicit `model.eval()` call `if opt.train=False` (#3475)

* call model.eval() when opt.train is False

call model.eval() when opt.train is False

* single-line if statement

* cleanup

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

* check_requirements() exclude `opencv-python` (#3495)

Fix for 3rd party or contrib versions of installed OpenCV as in #3494.

* Earlier `assert` for cpu and half option (#3508)

* early assert for cpu and half option

early assert for cpu and half option

* Modified comment

Modified comment

* Update tutorial.ipynb (#3510)

* Reduce test.py results spacing (#3511)

* Update README.md (#3512)

* Update README.md

Minor modifications

* 850 width

* Update greetings.yml

revert greeting change as PRs will now merge to master.

Co-authored-by: Piotr Skalski <SkalskiP@users.noreply.github.com>
Co-authored-by: SkalskiP <piotr.skalski92@gmail.com>
Co-authored-by: Peretz Cohen <pizzaz93@users.noreply.github.com>
Co-authored-by: tudoulei <34886368+tudoulei@users.noreply.github.com>
Co-authored-by: chocosaj <chocosaj@users.noreply.github.com>
Co-authored-by: BuildTools <unconfigured@null.spigotmc.org>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
Co-authored-by: Sam_S <SamSamhuns@users.noreply.github.com>
Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai>
Co-authored-by: edificewang <609552430@qq.com>
Lechtr pushed a commit to Lechtr/yolov5 that referenced this issue Jul 20, 2021
@glenn-jocher @Lechtr
Merge develop branch into master (ultralytics#3518)
9969677 
* update ci-testing.yml (ultralytics#3322)

* update ci-testing.yml

* update greetings.yml

* bring back os matrix

* update ci-testing.yml (ultralytics#3322)

* update ci-testing.yml

* update greetings.yml

* bring back os matrix

* Enable direct `--weights URL` definition (ultralytics#3373)

* Enable direct `--weights URL` definition

@kalenmike this PR will enable direct --weights URL definition. Example use case:
```
python train.py --weights https://storage.googleapis.com/bucket/dir/model.pt
```

* cleanup

* bug fixes

* weights = attempt_download(weights)

* Update experimental.py

* Update hubconf.py

* return bug fix

* comment mirror

* min_bytes

* Update tutorial.ipynb (ultralytics#3368)

add Open in Kaggle badge

* `cv2.imread(img, -1)` for IMREAD_UNCHANGED (ultralytics#3379)

* Update datasets.py

* comment

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

* COCO evolution fix (ultralytics#3388)

* COCO evolution fix

* cleanup

* update print

* print fix

* Create `is_pip()` function (ultralytics#3391)

Returns `True` if file is part of pip package. Useful for contextual behavior modification.

```python
def is_pip():
    # Is file in a pip package?
    return 'site-packages' in Path(__file__).absolute().parts
```

* Revert "`cv2.imread(img, -1)` for IMREAD_UNCHANGED (ultralytics#3379)" (ultralytics#3395)

This reverts commit 21a9607.

* Update FLOPs description (ultralytics#3422)

* Update README.md

* Changing FLOPS to FLOPs.

Co-authored-by: BuildTools <unconfigured@null.spigotmc.org>

* Parse URL authentication (ultralytics#3424)

* Parse URL authentication

* urllib.parse.unquote()

* improved error handling

* improved error handling

* remove %3F

* update check_file()

* Add FLOPs title to table (ultralytics#3453)

* Suppress jit trace warning + graph once (ultralytics#3454)

* Suppress jit trace warning + graph once

Suppress harmless jit trace warning on TensorBoard add_graph call. Also fix multiple add_graph() calls bug, now only on batch 0.

* Update train.py

* Update MixUp augmentation `alpha=beta=32.0` (ultralytics#3455)

Per VOC empirical results ultralytics#3380 (comment) by @developer0hye

* Add `timeout()` class (ultralytics#3460)

* Add `timeout()` class

* rearrange order

* Faster HSV augmentation (ultralytics#3462)

remove datatype conversion process that can be skipped

* Add `check_git_status()` 5 second timeout (ultralytics#3464)

* Add check_git_status() 5 second timeout

This should prevent the SSH Git bug that we were discussing @kalenmike

* cleanup

* replace timeout with check_output built-in timeout

* Improved `check_requirements()` offline-handling (ultralytics#3466)

Improve robustness of `check_requirements()` function to offline environments (do not attempt pip installs when offline).

* Add `output_names` argument for ONNX export with dynamic axes (ultralytics#3456)

* Add output names & dynamic axes for onnx export

Add output_names and dynamic_axes names for all outputs in torch.onnx.export. The first four outputs of the model will have names output0, output1, output2, output3

* use first output only + cleanup

Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Revert FP16 `test.py` and `detect.py` inference to FP32 default (ultralytics#3423)

* fixed inference bug ,while use half precision

* replace --use-half with --half

* replace space and PEP8 in detect.py

* PEP8 detect.py

* update --half help comment

* Update test.py

* revert space

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

* Add additional links/resources to stale.yml message (ultralytics#3467)

* Update stale.yml

* cleanup

* Update stale.yml

* reformat

* Update stale.yml HUB URL (ultralytics#3468)

* Stale `github.actor` bug fix (ultralytics#3483)

* Explicit `model.eval()` call `if opt.train=False` (ultralytics#3475)

* call model.eval() when opt.train is False

call model.eval() when opt.train is False

* single-line if statement

* cleanup

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

* check_requirements() exclude `opencv-python` (ultralytics#3495)

Fix for 3rd party or contrib versions of installed OpenCV as in ultralytics#3494.

* Earlier `assert` for cpu and half option (ultralytics#3508)

* early assert for cpu and half option

early assert for cpu and half option

* Modified comment

Modified comment

* Update tutorial.ipynb (ultralytics#3510)

* Reduce test.py results spacing (ultralytics#3511)

* Update README.md (ultralytics#3512)

* Update README.md

Minor modifications

* 850 width

* Update greetings.yml

revert greeting change as PRs will now merge to master.

Co-authored-by: Piotr Skalski <SkalskiP@users.noreply.github.com>
Co-authored-by: SkalskiP <piotr.skalski92@gmail.com>
Co-authored-by: Peretz Cohen <pizzaz93@users.noreply.github.com>
Co-authored-by: tudoulei <34886368+tudoulei@users.noreply.github.com>
Co-authored-by: chocosaj <chocosaj@users.noreply.github.com>
Co-authored-by: BuildTools <unconfigured@null.spigotmc.org>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
Co-authored-by: Sam_S <SamSamhuns@users.noreply.github.com>
Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai>
Co-authored-by: edificewang <609552430@qq.com>

(cherry picked from commit f3c3d2c)
BjarneKuehl pushed a commit to fhkiel-mlaip/yolov5 that referenced this issue Aug 26, 2022
@glenn-jocher
Update MixUp augmentation alpha=beta=32.0 (ultralytics#3455)
fd86784 
Per VOC empirical results ultralytics#3380 (comment) by @developer0hye
BjarneKuehl pushed a commit to fhkiel-mlaip/yolov5 that referenced this issue Aug 26, 2022
@glenn-jocher @SkalskiP
@pizzaz93 @tudoulei @chocosaj @developer0hye @SamSamhuns @PresageBoat
Merge develop branch into master (ultralytics#3518)
8be5168 
* update ci-testing.yml (ultralytics#3322)

* update ci-testing.yml

* update greetings.yml

* bring back os matrix

* update ci-testing.yml (ultralytics#3322)

* update ci-testing.yml

* update greetings.yml

* bring back os matrix

* Enable direct `--weights URL` definition (ultralytics#3373)

* Enable direct `--weights URL` definition

@kalenmike this PR will enable direct --weights URL definition. Example use case:
```
python train.py --weights https://storage.googleapis.com/bucket/dir/model.pt
```

* cleanup

* bug fixes

* weights = attempt_download(weights)

* Update experimental.py

* Update hubconf.py

* return bug fix

* comment mirror

* min_bytes

* Update tutorial.ipynb (ultralytics#3368)

add Open in Kaggle badge

* `cv2.imread(img, -1)` for IMREAD_UNCHANGED (ultralytics#3379)

* Update datasets.py

* comment

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

* COCO evolution fix (ultralytics#3388)

* COCO evolution fix

* cleanup

* update print

* print fix

* Create `is_pip()` function (ultralytics#3391)

Returns `True` if file is part of pip package. Useful for contextual behavior modification.

```python
def is_pip():
    # Is file in a pip package?
    return 'site-packages' in Path(__file__).absolute().parts
```

* Revert "`cv2.imread(img, -1)` for IMREAD_UNCHANGED (ultralytics#3379)" (ultralytics#3395)

This reverts commit 67db4b6.

* Update FLOPs description (ultralytics#3422)

* Update README.md

* Changing FLOPS to FLOPs.

Co-authored-by: BuildTools <unconfigured@null.spigotmc.org>

* Parse URL authentication (ultralytics#3424)

* Parse URL authentication

* urllib.parse.unquote()

* improved error handling

* improved error handling

* remove %3F

* update check_file()

* Add FLOPs title to table (ultralytics#3453)

* Suppress jit trace warning + graph once (ultralytics#3454)

* Suppress jit trace warning + graph once

Suppress harmless jit trace warning on TensorBoard add_graph call. Also fix multiple add_graph() calls bug, now only on batch 0.

* Update train.py

* Update MixUp augmentation `alpha=beta=32.0` (ultralytics#3455)

Per VOC empirical results ultralytics#3380 (comment) by @developer0hye

* Add `timeout()` class (ultralytics#3460)

* Add `timeout()` class

* rearrange order

* Faster HSV augmentation (ultralytics#3462)

remove datatype conversion process that can be skipped

* Add `check_git_status()` 5 second timeout (ultralytics#3464)

* Add check_git_status() 5 second timeout

This should prevent the SSH Git bug that we were discussing @kalenmike

* cleanup

* replace timeout with check_output built-in timeout

* Improved `check_requirements()` offline-handling (ultralytics#3466)

Improve robustness of `check_requirements()` function to offline environments (do not attempt pip installs when offline).

* Add `output_names` argument for ONNX export with dynamic axes (ultralytics#3456)

* Add output names & dynamic axes for onnx export

Add output_names and dynamic_axes names for all outputs in torch.onnx.export. The first four outputs of the model will have names output0, output1, output2, output3

* use first output only + cleanup

Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Revert FP16 `test.py` and `detect.py` inference to FP32 default (ultralytics#3423)

* fixed inference bug ,while use half precision

* replace --use-half with --half

* replace space and PEP8 in detect.py

* PEP8 detect.py

* update --half help comment

* Update test.py

* revert space

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

* Add additional links/resources to stale.yml message (ultralytics#3467)

* Update stale.yml

* cleanup

* Update stale.yml

* reformat

* Update stale.yml HUB URL (ultralytics#3468)

* Stale `github.actor` bug fix (ultralytics#3483)

* Explicit `model.eval()` call `if opt.train=False` (ultralytics#3475)

* call model.eval() when opt.train is False

call model.eval() when opt.train is False

* single-line if statement

* cleanup

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

* check_requirements() exclude `opencv-python` (ultralytics#3495)

Fix for 3rd party or contrib versions of installed OpenCV as in ultralytics#3494.

* Earlier `assert` for cpu and half option (ultralytics#3508)

* early assert for cpu and half option

early assert for cpu and half option

* Modified comment

Modified comment

* Update tutorial.ipynb (ultralytics#3510)

* Reduce test.py results spacing (ultralytics#3511)

* Update README.md (ultralytics#3512)

* Update README.md

Minor modifications

* 850 width

* Update greetings.yml

revert greeting change as PRs will now merge to master.

Co-authored-by: Piotr Skalski <SkalskiP@users.noreply.github.com>
Co-authored-by: SkalskiP <piotr.skalski92@gmail.com>
Co-authored-by: Peretz Cohen <pizzaz93@users.noreply.github.com>
Co-authored-by: tudoulei <34886368+tudoulei@users.noreply.github.com>
Co-authored-by: chocosaj <chocosaj@users.noreply.github.com>
Co-authored-by: BuildTools <unconfigured@null.spigotmc.org>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
Co-authored-by: Sam_S <SamSamhuns@users.noreply.github.com>
Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai>
Co-authored-by: edificewang <609552430@qq.com>
SecretStar112 added a commit to SecretStar112/yolov5 that referenced this issue May 24, 2023
@SecretStar112
Update MixUp augmentation alpha=beta=32.0 (#3455)
ee582ae 
Per VOC empirical results ultralytics/yolov5#3380 (comment) by @developer0hye
SecretStar112 added a commit to SecretStar112/yolov5 that referenced this issue May 24, 2023
@SecretStar112 @SkalskiP
@pizzaz93 @tudoulei @chocosaj @developer0hye @SamSamhuns @PresageBoat
Merge develop branch into master (#3518)
c872f57 
* update ci-testing.yml (#3322)

* update ci-testing.yml

* update greetings.yml

* bring back os matrix

* update ci-testing.yml (#3322)

* update ci-testing.yml

* update greetings.yml

* bring back os matrix

* Enable direct `--weights URL` definition (#3373)

* Enable direct `--weights URL` definition

@kalenmike this PR will enable direct --weights URL definition. Example use case:
```
python train.py --weights https://storage.googleapis.com/bucket/dir/model.pt
```

* cleanup

* bug fixes

* weights = attempt_download(weights)

* Update experimental.py

* Update hubconf.py

* return bug fix

* comment mirror

* min_bytes

* Update tutorial.ipynb (#3368)

add Open in Kaggle badge

* `cv2.imread(img, -1)` for IMREAD_UNCHANGED (#3379)

* Update datasets.py

* comment

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

* COCO evolution fix (#3388)

* COCO evolution fix

* cleanup

* update print

* print fix

* Create `is_pip()` function (#3391)

Returns `True` if file is part of pip package. Useful for contextual behavior modification.

```python
def is_pip():
    # Is file in a pip package?
    return 'site-packages' in Path(__file__).absolute().parts
```

* Revert "`cv2.imread(img, -1)` for IMREAD_UNCHANGED (#3379)" (#3395)

This reverts commit 21a9607e00f1365b21d8c4bd81bdbf5fc0efea24.

* Update FLOPs description (#3422)

* Update README.md

* Changing FLOPS to FLOPs.

Co-authored-by: BuildTools <unconfigured@null.spigotmc.org>

* Parse URL authentication (#3424)

* Parse URL authentication

* urllib.parse.unquote()

* improved error handling

* improved error handling

* remove %3F

* update check_file()

* Add FLOPs title to table (#3453)

* Suppress jit trace warning + graph once (#3454)

* Suppress jit trace warning + graph once

Suppress harmless jit trace warning on TensorBoard add_graph call. Also fix multiple add_graph() calls bug, now only on batch 0.

* Update train.py

* Update MixUp augmentation `alpha=beta=32.0` (#3455)

Per VOC empirical results ultralytics/yolov5#3380 (comment) by @developer0hye

* Add `timeout()` class (#3460)

* Add `timeout()` class

* rearrange order

* Faster HSV augmentation (#3462)

remove datatype conversion process that can be skipped

* Add `check_git_status()` 5 second timeout (#3464)

* Add check_git_status() 5 second timeout

This should prevent the SSH Git bug that we were discussing @kalenmike

* cleanup

* replace timeout with check_output built-in timeout

* Improved `check_requirements()` offline-handling (#3466)

Improve robustness of `check_requirements()` function to offline environments (do not attempt pip installs when offline).

* Add `output_names` argument for ONNX export with dynamic axes (#3456)

* Add output names & dynamic axes for onnx export

Add output_names and dynamic_axes names for all outputs in torch.onnx.export. The first four outputs of the model will have names output0, output1, output2, output3

* use first output only + cleanup

Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Revert FP16 `test.py` and `detect.py` inference to FP32 default (#3423)

* fixed inference bug ,while use half precision

* replace --use-half with --half

* replace space and PEP8 in detect.py

* PEP8 detect.py

* update --half help comment

* Update test.py

* revert space

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

* Add additional links/resources to stale.yml message (#3467)

* Update stale.yml

* cleanup

* Update stale.yml

* reformat

* Update stale.yml HUB URL (#3468)

* Stale `github.actor` bug fix (#3483)

* Explicit `model.eval()` call `if opt.train=False` (#3475)

* call model.eval() when opt.train is False

call model.eval() when opt.train is False

* single-line if statement

* cleanup

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

* check_requirements() exclude `opencv-python` (#3495)

Fix for 3rd party or contrib versions of installed OpenCV as in ultralytics/yolov5#3494.

* Earlier `assert` for cpu and half option (#3508)

* early assert for cpu and half option

early assert for cpu and half option

* Modified comment

Modified comment

* Update tutorial.ipynb (#3510)

* Reduce test.py results spacing (#3511)

* Update README.md (#3512)

* Update README.md

Minor modifications

* 850 width

* Update greetings.yml

revert greeting change as PRs will now merge to master.

Co-authored-by: Piotr Skalski <SkalskiP@users.noreply.github.com>
Co-authored-by: SkalskiP <piotr.skalski92@gmail.com>
Co-authored-by: Peretz Cohen <pizzaz93@users.noreply.github.com>
Co-authored-by: tudoulei <34886368+tudoulei@users.noreply.github.com>
Co-authored-by: chocosaj <chocosaj@users.noreply.github.com>
Co-authored-by: BuildTools <unconfigured@null.spigotmc.org>
Co-authored-by: Yonghye Kwon <developer.0hye@gmail.com>
Co-authored-by: Sam_S <SamSamhuns@users.noreply.github.com>
Co-authored-by: Samridha Shrestha <samridha.shrestha@g42.ai>
Co-authored-by: edificewang <609552430@qq.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@developer0hye developer0hye

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Update MixUp augmentation alpha=beta=32.0 ultralytics/yolov5
2 participants
@glenn-jocher @developer0hye