32dd1614f4
Update greetings.yml for auto-rebase on PR ( #2272 )
3 years ago
95aefea493
Dynamic ONNX engine generation ( #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>
3 years ago
e27ca0d845
Update minimum stride to 32 ( #2266 )
3 years ago
095d2c11d8
Created using Colaboratory
3 years ago
6f5d6fcdaa
Robust objectness loss balancing ( #2256 )
3 years ago
c09964c27c
Update inference default to multi_label=False ( #2252 )
* Update inference default to multi_label=False
* bug fix
* Update plots.py
* Update plots.py
3 years ago
ab2da5edc8
Merge remote-tracking branch 'origin/master'
3 years ago
47faf95079
reset head
3 years ago
5f42643a53
Unified hub and detect.py box and labels plotting ( #2243 )
3 years ago
db28ce61ac
Improved hubconf.py CI tests ( #2251 )
3 years ago
9d87307784
YOLOv5 Hub URL inference bug fix ( #2250 )
* Update common.py
* Update common.py
* Update common.py
3 years ago
d2e754b67b
Add isdocker() ( #2232 )
* Add isdocker()
* Update general.py
* Update general.py
3 years ago
5a40ce65ce
Update CI badge ( #2230 )
3 years ago
26c2e54c8f
Add check_imshow() ( #2231 )
* Add check_imshow()
* Update general.py
* Update general.py
3 years ago
f8464b4f66
Update yolo.py channel array ( #2223 )
3 years ago
7b833e37bf
LoadStreams() frame loss bug fix ( #2222 )
3 years ago
3ff783c18f
TTA augument boxes one pixel shifted in de-flip ud and lr ( #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>
3 years ago
3e560e2fae
YOLOv5 PyTorch Hub results.save() method retains filenames ( #2194 )
* save results with name
* debug
* save original imgs names
* Update common.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 years ago
17ac94b796
Created using Colaboratory
3 years ago
bdd88e1ed7
YOLOv5 Segmentation Dataloader Updates ( #2188 )
* Update C3 module
* Update C3 module
* Update C3 module
* Update C3 module
* update
* update
* update
* update
* update
* update
* update
* update
* update
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update datasets
* update
* update
* update
* update attempt_downlaod()
* merge
* merge
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* parameterize eps
* comments
* gs-multiple
* update
* max_nms implemented
* Create one_cycle() function
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* GitHub API rate limit fix
* update
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* ComputeLoss
* astuple
* epochs
* update
* update
* ComputeLoss()
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* merge
* merge
* merge
* merge
* update
* update
* update
* update
* commit=tag == tags[-1]
* Update cudnn.benchmark
* update
* update
* update
* updates
* updates
* updates
* updates
* updates
* updates
* updates
* update
* update
* update
* update
* update
* mosaic9
* update
* update
* update
* update
* update
* update
* institute cache versioning
* only display on existing cache
* reverse cache exists booleans
3 years ago
404749a33c
PyTorch Hub results.save('path/to/dir') ( #2179 )
3 years ago
a5d5f9262d
Changed socket port and added timeout ( #2176 )
3 years ago
c9bda112ae
Update utils/datasets.py to support .webp files ( #2174 )
Simply added 'webp' as an image format to the img_formats array so that webp image files can be used as training data.
3 years ago
ace3e02e40
Update requirements.txt ( #2173 )
3 years ago
c32b0aff76
Update detect.py ( #2167 )
Without this cv2.imshow opens a window but nothing is visible
3 years ago
a5359f6c32
Update data-autodownload background tasks ( #2154 )
* Update get_coco.sh
* Update get_voc.sh
3 years ago
6b634c6b87
Linear LR scheduler option ( #2150 )
* Linear LR scheduler option
* Update train.py
3 years ago
ad839eda38
Update train.py ( #2149 )
3 years ago
86897e3663
Update train.py test batch_size ( #2148 )
* Update train.py
* Update loss.py
3 years ago
e9b3de463a
Unique *.cache filenames fix ( #2134 )
* fix #2121
* Update test.py
* Update train.py
* Update autoanchor.py
* Update datasets.py
* Update log_dataset.py
* Update datasets.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 years ago
4bdc5a397e
LoadImages() pathlib update ( #2140 )
3 years ago
73a0669930
Start setup for improved W&B integration ( #1948 )
* Add helper functions for wandb and artifacts
* cleanup
* Reorganize files
* Update wandb_utils.py
* Update log_dataset.py
We can remove this code, as the giou hyp has been deprecated for a while now.
* Reorganize and update dataloader call
* yaml.SafeLoader
* PEP8 reformat
* remove redundant checks
* Add helper functions for wandb and artifacts
* cleanup
* Reorganize files
* Update wandb_utils.py
* Update log_dataset.py
We can remove this code, as the giou hyp has been deprecated for a while now.
* Reorganize and update dataloader call
* yaml.SafeLoader
* PEP8 reformat
* remove redundant checks
* Update util files
* Update wandb_utils.py
* Remove word size
* Change path of labels.zip
* remove unused imports
* remove --rect
* log_dataset.py cleanup
* log_dataset.py cleanup2
* wandb_utils.py cleanup
* remove redundant id_count
* wandb_utils.py cleanup2
* rename cls
* use pathlib for zip
* rename dataloader to dataset
* Change import order
* Remove redundant code
* remove unused import
* remove unused imports
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 years ago
9646ca438a
Update plot_study() ( #2112 )
3 years ago
be9edffded
Update test.py --task speed and study ( #2099 )
* Add --speed benchmark
* test range 256 - 1536
* update
* update
* update
* update
3 years ago
a18efc3a73
Add variable-stride inference support ( #2091 )
3 years ago
aa02b94825
Add Kaggle badge ( #2090 )
3 years ago
eeb2bbf648
Add Kaggle badge ( #2090 )
* Update README.md
* Update greetings.yml
* Created using Colaboratory
3 years ago
170d12e506
Add Amazon Deep Learning AMI environment ( #2085 )
* Update greetings.yml
* Update README.md
3 years ago
64628d6fc5
Update tutorial.ipynb
3 years ago
6e6f77be47
Add YOLOv5-P6 models ( #2083 )
3 years ago
6bfa9c2422
GhostConv update ( #2082 )
3 years ago
2acbe9699a
W&B epoch logging update ( #2073 )
3 years ago
630ec06af6
Update to colors.TABLEAU_COLORS ( #2069 )
3 years ago
f639e14e4d
Metric-Confidence plots feature addition ( #2057 )
* Metric-Confidence plots feature addition
* cleanup
* Metric-Confidence plots feature addition
* cleanup
* Update run-once lines
* cleanup
* save all 4 curves to wandb
3 years ago
2a835c79a9
Update run-once lines ( #2058 )
3 years ago
f59f80114c
Add 'exclude' tuple to check_requirements() ( #2041 )
3 years ago
59c21c7bcb
W&B log epoch ( #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
3 years ago
08d3119e09
Add histogram equalization fcn ( #2049 )
3 years ago
d68afedb32
Confusion matrix native image-space fix ( #2046 )
Make sure the labels and predictions are equally scaled on confusion_matrix.process_batch
3 years ago
8fcbe43423
Check im.format during dataset caching ( #2042 )
* Check im.format during dataset caching
* Update datasets.py
3 years ago
Glenn Jocher
Aditya Lohia
Yann Defretin
VdLMV
Daniel Khromov
NanoCode012
Transigent
ab-101
train255
Ayush Chaurasia
ramonhollands