2b3109eeb0
Fix DDP destruction `LOGGER.info()` ( #4863 )
2021-09-20 13:12:48 +02:00
4c839eeb10
Simplify `check_requirements()` usage ( #4855 )
...
* Simplify `check_requirements()` usage
* remove assert, print()
2021-09-18 18:34:30 +02:00
4d1a2ac87e
Update `sys.path.append(str(ROOT))` ( #4852 )
...
* Update `sys.path.append(str(ROOT))`
* Cleanup
2021-09-18 15:02:08 +02:00
3732f9ac8a
Refactor argparser printing to `print_args()` ( #4850 )
...
* Refactor argparser printing to `print_args()`
* Cleanup
2021-09-18 14:16:19 +02:00
621b6d5ba8
Evolution `--resume` fix ( #4802 )
...
Also disable `/weights` dir creation when evolving as no weights are saved and empty folder causes user expectations of weights.
2021-09-15 13:13:33 +02:00
c47be26f34
Replace `path.absolute()` with `path.resolve()` ( #4763 )
2021-09-11 22:46:33 +02:00
c5360f6e70
Fix `--data from_HUB.zip` ( #4732 )
...
@KalenMike
2021-09-09 18:01:59 +02:00
a2b3c71636
Add suffix checks ( #4711 )
...
* Add suffix checks
* Cleanup
* Cleanup2
* Cleanup3
2021-09-08 14:36:12 +02:00
2317f86ca4
Optimised Callback Class to Reduce Code and Fix Errors ( #4688 )
...
* added callbacks
* added back callback to main
* added save_dir to callback output
* reduced code count
* updated callbacks
* added default callback class to main, added missing parameters to on_model_save
* Glenn updates
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-09-07 18:32:15 +02:00
548745181a
EarlyStopper updates ( #4679 )
2021-09-05 19:09:53 +02:00
f64fab5825
Fixed 'meta' and 'hyp' may out of order when using evolve ( #4657 )
...
* Fixed 'meta' and 'hyp' may out of order when using evolve
* Update gitignore
2021-09-05 17:43:09 +02:00
50a9828679
DDP `torch.jit.trace()` `--sync-bn` fix ( #4615 )
...
* Remove assert
* debug0
* trace=not opt.sync
* sync to sync_bn fix
* Cleanup
2021-08-30 18:35:07 +02:00
de44376d1b
Create `Annotator()` class ( #4591 )
...
* Add Annotator() class
* Download Arial
* 2x for loop
* Cleanup
* tuple 2 list
* max_size=1920
* bold logging results to
* tolist()
* im = annotator.im
* PIL save in detect.py
* Smart asarray in detect.py
* revert to cv2.imwrite
* Cleanup
* Return result asarray
* Add `Profile()` profiler
* CamelCase Timeout
* Resize after mosaic
* pillow>=8.0.0
* daemon imwrite
* Add cv2 support
* Remove plot_wh_methods and plot_one_box
* pil=False for hubconf.py annotations
* im.shape bug fix
* colorstr common.py
* join daemons
* Update t.daemon
* Removed daemon saving
2021-08-29 16:46:13 +02:00
d7aa3f153d
Remove `image_weights` DDP code ( #4579 )
...
* Initial commit
* Update
2021-08-28 19:17:21 +02:00
93cc015748
Add EarlyStopping feature ( #4576 )
...
* Add EarlyStopping feature
* Add comment
* Cleanup
* Cleanup2
* debug
* debug2
* debug3
* debug3
* debug4
* debug5
* debug6
* debug7
* debug8
* debug9
* debug10
* debug11
* debug12
* Cleanup
* Add TODO for known DDP issue
2021-08-28 19:03:52 +02:00
19d03a955c
Remove DDP process group timeout ( #4422 )
2021-08-15 18:32:41 +02:00
24bea5e4b7
Standardize headers and docstrings ( #4417 )
...
* Implement new headers
* Reformat 1
* Reformat 2
* Reformat 3 - math
* Reformat 4 - yaml
2021-08-14 21:17:51 +02:00
ce7deec440
`int(mlc)` ( #4385 )
2021-08-11 17:32:13 +02:00
86c7150cfd
Update newline ( #4308 )
2021-08-04 17:41:38 +02:00
e78aeac973
Evolve in CSV format ( #4307 )
...
* Update evolution to CSV format
* Update
* Update
* Update
* Update
* Update
* reset args
* reset args
* reset args
* plot_results() fix
* Cleanup
* Cleanup2
2021-08-04 17:13:38 +02:00
2d99063201
Feature `python train.py --cache disk` ( #4049 )
...
* Add cache-on-disk and cache-directory to cache images on disk
* Fix load_image with cache_on_disk
* Add no_cache flag for load_image
* Revert the parts('logging' and a new line) that do not need to be modified
* Add the assertion for shapes of cached images
* Add a suffix string for cached images
* Fix boundary-error of letterbox for load_mosaic
* Add prefix as cache-key of cache-on-disk
* Update cache-function on disk
* Add psutil in requirements.txt
* Update train.py
* Cleanup1
* Cleanup2
* Skip existing npy
* Include re-space
* Export return character fix
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-08-02 18:47:24 +02:00
b74929c910
Add `train.py` and `val.py` callbacks ( #4220 )
...
* added callbacks
* Update callbacks.py
* Update train.py
* Update val.py
* Fix CamlCase add staticmethod
* Refactor logger into callbacks
* Cleanup
* New callback on_val_image_end()
* Add curves and results images to TensorBoard
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-08-01 00:18:07 +02:00
bceb57b910
Add `python train.py --freeze N` argument ( #4238 )
...
* Add freeze as an argument
I train on different platforms and sometimes I want to freeze some layers. I have to go into the code and change it and also keep track of how many layers I froze on what platform. Please add the number of layers to freeze as an argument in future versions thanks.
* Update train.py
* Update train.py
* Cleanup
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-07-30 17:39:48 +02:00
8d3c3ef45c
Fix weight decay comment ( #4228 )
2021-07-30 01:35:39 +02:00
c2c958c350
Explicit `requirements.txt` location ( #4225 )
2021-07-29 17:29:39 +02:00
b60b62e874
PyCharm reformat ( #4209 )
...
* PyCharm reformat
* YAML reformat
* Markdown reformat
2021-07-28 23:35:14 +02:00
e88e8f7a98
W&B: Restructure code to support the new dataset_check() feature ( #4197 )
...
* Improve docstrings and run names
* default wandb login prompt with timeout
* return key
* Update api_key check logic
* Properly support zipped dataset feature
* update docstring
* Revert tuorial change
* extend changes to log_dataset
* add run name
* bug fix
* bug fix
* Update comment
* fix import check
* remove unused import
* Hardcore .yaml file extension
* reduce code
* Reformat using pycharm
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-07-28 17:40:08 +02:00
5d66e48723
Train from `--data path/to/dataset.zip` feature ( #4185 )
...
* Train from `--data path/to/dataset.zip` feature
* Update dataset_stats()
* cleanup
* cleanup2
2021-07-28 02:04:10 +02:00
0ad6301c96
Update script headers ( #4163 )
...
* Update download script headers
* cleanup
* bug fix attempt
* bug fix attempt2
* bug fix attempt3
* cleanup
2021-07-26 15:23:33 +02:00
96e36a7c91
New CSV Logger ( #4148 )
...
* New CSV Logger
* cleanup
* move batch plots into Logger
* rename comment
* Remove total loss from progress bar
* mloss :-1 bug fix
* Update plot_results()
* Update plot_results()
* plot_results bug fix
2021-07-25 19:06:37 +02:00
efe60b5681
Refactor train.py and val.py `loggers` ( #4137 )
...
* Update loggers
* Config
* Update val.py
* cleanup
* fix1
* fix2
* fix3 and reformat
* format sweep.py
* Logger() class
* cleanup
* cleanup2
* wandb package import fix
* wandb package import fix2
* txt fix
* fix4
* fix5
* fix6
* drop wandb into utils/loggers
* fix 7
* rename loggers/wandb_logging to loggers/wandb
* Update message
* Update message
* Update message
* cleanup
* Fix x axis bug
* fix rank 0 issue
* cleanup
2021-07-25 01:18:39 +02:00
63dd65e7ed
Update train.py ( #4136 )
...
* Refactor train.py
* Update imports
* Update imports
* Update optimizer
* cleanup
2021-07-24 16:11:39 +02:00
2c073cd207
Add train.py ``--img-size` floor ( #4099 )
2021-07-21 16:50:47 +02:00
f7d8562060
`val.py` refactor ( #4053 )
...
* val.py refactor
* cleanup
* cleanup
* cleanup
* cleanup
* save after eval
* opt.imgsz bug fix
* wandb refactor
* dataloader to train_loader
* capitalize global variables
* runs/hub/exp to runs/detect/exp
* refactor wandb logging
* Refactor wandb operations (#4061 )
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
2021-07-19 10:43:01 +02:00
951922c735
Add `--sync-bn` known issue ( #4032 )
...
* Add `--sync-bn` known issue
* Update train.py
2021-07-17 13:07:19 +02:00
720aaa65c8
Rename `test.py` to `val.py` ( #4000 )
2021-07-14 15:43:54 +02:00
e7888af94c
Fix inconsistent NMS IoU value for COCO ( #3934 )
...
Evaluation of 'best' and 'last' models will use the same params as the evaluation during the training phase.
This PR fixes https://github.com/ultralytics/yolov5/issues/3907
2021-07-08 15:29:02 +02:00
8930e22cce
Evolution commented `hyp['anchors']` fix ( #3887 )
...
Fix for `KeyError: 'anchors'` error when start hyperparameter evolution:
```bash
python train.py --evolve
```
```bash
Traceback (most recent call last):
File "E:\yolov5\train.py", line 623, in <module>
hyp[k] = max(hyp[k], v[1]) # lower limit
KeyError: 'anchors'
```
2021-07-05 12:48:27 +02:00
d3e9d69850
`--evolve 300` generations CLI argument ( #3863 )
...
* evolve command accepts argument for number of generations
* evolve generations argument used in evolve for loop
* evolve argument boolean fixes
* default to 300 evolve generations
* Update train.py
Co-authored-by: John San Soucie <jsansoucie@whoi.edu>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-07-04 12:14:35 +02:00
c6c88dc601
Copy-Paste augmentation for YOLOv5 ( #3845 )
...
* Copy-paste augmentation initial commit
* if any segments
* Add obscuration rejection
* Add copy_paste hyperparameter
* Update comments
2021-07-01 00:35:04 +02:00
3974d725b6
Fix warmup `accumulate` ( #3722 )
...
* gradient accumulation during warmup in train.py
Context:
`accumulate` is the number of batches/gradients accumulated before calling the next optimizer.step().
During warmup, it is ramped up from 1 to the final value nbs / batch_size.
Although I have not seen this in other libraries, I like the idea. During warmup, as grads are large, too large steps are more of on issue than gradient noise due to small steps.
The bug:
The condition to perform the opt step is wrong
> if ni % accumulate == 0:
This produces irregular step sizes if `accumulate` is not constant. It becomes relevant when batch_size is small and `accumulate` changes many times during warmup.
This demo also shows the proposed solution, to use a ">=" condition instead:
https://colab.research.google.com/drive/1MA2z2eCXYB_BC5UZqgXueqL_y1Tz_XVq?usp=sharing
Further, I propose not to restrict the number of warmup iterations to >= 1000. If the user changes hyp['warmup_epochs'], this causes unexpected behavior. Also, it makes evolution unstable if this parameter was to be optimized.
* replace last_opt_step tracking by do_step(ni)
* add docstrings
* move down nw
* Update train.py
* revert math import move
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-06-28 12:25:13 +02:00
92d49fde35
Update seeds for single-GPU reproducibility ( #3789 )
...
For seed=0 on single-GPU.
2021-06-26 15:42:40 +02:00
09246a5a33
fix/incorrect_fitness_import ( #3770 )
2021-06-25 16:16:18 +02:00
f2d97ebb25
Remove DDP MultiHeadAttention fix ( #3768 )
2021-06-25 12:52:05 +02:00
f79d7479da
Add optional dataset.yaml `path` attribute ( #3753 )
...
* Add optional dataset.yaml `path` attribute
@KalenMike
* pass locals to python scripts
* handle lists
* update coco128.yaml
* Capitalize first letter
* add test key
* finalize GlobalWheat2020.yaml
* finalize objects365.yaml
* finalize SKU-110K.yaml
* finalize SKU-110K.yaml
* finalize VisDrone.yaml
* NoneType fix
* update download comment
* voc to VOC
* update
* update VOC.yaml
* update VOC.yaml
* remove dashes
* delete get_voc.sh
* force coco and coco128 to ../datasets
* Capitalize Argoverse_HD.yaml
* Capitalize Objects365.yaml
* update Argoverse_HD.yaml
* coco segments fix
* VOC single-thread
* update Argoverse_HD.yaml
* update data_dict in test handling
* create root
2021-06-25 01:25:03 +02:00
ae4261c774
Force non-zero hyp evolution weights `w` ( #3748 )
...
Fix for https://github.com/ultralytics/yolov5/issues/3741
2021-06-23 12:56:22 +02:00
fdc22398fa
Create `data/hyps` directory ( #3747 )
2021-06-23 12:49:38 +02:00
1f69d12591
Update 4 main ops for paths and .run() ( #3715 )
...
* Add yolov5/ to path
* rename functions to run()
* cleanup
* rename fix
* CI fix
* cleanup find models/export.py
2021-06-21 17:25:04 +02:00
75c0ff43af
[x]W&B: Don't resume transfer learning runs ( #3604 )
...
* Allow config cahnge
* Allow val change in wandb config
* Don't resume transfer learning runs
* Add entity in log dataset
2021-06-21 14:00:25 +02:00
e8810a53e8
Update DDP backend `if dist.is_nccl_available()` ( #3705 )
2021-06-20 17:15:42 +02:00
Glenn Jocher
Kalen Michael
imyhxy
junji hashimoto
IneovaAI
Ayush Chaurasia
Eldar Kurtic
san-soucie
yellowdolphin
Piotr Skalski