Commit Graph
14 Commits
Author SHA1 Message Date
imyhxyandUltralyticsAssistant 1435a8eed6 Add timing cache to accelerate consequent .engine export (#13386)
* fix: typos

* feat: enable timing cache for engine export

* Auto-format by https://ultralytics.com/actions

---------

Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
2024-11-08 23:24:30 +01:00
imyhxy 94a6245617 Fix bug when enable --quad training option (#13355)
* fix: quad training

* fix: quad training in segmentation
2024-10-15 18:22:02 +02:00
imyhxy ca00c34c2a Fix docs typos in callbacks.py (#12750)
* Update callbacks.py

Signed-off-by: imyhxy <imyhxy@gmail.com>

* Update general.py

Signed-off-by: imyhxy <imyhxy@gmail.com>

---------

Signed-off-by: imyhxy <imyhxy@gmail.com>
2024-02-25 13:57:41 +01:00
imyhxyandGlenn Jocher 81f81d3e97 Fixed randrange warnings in Python>=3.10 (#11161)
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2023-03-23 20:30:10 +01:00
imyhxyandGlenn Jocher d223460f3a Fixed creation of empty directories in path was entered mistaken (#11174)
FFixed creation of empty directories in path was entered mistaken

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2023-03-23 20:27:46 +01:00
imyhxy 4db6757ef9 Fixed access 'names' from a DistributedDataParallel module (#11023) 2023-02-20 11:23:13 +01:00
imyhxy ca0a00784d Fixed wandb logger KeyError (#6637) 2022-02-14 17:08:36 +01:00
imyhxy 4e841b9b16 Reuse de_parallel() rather than is_parallel() (#6354) 2022-01-20 10:50:17 -10:00
imyhxyandGlenn Jocher a2f4a1799b TensorRT 7 anchor_grid compatibility fix (#6185)
* fix: TensorRT 7 incompatiable

* Add comment

* Add if: else and comment

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2022-01-04 11:09:25 -08:00
imyhxy a4207a202d Fix TensorRT potential unordered binding addresses (#5826)
* feat: change file suffix in pythonic way

* fix: enforce binding addresses order

* fix: enforce binding addresses order
2021-11-30 13:52:22 +01:00
imyhxyandGlenn Jocher 7a39803476 Export, detect and validation with TensorRT engine file (#5699)
* Export and detect with TensorRT engine file

* Resolve `isort`

* Make validation works with TensorRT engine

* feat: update export docstring

* feat: change suffix from *.trt to *.engine

* feat: get rid of pycuda

* feat: make compatiable with val.py

* feat: support detect with fp16 engine

* Add Lite to Edge TPU string

* Remove *.trt comment

* Revert to standard success logger.info string

* Fix Deprecation Warning

```
export.py:310: DeprecationWarning: Use build_serialized_network instead.
  with builder.build_engine(network, config) as engine, open(f, 'wb') as t:
```

* Revert deprecation warning fix

@imyhxy it seems we can't apply the deprecation warning fix because then export fails, so I'm reverting my previous change here.

* Update export.py

* Update export.py

* Update common.py

* export onnx to file before building TensorRT engine file

* feat: triger ONNX export failed early

* feat: load ONNX model from file

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-11-22 14:58:07 +01:00
imyhxy 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
imyhxyandfkwong 771ac6c53d Fixed logging level in distributed mode (#4284)
Co-authored-by: fkwong <huangfuqiang@transai.cn>
2021-08-03 13:11:42 +02:00
imyhxy 4495e00016 Fix indentation in log_training_progress() (#4126) 2021-07-23 14:55:00 +02:00