Ankle/yolov5_birdproject
1
0 Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
1,753 Commits 1 Branch 0 Tags
d8b5beb0b0a5cb3ec3ea20e9fff415057dcf25f6
Commit Graph
1753 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Glenn Jocher d8b5beb0b0 Fix2 select_device() for Multi-GPU (#6461) 
* Fix2 select_device() for Multi-GPU

* Cleanup

* Cleanup

* Simplify error message

* Improve assert

* Update torch_utils.py
 2022-01-28 08:18:01 +01:00
Glenn Jocher 856d4e5733 Fix select_device() for Multi-GPU (#6434) 
* Fix `select_device()` for Multi-GPU

Possible fix for https://github.com/ultralytics/yolov5/issues/6431

* Update torch_utils.py

* Update torch_utils.py

* Update torch_utils.py

* Update torch_utils.py

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update
 2022-01-26 23:47:00 +01:00
Glenn Jocher fe7de6a82d Revert "Remove dataset_stats() autodownload capability (#6303)" (#6442) 
This reverts commit 3119b2f27c.
 2022-01-26 19:10:59 +01:00
toschi23 3b7ac28ed1 Add *.asf video support (#6436) 2022-01-26 14:26:02 +01:00
Glenn Jocher d5966c93f1 Namespace VERBOSE env variable to YOLOv5_VERBOSE (#6428) 
* Verbose updates

* Verbose updates
 2022-01-25 17:57:27 -05:00
Glenn Jocher ff8646cdea Update workflows (#6427) 
* Workflow updates

* quotes fix

* best to weights fix
 2022-01-25 17:33:22 -05:00
Motoki KimuraandGlenn Jocher 16563ac5b5 Prefer tflite_runtime for TFLite inference if installed (#6406) 
* import tflite_runtime if tensorflow not installed

* rename tflite to tfli

* Attempt tflite_runtime for all TFLite workflows

Also rename tfli to tfl

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-01-25 07:24:24 -08:00
Jonathan SamelsonandGlenn Jocher ed9bac8392 Rename logger from 'utils.logger' to 'yolov5' (#6421) 
* Gave a more explicit name to the logger

* Cleanup

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-01-25 07:21:06 -08:00
Glenn Jocher cfecd903a3 Update greetings.yaml email address (#6412) 
* Update `greetings.yaml` email address

* Update greetings.yml
 2022-01-24 15:28:52 -08:00
Glenn Jocher 482af479c0 Add detect.py GIF video inference (#6410) 
* Add detect.py GIF video inference

* Cleanup
 2022-01-24 13:11:11 -08:00
MatthiasandGlenn Jocher 8efe97719c Add stop_training=False flag to callbacks (#6365) 
* New flag 'stop_training' in util.callbacks.Callbacks class to prematurely stop training from callback handler

* Removed most of the new  checks, leaving only the one after calling 'on_train_batch_end'

* Cleanup

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-01-22 16:37:21 -10:00
Glenn Jocher c43439aa31 Add albumentations to Dockerfile (#6392) 2022-01-21 21:06:02 -10:00
Glenn Jocher bd815d48df FROM nvcr.io/nvidia/pytorch:21.10-py3 (#6379) 
21.12 generates dockerhub errors so rolling back to 21.10 with latest pytorch install. Not sure if this torch install will work on non-GPU dockerhub autobuild so this is an experiment.
 2022-01-20 19:15:04 -10:00
Glenn Jocher 1b41a1d059 FROM nvcr.io/nvidia/pytorch:21.12-py3 (#6377) 2022-01-20 17:59:41 -10:00
Ayush ChaurasiaandGlenn Jocher 9bcc32a5bf Flush callbacks when on --evolve (#6374) 
* log best.pt metrics at train end

* update

* Update __init__.py

* flush callbacks when using evolve

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-01-20 13:22:47 -10:00
sitecao e1893c894a DEVICE_COUNT instead of WORLD_SIZE to calculate nw (#6324) 2022-01-20 13:06:26 -10:00
imyhxy 4e841b9b16 Reuse de_parallel() rather than is_parallel() (#6354) 2022-01-20 10:50:17 -10:00
johnk2hawaii 9708cf56ea New environment variable VERBOSE (#6353) 
New environment variable `VERBOSE`
 2022-01-19 14:32:19 -10:00
Glenn Jocherandpre-commit-ci[bot] 750c42e43e export.py automatic forward_export (#6352) 
* `export.py` automatic `forward_export`

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-01-19 12:24:40 -10:00
Glenn Jocher e5219099cd Created using Colaboratory 2022-01-19 10:18:29 -10:00
Glenn Jocher 0cf932bf63 export.py return exported files/dirs (#6343) 
* `export.py` return exported files/dirs

* Path to str
 2022-01-18 15:18:23 -10:00
Glenn Jocher e2e95b2d8e TensorRT assert im.device.type != 'cpu' on export (#6340) 
* TensorRT `assert im.device.type != 'cpu'` on export

* Update export.py
 2022-01-18 13:52:25 -10:00
Glenn Jocher fd55271c04 Console corrupted -> corrupt (#6338) 
* Console corrupted -> corrupt 

Minor style changes.

* Update export.py
 2022-01-18 10:49:26 -10:00
Glenn Jocher 3119b2f27c Remove dataset_stats() autodownload capability (#6303) 
* Remove `dataset_stats()` autodownload capability

@kalenmike security update per Slack convo

* Update datasets.py
 2022-01-18 10:04:49 -10:00
OtfotandGlenn Jocher db1f83be63 Fix train.py parameter groups desc error (#6318) 
* Fix `train.py` parameter groups desc error

* Cleanup

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-01-16 20:58:34 -10:00
Glenn Jocher 436ffc417a select_device() cleanup (#6302) 
* `select_device()` cleanup

* Update torch_utils.py

* Update torch_utils.py

* Update torch_utils.py

* Update torch_utils.py

* Update torch_utils.py
 2022-01-14 15:48:15 -10:00
Henry a1a9c6884c Fixing bug multi-gpu training (#6299) 
* Fixing bug multi-gpu training

This solves this issue: https://github.com/ultralytics/yolov5/issues/6297#issue-1103853348

* Update torch_utils.py for pep8
 2022-01-14 10:11:06 -10:00
Glenn Jocher e7bf38277f Fix device count check (#6290) 
* Fix device count check()

* Update torch_utils.py

* Update torch_utils.py

* Update hubconf.py
 2022-01-13 21:23:03 -10:00
Glenn Jocher af001349e4 Add is_kaggle() function (#6285) 
* Add `is_kaggle()` function

Return True if environment is Kaggle Notebook.

* Remove root loggers only if is_kaggle() == True

* Update general.py
 2022-01-13 12:39:42 -10:00
Glenn Jocher 80473a6551 Update export.py with Detect, Validate usages (#6280) 2022-01-12 15:48:40 -10:00
Glenn Jocherandpre-commit-ci[bot] f3085accd3 Enable ONNX --half FP16 inference (#6268) 
* Enable ONNX ``--half` FP16 inference

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-01-11 10:13:17 -10:00
Glenn Jocher b3eaf5008b TensorRT pip install 2022-01-10 16:49:10 -10:00
Jinwoong YooandGlenn Jocher 9b13a594e9 Fix cmd string on tfjs export (#6243) 
* Fix cmd string on tfjs export

* Cleanup

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-01-09 20:40:47 -10:00
Glenn Jocher 6865d19a92 TensorRT 7 export fix (#6235) 2022-01-07 09:31:17 -08:00
Glenn Jocher 33a67b4918 Update P2-P7 models/hub variants (#6230) 
* Update p2-p7 `models/hub` variants

* Update common.py

* AutoAnchor camelcase corrections
 2022-01-06 11:08:09 -08:00
Glenn Jocher ad565e31d2 Update README speed reproduction command (#6228) 2022-01-06 09:55:31 -08:00
Glenn Jocher f80c463010 Attempt edgetpu-compiler autoinstall (#6223) 
* Attempt `edgetpu-compiler` autoinstall

Attempt to install edgetpu-compiler dependency if missing on Linux.

* Update export.py

* Update export.py
 2022-01-05 20:57:20 -08:00
Glenn Jocher b4ac3df6ff Add edgetpu_compiler checks (#6218) 
* Add `edgetpu_compiler` checks

* Update export.py

* Update export.py

* Update export.py

* Update export.py

* Update export.py

* Update export.py
 2022-01-05 14:55:04 -08:00
Glenn Jocher 00d7b97869 TFLite --int8 'flatbuffers==1.12' fix 2 (#6217) 
* TFLite `--int8` 'flatbuffers==1.12' fix 2

Reorganizes #6216 fix to update before `tensorflow` import so no restart required.

* Update export.py
 2022-01-05 13:34:36 -08:00
Glenn Jocher 8125ec5d42 TFLite --int8 'flatbuffers==1.12' fix (#6216) 
* TFLite `--int8` 'flatbuffers==1.12' fix

Temporary workaround for TFLite INT8 export.

* Update export.py

* Update export.py
 2022-01-05 13:01:21 -08:00
Glenn Jocher 5402753a53 Edge TPU compiler comment (#6196) 
* Edge TPU compiler comment

* 7 to 8 fix
 2022-01-04 19:36:12 -08:00
Glenn Jocher 9e9219fe17 Fix nan-robust stream FPS (#6198) 
Fix for Webcam stop working suddenly (Issue #6197)
 2022-01-04 19:32:42 -08:00
Glenn Jocher b5b56a3c88 Add CoreML inference (#6195) 
* Add Apple CoreML inference

* Cleanup
 2022-01-04 17:49:09 -08:00
Glenn Jocher 7b31a531b4 Add tensorrt>=7.0.0 checks (#6193) 
* Add `tensorrt>=7.0.0` checks

* Update export.py

* Update common.py

* Update export.py
 2022-01-04 13:39:13 -08:00
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
Yin RongyinrongGlenn Jocher
 		fb839298a1 Fix TorchScript on mobile export (#6183) 
* fix export of TorchScript on mobile

* Cleanup

Co-authored-by: yinrong <yinrong@xiaomi.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-01-03 20:25:48 -08:00
Glenn Jocher 5bd6a97b18 Global export format sort (#6182) 
* Global export sort

* Cleanup
 2022-01-03 20:08:15 -08:00
Glenn Jocher 7cad6597bb Ignore *_openvino_model/ dir (#6180) 2022-01-03 18:43:21 -08:00
Glenn Jocher 63a4d862aa Add OpenVINO inference (#6179) 2022-01-03 15:41:26 -08:00
Glenn Jocher b4a29b5a8d Update NMS max_wh=7680 for 8k images (#6178) 2022-01-03 10:54:52 -08:00