e97d129db4
Update export.py with --train mode argument ( #3066 )
2021-05-07 13:10:07 +02:00
f2de1ad2aa
Comment fix ( #3058 )
...
Co-authored-by: kepler62f <>
2021-05-07 12:28:55 +02:00
3ef3a95cfa
Do not optimize CoreML TorchScript model ( #3055 )
2021-05-06 17:23:33 +02:00
b8be76f915
Add get_coco128.sh for downloading the coco128 dataset ( #3047 )
...
* Add get_coco128.sh
* Update get_coco128.sh
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-05-06 13:44:14 +02:00
b18ca31ff5
use check_file for --data ( #3035 )
2021-05-05 14:28:19 +02:00
85b6fdda0f
FROM nvcr.io/nvidia/pytorch:21.03-py3
...
Issues with 21.04
2021-05-05 01:00:12 +02:00
4c7d686d7e
FROM nvcr.io/nvidia/pytorch:21.04-py3 ( #3030 )
2021-05-05 00:16:35 +02:00
8cab907f60
download() ThreadPool update ( #3027 )
...
* download() ThreadPool update
* update train image count
* cid + 1
2021-05-04 23:37:31 +02:00
5189b3addb
Objects365 Update
2021-05-04 02:25:14 +02:00
b292837e36
Fix ONNX export using --grid --simplify --dynamic simultaneously ( #2982 )
...
* Update yolo.py
* Update export.py
* fix export grid
* Update export.py, remove detect export attribute
* rearrange if order
* remove --grid, default inplace=False
* rename exp_dynamic to onnx_dynamic, comment
* replace bs with 1 in anchor_grid[i] index 0
* Update export.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-05-03 19:01:29 +02:00
41cc7caee6
Add NMS threshold checks ( #3020 )
...
* Add NMS threshold checks
* fix
2021-05-03 15:07:20 +02:00
fcd57028d2
Add is_colab() function ( #3018 )
2021-05-03 12:37:50 +02:00
e2a80c6c0f
Add support for FP16 (half) to export.py ( #3010 )
...
* Added support for fp16 (half) to export.py
* minimize code additions
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-05-02 22:42:33 +02:00
31ee54c28c
Hubconf.py bug fix ( #3007 )
2021-05-01 18:15:17 +02:00
7c89c829e3
cleanup
2021-05-01 17:48:12 +02:00
c1a44ed9c5
Update hubconf.py for unified loading ( #3005 )
2021-05-01 17:35:02 +02:00
37eaffec7d
Curl update ( #3004 )
...
* Curl update
* Curl update
2021-05-01 17:29:51 +02:00
4d7bca7648
Add unzip flag to download() ( #3002 )
2021-05-01 12:37:41 +02:00
f55730ee9c
Objects365 bug fix
2021-05-01 01:03:09 +02:00
54652fe3ff
Objects365 update
2021-05-01 00:16:58 +02:00
801b469878
Improve performance of dataset Logger ( #2943 )
...
* Improve performance of Dataset Logger
* Fix scaling bug
2021-04-30 21:54:26 +02:00
d08575ee5e
PyTorch Hub load directly when possible ( #2986 )
2021-04-30 14:59:51 +02:00
9b91db6d1a
Created using Colaboratory
2021-04-30 13:15:31 +02:00
41f5cc5637
YOLOv5 AWS Inferentia Inplace compatibility updates ( #2953 )
...
* Added flag to enable/disable all inplace and assignment operations
* Removed shape print statements
* Scope Detect/Model import to avoid circular dependency
* PEP8
* create _descale_pred()
* replace lost space
* replace list with tuple
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-04-30 12:54:48 +02:00
955eea8b96
Make cache saving optional ( #2977 )
2021-04-30 00:56:44 +02:00
a833ee2a46
Update check_requirements() exclude list ( #2974 )
2021-04-29 21:16:23 +02:00
dbce1bc54c
Objects365 Dataset ( #2932 )
...
* add object365
* ADD CONVERSION SCRIPT
* fix transcript
* Reformat and simplify
* spelling
* Update get_objects365.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-04-29 20:43:33 +02:00
33712d6dd0
Global Wheat Detection 2020 Dataset Auto-Download ( #2968 )
...
* Create GlobalWheat2020.yaml
* Update and rename visdrone.yaml to VisDrone.yaml
* Update GlobalWheat2020.yaml
2021-04-28 20:11:02 +02:00
2c7c075fb1
Update restapi.py ( #2967 )
2021-04-28 17:50:07 +02:00
57812df68c
New Colors() class ( #2963 )
2021-04-28 16:05:14 +02:00
4200674a13
Add yolov5/ to sys.path() for *.py subdir exec ( #2949 )
...
* Add yolov5/ to sys.path() for *.py subdir exec
* Update export.py
2021-04-27 17:02:07 +02:00
4890499344
Improved yolo.py profiling ( #2940 )
...
* Improved yolo.py profiling
Improved column order and labelling.
* Update yolo.py
2021-04-26 23:58:21 +02:00
6c1290fe03
Update README.md ( #2934 )
...
* Update README.md
dependencies:
ImportError: libGL.so.1: cannot open shared object file: No such file or directory
ImportError: libgthread-2.0.so.0: cannot open shared object file: No such file or directory
ImportError: libSM.so.6: cannot open shared object file: No such file or directory
ImportError: libXrender.so.1: cannot open shared object file: No such file or directory
* replace older apt-get with apt
Code commented for now until a better understanding of the issue, and also code is not cross-platform compatible.
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-04-26 23:56:25 +02:00
1849916726
Check_requirements() enclosing apostrophe bug fix ( #2929 )
...
This fixes a bug where the '>' symbol in python package requirements was not running correctly with subprocess.check_output() commands.
2021-04-25 23:33:25 +02:00
9c7bb5a52c
ACON Activation batch-size 1 bug patch ( #2901 )
...
* ACON Activation batch-size 1 bug path
This is not a great solution to https://github.com/nmaac/acon/issues/4 but it's all I could think of at the moment.
WARNING: YOLOv5 models with MetaAconC() activations are incapable of running inference at batch-size 1 properly due to a known bug in https://github.com/nmaac/acon/issues/4 with no known solution.
* Update activations.py
* Update activations.py
* Update activations.py
* Update activations.py
2021-04-25 22:54:07 +02:00
c0d3f80544
Add verbose option to pytorch hub models ( #2926 )
...
* Add verbose and update print to logging
* Fix positonal param
* Revert auto formatting changes
* Update hubconf.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-04-25 22:01:05 +02:00
3665c0f59b
test.py native --single-cls ( #2928 )
2021-04-25 20:05:16 +02:00
aa78069c58
Change default value of hide-conf argument to false ( #2925 )
2021-04-25 14:18:14 +02:00
eae28a93b0
Change default value of hide label argument to False ( #2923 )
2021-04-24 19:58:02 +02:00
de19d396e7
Update visdrone.yaml ( #2921 )
2021-04-24 16:28:27 +02:00
45632b2704
Update download() for tar.gz files ( #2919 )
...
* Update download() for tar.gz files
* Update general.py
2021-04-24 15:53:15 +02:00
1b1ab4cca2
Add file_size() function ( #2911 )
...
* Add file_size() function
* Update export.py
2021-04-24 01:31:11 +02:00
646386ff09
Update export.py for 2 dry runs ( #2910 )
...
* Update export.py for 2 dry runs
* Update export.py
2021-04-24 00:10:38 +02:00
a2a514dec8
Update export.py ( #2909 )
2021-04-23 23:50:02 +02:00
28db237639
Default optimize_for_mobile() on TorchScript models ( #2908 )
...
Per https://pytorch.org/tutorials/recipes/script_optimized.html this should improve performance on torchscript models (and maybe coreml models also since coremltools operates on a torchscript model input, though this still requires testing).
2021-04-23 21:21:58 +02:00
f662c18507
Add detect.py --hide-conf --hide-labels --line-thickness options ( #2658 )
...
* command line option for line thickness and hiding labels
* command line option for line thickness and hiding labels
* command line option for line thickness and hiding labels
* command line option for line thickness and hiding labels
* command line option for line thickness and hiding labels
* command line option for hiding confidence values
* Update detect.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-04-23 21:07:48 +02:00
14d2d2d75f
Update google_utils.py ( #2900 )
2021-04-22 20:27:32 +02:00
cdb678f418
Update yolo.py ( #2899 )
2021-04-22 19:27:21 +02:00
b40dd99167
Explicit opt function arguments ( #2817 )
...
* more explicit function arguments
* fix typo in detect.py
* revert import order
* revert import order
* remove default value
2021-04-22 18:17:30 +02:00
264d860f8d
ACON activation function ( #2893 )
...
* ACON Activation Function
## 🚀 Feature
There is a new activation function [ACON (CVPR 2021)](https://arxiv.org/pdf/2009.04759.pdf ) that unifies ReLU and Swish.
ACON is simple but very effective, code is here: https://github.com/nmaac/acon/blob/main/acon.py#L19
The improvements are very significant:
## Alternatives
It also has an enhanced version meta-ACON that uses a small network to learn beta explicitly, which may influence the speed a bit.
## Additional context
[Code](https://github.com/nmaac/acon ) and [paper](https://arxiv.org/pdf/2009.04759.pdf ).
* Update activations.py
2021-04-22 17:26:05 +02:00
Glenn Jocher
kepler62f
Jiacong Fang
Ayush Chaurasia
jylink
Hodovo
jluntamazon
Ferdinand Loesch
BZFYS
NanoCode012
albinxavi
Maximilian Peters
fcakyon
