mirrors/yolov5
1
0
Fork 0
mirror of https://github.com/ultralytics/yolov5.git synced 2025-06-03 14:49:29 +08:00
Code Issues Projects Releases Wiki Activity
1,659 Commits 10 Branches 10 Tags
Commit Graph

271 Commits

Author SHA1 Message Date
Glenn Jocher
7bf04d9bbf
AutoShape() models as DetectMultiBackend() instances (#5845) 
* Update AutoShape()

* autodownload ONNX

* Cleanup

* Finish updates

* Add Usage

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* fix device

* Update hubconf.py

* Update common.py

* smart param selection

* autodownload all formats

* autopad only pytorch models

* new_shape edits

* stride tensor fix

* Cleanup
 2021-12-04 15:00:07 +01:00
Glenn Jocher
00e308f7be
Update TorchScript suffix to *.torchscript (#5856) 2021-12-02 16:06:45 +01:00
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
Glenn Jocher
fcd180d336
Refactor new model.warmup() method (#5810) 
* Refactor new `model.warmup()` method

* Add half
 2021-11-27 12:29:45 +01:00
Phil2020
53349dac8e
Scope TF imports in DetectMultiBackend() (#5792) 
* tensorflow or tflite exclusively as interpreter

As per bug report https://github.com/ultralytics/yolov5/issues/5709 I think there should be only one attempt to assign interpreter, and it appears tflite is only ever needed for the case of edgetpu model.

* Scope imports

* Nested definition line fix

* Update common.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-11-25 17:54:00 +01:00
imyhxy
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
Glenn Jocher
46daa7b78d
Remove .autoshape() method (#5694) 2021-11-20 01:11:36 +01:00
Jirka Borovec
eb51ffdcac
Prune unused imports (#5711) 
* prune unused imports

* [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>
 2021-11-19 13:32:53 +01:00
Nrupatunga
0453b758e7
TFDetect dynamic anchor count assignment fix (#5668) 
* fix tf.py when anchors not equal to 3

* revert the isort fix

* update the fix to use anchor attribute available already
 2021-11-16 12:36:00 +01:00
Ding Yiwei
c2523be634
Replace 2 transpose() with 1 permute in TransformerBlock()` (#5645) 2021-11-15 10:06:18 +01:00
Glenn Jocher
3883261143
New DetectMultiBackend() class (#5549) 
* New `DetectMultiBackend()` class

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

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

* pb to pt fix

* Cleanup

* explicit apply_classifier path

* Cleanup2

* Cleanup3

* Cleanup4

* Cleanup5

* Cleanup6

* val.py MultiBackend inference

* warmup fix

* to device fix

* pt fix

* device fix

* Val cleanup

* COCO128 URL to assets

* half fix

* detect fix

* detect fix 2

* remove half from DetectMultiBackend

* training half handling

* training half handling 2

* training half handling 3

* Cleanup

* Fix CI error

* Add torchscript _extra_files

* Add TorchScript

* Add CoreML

* CoreML cleanup

* New `DetectMultiBackend()` class

* pb to pt fix

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

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

* Cleanup

* explicit apply_classifier path

* Cleanup2

* Cleanup3

* Cleanup4

* Cleanup5

* Cleanup6

* val.py MultiBackend inference

* warmup fix

* to device fix

* pt fix

* device fix

* Val cleanup

* COCO128 URL to assets

* half fix

* detect fix

* detect fix 2

* remove half from DetectMultiBackend

* training half handling

* training half handling 2

* training half handling 3

* Cleanup

* Fix CI error

* Add torchscript _extra_files

* Add TorchScript

* Add CoreML

* CoreML cleanup

* revert default to pt

* Add Usage examples

* Cleanup val

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2021-11-09 16:45:02 +01:00
Glenn Jocher
79bca2bf64
LOGGER consolidation (#5569) 
* Logger consolidation

* [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>
 2021-11-08 16:32:15 +01:00
Glenn Jocher
3f64ad1760
Fix save_one_box() (#5545) 
* Fix `save_one_box()`

* [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>
 2021-11-06 19:28:03 +01:00
Glenn Jocher
60c8a4f696
Fix for *.yaml emojis on load (#5543) 
Fix for Colab hub error:


```python
import yaml

with open('yolov5s.yaml', errors='ignore') as f:
     d = yaml.safe_load(f)  # model dict

print(d)

---------------------------------------------------------------------------
ReaderError                               Traceback (most recent call last)
<ipython-input-8-1150b5143073> in <module>()
      2 
      3 with open('yolov5s.yaml', errors='ignore') as f:
----> 4      d = yaml.safe_load(f)  # model dict
      5 
      6 print(d)

6 frames
/usr/local/lib/python3.7/dist-packages/yaml/reader.py in check_printable(self, data)
    142             position = self.index+(len(self.buffer)-self.pointer)+match.start()
    143             raise ReaderError(self.name, position, ord(character),
--> 144                     'unicode', "special characters are not allowed")
    145 
    146     def update(self, length):

ReaderError: unacceptable character #x1f680: special characters are not allowed
  in "yolov5s.yaml", position 9
```
 2021-11-06 16:03:14 +01:00
Glenn Jocher
fa2344cdd8
Update models/hub/*.yaml files for v6.0n release (#5540) 
* Update model yamls for v6.0

* Add python models/yolo.py --test

* Ghost fix
 2021-11-06 15:07:45 +01:00
Deep Patel
336437998f
Suppress ONNX export trace warning (#5437) 
Checking for `onnx_dynamic` first should suppress the warning:

```log
TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic
```
 2021-11-05 19:31:53 +01:00
Glenn Jocher
bfacfc6b4a
Update cls bias init (#5520) 
* Update cls bias init

Increased numerical precision. Returns 1.0 probability for single-class datasets now. Addresses https://github.com/ultralytics/yolov5/issues/5357

```python
torch.sigmoid(torch.tensor([math.log(0.6 / (1 - 0.99999))]))
Out[19]: tensor([1.0000])
```

* Update yolo.py
 2021-11-05 13:18:46 +01:00
Jirka Borovec
0155548384
precommit: isort (#5493) 
* precommit: isort

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

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

* Update isort config

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

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

* Update name

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-11-04 17:24:25 +01:00
Glenn Jocher
5866646cc8
Fix float zeros format (#5491) 
* Fix float zeros format

* 255 to integer
 2021-11-03 23:36:53 +01:00
Glenn Jocher
06bf8ef7e5
Add tf.py verification printout (#5484) 
* Update tf.py with verified confirmation

* Update ci-testing.yml

* Update ci-testing.yml
 2021-11-03 19:04:51 +01:00
Glenn Jocher
042f02ff9b
Fix tf.py LoadImages() dataloader return values (#5455) 2021-11-02 23:04:15 +01:00
Glenn Jocher
7b1f7aec46
Update get_loggers() (#4854) 
* Update `set_logging()`

* Update export.py

* pre-commit fixes

* Update LoadImages

* Update LoadStreams

* Update print_args

* Single LOGGER definition

* yolo.py fix

Co-authored-by: pre-commit <pre-commit@example.com>
 2021-11-01 18:22:13 +01:00
Glenn Jocher
8c326a1edf
Meshgrid indexing='ij' for PyTorch 1.10 (#5309) 
* Meshgrid `indexing='ij'` for PyTorch 1.10

Will not merge currently as breaks backwards compatibility.

* Meshgrid `indexing='ij'` for PyTorch 1.10

Will not merge currently as breaks backwards compatibility.

* Add check_version hard argument

* Update comment
 2021-11-01 14:33:08 +01:00
Glenn Jocher
5d4258fac5
Fix MixConv2d() remove shortcut + apply depthwise (#5410) 2021-10-30 13:38:51 +02:00
Jirka Borovec
ed887b5976
Add pre-commit CI actions (#4982) 
* define pre-commit

* add CI code

* configure

* apply pre-commit

* fstring

* apply MD

* pre-commit

* Update torch_utils.py

* Update print strings

* notes

* Cleanup code-format.yml

* Update setup.cfg

* Update .pre-commit-config.yaml

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-10-28 18:35:01 +02:00
Glenn Jocher
9c31a66f5d
Update AutoShape.forward() model.classes example (#5324) 2021-10-25 14:03:25 +02:00
Yoni Chechik
34da872ab6
fix tf conversion in new v6 models (#5153) 
* fix `tf` conversion in new v6 (#5147)

* sort imports

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-10-12 08:38:54 -07:00
Glenn Jocher
956be8e642
YOLOv5 release v6.0 (#5141) 
* Update P5 models

* Update P6 models

* Update with GFLOPs and Params

* Update with GFLOPs and Params

* Update README

* Update

* Update README

* Update

* Update

* Add times

* Update README

* Update results

* Update results

* Update results

* Update hyps

* Update plots

* Update plots

* Update README.md

* Add nano models to hubconf.py
 2021-10-11 23:47:18 -07:00
Jebastin Nadar
9d75e42f98
Refactor Detect() anchors for ONNX <> OpenCV DNN compatibility (#4833) 
* refactor anchors and anchor_grid in Detect Layer

* fix CI failures by adding compatibility

* fix tf failure

* fix different devices errors

* Cleanup

* fix anchors overwriting issue

* better refactoring

* Remove self.anchor_grid shape check (redundant with self.grid check)

Also PEP8 / 120 line width

* Convert _make_grid() from static to dynamic method

* Remove anchor_grid.to(device)

clone() should already clone to same device as self.anchors

* fix different devices error

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-10-11 09:58:42 -07:00
Jebastin Nadar
a0e15046c3
Fix different devices bug when moving model from GPU to CPU (#5110) 
* fix different devices bug

* extend _apply() instead of to() for a general fix

* Only apply if Detect() is last layer

Co-authored-by: Jebastin Nadar <njebastin10@gmail.com>

* Indent fix

* Add comment to yolo.py

* Add comment to common.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-10-10 14:24:05 -07:00
Glenn Jocher
070af88108
Fix yaml.safe_load() ignore emoji errors (#5060) 2021-10-05 13:41:52 -07:00
Glenn Jocher
d133968b1e
Clip TTA Augmented Tails (#5028) 
* Clip TTA Augmented Tails

Experimental TTA update.

* Update yolo.py

* Update yolo.py

* Update yolo.py

* Update yolo.py
 2021-10-04 15:48:55 -07:00
Zhiqiang Wang
1922ddeac0
Fix pylint: do not use bare 'except' (#5025) 
* Fix E722, do not use bare 'except'

* Remove used codes

* Add FileNotFoundError in LoadImagesAndLabels

* Remove AssertionError

* Ignore LoadImagesAndLabels

* Ignore downloads.py

* Ignore torch_utils.py

* Ignore train.py

* Ignore datasets.py

* Enable utils/download.py

* Fixing exception in thop

* Remove unused code

* Fixing exception in LoadImagesAndLabels

* Fixing exception in exif_size

* Fixing exception in parse_model

* Ignore exceptions in requests

* Revert the exception as suggested

* Revert the exception as suggested
 2021-10-03 17:54:40 -07:00
Glenn Jocher
fb982d6030
Fix relative ROOT Pytorch Hub custom model bug (#4974) 
* Fix relative `ROOT` Pytorch Hub custom model bug

* Update yolo.py
 2021-09-28 06:36:12 -07:00
Glenn Jocher
5ed28603cf
Update relative ROOT logic (#4955) 
* Update relative `ROOT` logic

* python 3.9 Path().is_relative_to() removal
 2021-09-27 18:26:41 -07:00
Glenn Jocher
a820b43aca
Automatic Chinese fonts plotting (#4951) 
* Automatic Chinese fonts plotting

* Default PIL=False
 2021-09-27 13:48:15 -07:00
Jiacong Fang
2c2ef25f8b
TensorFlow.js export enhancements (#4905) 
* Add arguments to TensorFlow NMS call

* Add regex substitution to reorder Identity_*

* Delete reorder in docstring

* Cleanup

* Cleanup2

* Removed `+ \` on string ends (not needed)

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-09-24 14:18:15 -07:00
Glenn Jocher
4d1a2ac87e
Update sys.path.append(str(ROOT)) (#4852) 
* Update `sys.path.append(str(ROOT))`

* Cleanup
 2021-09-18 15:02:08 +02:00
Glenn Jocher
3732f9ac8a
Refactor argparser printing to print_args() (#4850) 
* Refactor argparser printing to `print_args()`

* Cleanup
 2021-09-18 14:16:19 +02:00
Jiacong Fang
3beb871ba4
Multiple TF export improvements (#4824) 
* Add fused conv support

* Set all saved_model values to non trainable

* Fix TFLite fp16 model export

* Fix int8 TFLite conversion
 2021-09-16 15:27:22 +02:00
Glenn Jocher
0dc725e3dc
Refactor forward() method profiling (#4816) 2021-09-16 09:47:34 +02:00
Glenn Jocher
c3a93d783d
Add TensorFlow formats to export.py (#4479) 
* Initial commit

* Remove unused export_torchscript return

* ROOT variable

* Add prefix to fcn arg

* fix ROOT

* check_yaml into run()

* interim fixes

* imgsz=(320, 320)

* Hardcode tf_raw_resize False

* Finish opt elimination

* Update representative_dataset_gen()

* Update export.py with TF methods

* SiLU and GraphDef fixes

* file_size() directory handling feature

* export fixes

* add lambda: to representative_dataset

* Detect training False default

* Fuse false for TF models

* Embed agnostic NMS arguments

* Remove lambda

* TensorFlow.js export success

* Add pb to Usage

* Add *_tfjs_model/ to ignore files

* prepend YOLOv5 to function headers

* Remove end --- comments

* parameterize tfjs export pb file

* update run() data default /ROOT

* update --include help

* update imports

* return ct_model

* Consolidate TFLite export

* pb prerequisite to tfjs

* TF modules CamelCase

* Remove exports from tf.py and cleanup

* pass agnostic NMS arguments

* CI

* CI

* ignore *_web_model/

* Add tensorflow to CI dependencies

* CI tensorflow-cpu

* Update requirements.txt

* Remove tensorflow check_requirement

* CI coreml tfjs

* export only onnx torchscript

* reorder exports torchscript first
 2021-09-12 15:52:24 +02:00
Glenn Jocher
c47be26f34
Replace path.absolute() with path.resolve() (#4763) 2021-09-11 22:46:33 +02:00
Jean-Baptiste Martin
1cad0ce2c7
Allow multi_label option for NMS with PyTorch Hub (#4728) 
* Allow specifying multi_label option for NMS when using torch hub

* Reformat

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-09-09 15:32:04 +02:00
ELHoussineT
0d8a184237
Add crops = results.crops() dictionary (#4676) 
* adding get cropped functionality

* Add target logic in existing functions

* Crops cleanup

* Add dictionary keys: conf, cls, box

* Bug fixes - avoid return after first image

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2021-09-08 19:42:28 +02:00
Glenn Jocher
a2b3c71636
Add suffix checks (#4711) 
* Add suffix checks

* Cleanup

* Cleanup2

* Cleanup3
 2021-09-08 14:36:12 +02:00
Yukun Xia
35fe031461
Fix: add P2 layer 21 to yolov5-p2.yaml Detect() inputs (#4608) 
Layer 21 includes the information of xsmall objects
 2021-08-30 15:46:33 +02:00
Glenn Jocher
e5e5ebc799
Auto-UTF handling (#4594) 2021-08-29 17:15:18 +02:00
Glenn Jocher
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
Glenn Jocher
2da6444c92
Fix for python models/yolo.py --profile (#4541) 
Profiling fix copies input to Detect layer to circumvent inplace changes to the feature maps.
 2021-08-25 21:23:28 +02:00