* removed transpose op for better edgetpu support
* fix for training case
* enabled experimental new quantizer flag
* precalculate add and mul ops at compile time
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* refactor: use edgetpu flag
* fix: remove bitwise and assignation to tflite
* Cleanup and fix tflite
* Cleanup
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Fix CoreML P6 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>
* Fix exporting saved_model: pb exceeds 2GB
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Replace TF v1.x API with TF v2.x API for saved_model export
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Clean up
* Remove lambda in tf.function()
* Revert "Remove lambda in tf.function()" to be compatible with TF v2.4
This reverts commit 46c7931f11dfdea6ae340c77287c35c30b9e0779.
* Fix for pre-commit.ci
* Cleanup1
* Cleanup2
* Backwards compatibility update
* Update common.py
* Update common.py
* Cleanup3
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>
* Edge TPU `tf.lite.experimental.load_delegate` fix
Fix attempt for #6535
* [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>
* 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>
* Add models/tf.py for TensorFlow and TFLite export
* Set auto=False for int8 calibration
* Update requirements.txt for TensorFlow and TFLite export
* Read anchors directly from PyTorch weights
* Add --tf-nms to append NMS in TensorFlow SavedModel and GraphDef export
* Remove check_anchor_order, check_file, set_logging from import
* Reformat code and optimize imports
* Autodownload model and check cfg
* update --source path, img-size to 320, single output
* Adjust representative_dataset
* Put representative dataset in tfl_int8 block
* detect.py TF inference
* weights to string
* weights to string
* cleanup tf.py
* Add --dynamic-batch-size
* Add xywh normalization to reduce calibration error
* Update requirements.txt
TensorFlow 2.3.1 -> 2.4.0 to avoid int8 quantization error
* Fix imports
Move C3 from models.experimental to models.common
* Add models/tf.py for TensorFlow and TFLite export
* Set auto=False for int8 calibration
* Update requirements.txt for TensorFlow and TFLite export
* Read anchors directly from PyTorch weights
* Add --tf-nms to append NMS in TensorFlow SavedModel and GraphDef export
* Remove check_anchor_order, check_file, set_logging from import
* Reformat code and optimize imports
* Autodownload model and check cfg
* update --source path, img-size to 320, single output
* Adjust representative_dataset
* detect.py TF inference
* Put representative dataset in tfl_int8 block
* weights to string
* weights to string
* cleanup tf.py
* Add --dynamic-batch-size
* Add xywh normalization to reduce calibration error
* Update requirements.txt
TensorFlow 2.3.1 -> 2.4.0 to avoid int8 quantization error
* Fix imports
Move C3 from models.experimental to models.common
* implement C3() and SiLU()
* Add TensorFlow and TFLite Detection
* Add --tfl-detect for TFLite Detection
* Add int8 quantized TFLite inference in detect.py
* Add --edgetpu for Edge TPU detection
* Fix --img-size to add rectangle TensorFlow and TFLite input
* Add --no-tf-nms to detect objects using models combined with TensorFlow NMS
* Fix --img-size list type input
* Update README.md
* Add Android project for TFLite inference
* Upgrade TensorFlow v2.3.1 -> v2.4.0
* Disable normalization of xywh
* Rewrite names init in detect.py
* Change input resolution 640 -> 320 on Android
* Disable NNAPI
* Update README.me --img 640 -> 320
* Update README.me for Edge TPU
* Update README.md
* Fix reshape dim to support dynamic batching
* Fix reshape dim to support dynamic batching
* Add epsilon argument in tf_BN, which is different between TF and PT
* Set stride to None if not using PyTorch, and do not warmup without PyTorch
* Add list support in check_img_size()
* Add list input support in detect.py
* sys.path.append('./') to run from yolov5/
* Add int8 quantization support for TensorFlow 2.5
* Add get_coco128.sh
* Remove --no-tfl-detect in models/tf.py (Use tf-android-tfl-detect branch for EdgeTPU)
* Update requirements.txt
* Replace torch.load() with attempt_load()
* Update requirements.txt
* Add --tf-raw-resize to set half_pixel_centers=False
* Remove android directory
* Update README.md
* Update README.md
* Add multiple OS support for EdgeTPU detection
* Fix export and detect
* Export 3 YOLO heads with Edge TPU models
* Remove xywh denormalization with Edge TPU models in detect.py
* Fix saved_model and pb detect error
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix pre-commit.ci failure
* Add edgetpu in export.py docstring
* Fix Edge TPU model detection exported by TF 2.7
* Add class names for TF/TFLite in DetectMultibackend
* Fix assignment with nl in TFLite Detection
* Add check when getting Edge TPU compiler version
* Add UTF-8 encoding in opening --data file for Windows
* Remove redundant TensorFlow import
* Add Edge TPU in export.py's docstring
* Add the detect layer in Edge TPU model conversion
* Default `dnn=False`
* Cleanup data.yaml loading
* Update detect.py
* Update val.py
* Comments and generalize data.yaml names
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: unknown <fangjiacong@ut.cn>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
* Check TensorRT>=8.0.0 version
* [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>
* Fix tolist() to add the file for each Detection
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Fix PEP8 requirement for 2 spaces before an inline comment
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* Cleanup
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>
* 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>
* 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>
* 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>
* 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>
* 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>
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
```
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
```
* 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>
* 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
* 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>
* Add models/tf.py for TensorFlow and TFLite export
* Set auto=False for int8 calibration
* Update requirements.txt for TensorFlow and TFLite export
* Read anchors directly from PyTorch weights
* Add --tf-nms to append NMS in TensorFlow SavedModel and GraphDef export
* Remove check_anchor_order, check_file, set_logging from import
* Reformat code and optimize imports
* Autodownload model and check cfg
* update --source path, img-size to 320, single output
* Adjust representative_dataset
* Put representative dataset in tfl_int8 block
* detect.py TF inference
* weights to string
* weights to string
* cleanup tf.py
* Add --dynamic-batch-size
* Add xywh normalization to reduce calibration error
* Update requirements.txt
TensorFlow 2.3.1 -> 2.4.0 to avoid int8 quantization error
* Fix imports
Move C3 from models.experimental to models.common
* Add models/tf.py for TensorFlow and TFLite export
* Set auto=False for int8 calibration
* Update requirements.txt for TensorFlow and TFLite export
* Read anchors directly from PyTorch weights
* Add --tf-nms to append NMS in TensorFlow SavedModel and GraphDef export
* Remove check_anchor_order, check_file, set_logging from import
* Reformat code and optimize imports
* Autodownload model and check cfg
* update --source path, img-size to 320, single output
* Adjust representative_dataset
* detect.py TF inference
* Put representative dataset in tfl_int8 block
* weights to string
* weights to string
* cleanup tf.py
* Add --dynamic-batch-size
* Add xywh normalization to reduce calibration error
* Update requirements.txt
TensorFlow 2.3.1 -> 2.4.0 to avoid int8 quantization error
* Fix imports
Move C3 from models.experimental to models.common
* implement C3() and SiLU()
* Fix reshape dim to support dynamic batching
* Add epsilon argument in tf_BN, which is different between TF and PT
* Set stride to None if not using PyTorch, and do not warmup without PyTorch
* Add list support in check_img_size()
* Add list input support in detect.py
* sys.path.append('./') to run from yolov5/
* Add int8 quantization support for TensorFlow 2.5
* Add get_coco128.sh
* Remove --no-tfl-detect in models/tf.py (Use tf-android-tfl-detect branch for EdgeTPU)
* Update requirements.txt
* Replace torch.load() with attempt_load()
* Update requirements.txt
* Add --tf-raw-resize to set half_pixel_centers=False
* Add --agnostic-nms for TF class-agnostic NMS
* Cleanup after merge
* Cleanup2 after merge
* Cleanup3 after merge
* Add tf.py docstring with credit and usage
* pb saved_model and tflite use only one model in detect.py
* Add use cases in docstring of tf.py
* Remove redundant `stride` definition
* Remove keras direct import
* Fix `check_requirements(('tensorflow>=2.4.1',))`
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Add feature map visualization
Add a feature_visualization function to visualize the mid feature map of the model.
* Update yolo.py
* remove boolean from forward and reorder if statement
* remove print from forward
* General cleanup
* Indent
* Update plots.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Slightly modify CLI execution
This simple change makes it easier to run the primary functions of this
repo (train/detect/test) from within Python. An object which represents
`opt` can be constructed and fed to the `main` function of each of these
modules, rather than having to call the lower level functions directly,
or run the module as a script.
* Update export.py
Add CLI parsing update for more convenient module usage within Python.
Co-authored-by: Lewis Belcher <lb@desupervised.io>
* Added max_det parameters in various places
* 120 character line
* PEP8
* 120 character line
* Update inference default to 1000 instances
* Update inference default to 1000 instances
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* rename class autoShape -> AutoShape
follow other class naming convention
* rename class autoShape -> AutoShape
follow other classes' naming convention
* rename class autoShape -> AutoShape
* Allow users to skip exporting in formats that they don't care about
* Correct comments
* Update export.py
renamed --skip-format to --exclude
* Switched format from exclude to include (as instructed by @glenn-jocher)
* cleanup
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* 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>
Glenn Jocher
Mrinal Jain
paradigm
DavidB
Raffaele Galliera
Jiacong Fang
Jirka Borovec
Motoki Kimura
Deep Patel
Yono Mittlefehldt
Li Zeng
imyhxy
Phil2020
Nrupatunga
Ding Yiwei
Yoni Chechik
Jebastin Nadar
Zhiqiang Wang
Jean-Baptiste Martin
ELHoussineT
Yukun Xia
Yuantao Yang
Yonghye Kwon
KEN
jmiranda-laplateforme
Valentin Aliferov
Zigarss
lb-desupervised
WangChaofeng
Adrian Holovaty
Cristi Fati
jylink
Hodovo
jluntamazon
NanoCode012