220-yolov5-accuracy-check-and-quantization demo (openvinotoolkit#592)

* Update new demo 306-pytorch-object-detection-accuracy-check-and-quantization * Fix sh command issue for demo 306 * Fix demo 306 code check * Update readme for 306 demo * Update demo 219 * update readme * fix docker build issue * rebase to master * update * update * Update Yolov5 project to 220-demo * Update notebooks/README.md Co-authored-by: Adrian Boguszewski <[email protected]> * Update README.md Co-authored-by: Adrian Boguszewski <[email protected]> * Update notebooks/220-yolov5-accuracy-check-and-quantization/220-yolov5-accuracy-check-and-quantization.ipynb Co-authored-by: Adrian Boguszewski <[email protected]> * update * Update replace os.path to Path func * update * Update to fix onnx issue in Win10 * Update to fix * include in the markdown cell that this process should take a few minutes * Update onnx>=1.11.0 * Update pipfile * Update pipfile * to merge with master commit * Fix pipfile.lock * Fix onnx>=1.11.0,<1.12.0 due py3.6 not support onnx 1.12.0 * Fix onnx>=1.11.0,<1.12.0 due py3.6 not support onnx 1.12.0 * overcome onnx issue on win by import workaround * update onnx>=1.11.0, <1.12.0 * update pipfile onnx>=1.11.0 Co-authored-by: Adrian Boguszewski <[email protected]> Co-authored-by: Sun, Xiake <[email protected]> Co-authored-by: Paula Ramos <[email protected]>
nikita-savelyevv · Jul 21, 2022 · 8a9e9ca · 8a9e9ca
1 parent f1c289a
commit 8a9e9ca
Show file tree

Hide file tree

Showing 9 changed files with 1,352 additions and 48 deletions.
diff --git a/.docker/Pipfile b/.docker/Pipfile
@@ -23,6 +23,7 @@ nbval = "*"
 nest-asyncio = "<=1.5.4"
 nltk = ">=3.6.4"
 nncf = {extras = ["torch", "tf"]}
+onnx = ">=1.11.0"
 openvino-dev = {extras = ["onnx","tensorflow2"], version = "==2022.1.0"}
 ovmsclient = "*"
 paddle2onnx = ">=0.6,<=0.9.6"
@@ -36,6 +37,7 @@ pytorch_lightning = "*"
 pytube = "*"
 rsa = ">=4.7"
 scikit-learn = ">=0.24.2"
+seaborn = ">=0.11.0"
 setuptools = ">56.0.0"
 supervisor = "==4.1.0"
 tensorflow_datasets = "*"

diff --git a/.docker/Pipfile.lock b/.docker/Pipfile.lock
diff --git a/README.md b/README.md
@@ -138,10 +138,12 @@ More amazing notebooks here!
 | [217-vision-deblur](notebooks/217-vision-deblur/)<br>[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/217-vision-deblur?labpath=notebooks%2F217-vision-deblur%2F217-vision-deblur.ipynb)| Deblur Images with DeblurGAN-v2 | <img src="https://user-images.githubusercontent.com/41332813/158430181-05d07f42-cdb8-4b7a-b7dc-e7f7d9391877.png" width=225> |
 | [218-vehicle-detection-and-recognition](notebooks/218-vehicle-detection-and-recognition/)<br> | Use pre-trained models to detect and recognize vehicles and their attributes with OpenVINO | <img src = "https://user-images.githubusercontent.com/47499836/163544861-fa2ad64b-77df-4c16-b065-79183e8ed964.png" width=225> |
 | [219-knowledge-graphs-conve](notebooks/219-knowledge-graphs-conve/)<br> | Optimize the knowledge graph embeddings model (ConvE) with OpenVINO ||
+| [220-yolov5-accuracy-check-and-quantization](notebooks/220-yolov5-accuracy-check-and-quantization)<br> | Quantize the Ultralytics YOLOv5 model and check accuracy using the OpenVINO POT API | <img src = "https://user-images.githubusercontent.com/44352144/177097174-cfe78939-e946-445e-9fce-d8897417ef8e.png"  width=225> |
 | [221-machine-translation](notebooks/221-machine-translation)<br> | Real-time translation from English to German |  |
 
 
 
+
 </details>
 </p>
 

diff --git a/README_cn.md b/README_cn.md
@@ -57,6 +57,7 @@
 | [213-question-answering](notebooks/213-question-answering/)<br>[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?filepath=notebooks%2F213-question-answering%2F213-question-answering.ipynb) | 根据语境回答问题 | <img src="https://user-images.githubusercontent.com/4547501/152571639-ace628b2-e3d2-433e-8c28-9a5546d76a86.gif" width=225> |
 | [216-license-plate-recognition](notebooks/216-license-plate-recognition/)<br> | 在交通中识别中国车牌 | <img src="https://user-images.githubusercontent.com/70456146/162759539-4a0a996f-dabe-40ea-98d6-85b4dce8511d.png" width=225> |
 | [218-vehicle-detection-and-recognition](notebooks/218-vehicle-detection-and-recognition/)<br> | 车辆检测与识别 | <img src = "https://user-images.githubusercontent.com/47499836/163544861-fa2ad64b-77df-4c16-b065-79183e8ed964.png" width=225> |
+| [220-yolov5-accuracy-check-and-quantization](notebooks/220-yolov5-accuracy-check-and-quantization) | 基于POT工具量化Ultralytics Yolov5模型并分析精度 | <img src = "https://user-images.githubusercontent.com/44352144/177097174-cfe78939-e946-445e-9fce-d8897417ef8e.png"  width=225> |
 
 ### 模型训练