首页下载资源人工智能YOLOV5知识蒸馏源码

ZIPYOLOV5知识蒸馏源码

m0_515790411004.28KB需要积分:1

资源文件列表:

yolov5_distillation.zip 大约有168个文件
  1. yolov5_distillation/
  2. yolov5_distillation/.dockerignore 3.62KB
  3. yolov5_distillation/.gitattributes 75B
  4. yolov5_distillation/.github/
  5. yolov5_distillation/.github/FUNDING.yml 118B
  6. yolov5_distillation/.github/ISSUE_TEMPLATE/
  7. yolov5_distillation/.github/ISSUE_TEMPLATE/bug-report.yml 2.87KB
  8. yolov5_distillation/.github/ISSUE_TEMPLATE/config.yml 322B
  9. yolov5_distillation/.github/ISSUE_TEMPLATE/feature-request.yml 1.76KB
  10. yolov5_distillation/.github/ISSUE_TEMPLATE/question.yml 1.12KB
  11. yolov5_distillation/.github/dependabot.yml 441B
  12. yolov5_distillation/.github/workflows/
  13. yolov5_distillation/.github/workflows/ci-testing.yml 3.42KB
  14. yolov5_distillation/.github/workflows/codeql-analysis.yml 2KB
  15. yolov5_distillation/.github/workflows/greetings.yml 4.95KB
  16. yolov5_distillation/.github/workflows/rebase.yml 639B
  17. yolov5_distillation/.github/workflows/stale.yml 1.89KB
  18. yolov5_distillation/.gitignore 3.88KB
  19. yolov5_distillation/.idea/
  20. yolov5_distillation/.idea/.gitignore 50B
  21. yolov5_distillation/.idea/inspectionProfiles/
  22. yolov5_distillation/.idea/inspectionProfiles/Project_Default.xml 2.92KB
  23. yolov5_distillation/.idea/inspectionProfiles/profiles_settings.xml 174B
  24. yolov5_distillation/.idea/misc.xml 199B
  25. yolov5_distillation/.idea/modules.xml 283B
  26. yolov5_distillation/.idea/workspace.xml 2.96KB
  27. yolov5_distillation/.idea/yolov5_prune.iml 496B
  28. yolov5_distillation/1.6'
  29. yolov5_distillation/CONTRIBUTING.md 4.87KB
  30. yolov5_distillation/Dockerfile 1.43KB
  31. yolov5_distillation/LICENSE 34.3KB
  32. yolov5_distillation/README.md 7.07KB
  33. yolov5_distillation/__pycache__/
  34. yolov5_distillation/__pycache__/val.cpython-38.pyc 13.22KB
  35. yolov5_distillation/data/
  36. yolov5_distillation/data/Argoverse.yaml 2.7KB
  37. yolov5_distillation/data/GlobalWheat2020.yaml 1.87KB
  38. yolov5_distillation/data/Objects365.yaml 7.92KB
  39. yolov5_distillation/data/SKU-110K.yaml 2.32KB
  40. yolov5_distillation/data/VOC.yaml 3.33KB
  41. yolov5_distillation/data/VisDrone.yaml 2.88KB
  42. yolov5_distillation/data/coco.yaml 2.31KB
  43. yolov5_distillation/data/coco128.yaml 1.68KB
  44. yolov5_distillation/data/hyps/
  45. yolov5_distillation/data/hyps/hyp.finetune.yaml 907B
  46. yolov5_distillation/data/hyps/hyp.finetune_objects365.yaml 460B
  47. yolov5_distillation/data/hyps/hyp.scratch-high.yaml 1.64KB
  48. yolov5_distillation/data/hyps/hyp.scratch-low.yaml 1.65KB
  49. yolov5_distillation/data/hyps/hyp.scratch-med.yaml 1.65KB
  50. yolov5_distillation/data/hyps/hyp.scratch.yaml 1.62KB
  51. yolov5_distillation/data/images/
  52. yolov5_distillation/data/images/bus.jpg 476.01KB
  53. yolov5_distillation/data/images/zidane.jpg 164.99KB
  54. yolov5_distillation/data/scripts/
  55. yolov5_distillation/data/scripts/download_weights.sh 523B
  56. yolov5_distillation/data/scripts/get_coco.sh 900B
  57. yolov5_distillation/data/scripts/get_coco128.sh 615B
  58. yolov5_distillation/data/xView.yaml 4.98KB
  59. yolov5_distillation/deploy/
  60. yolov5_distillation/deploy/openvino/
  61. yolov5_distillation/deploy/openvino/eval_openvino_yolov5.py 10.27KB
  62. yolov5_distillation/deploy/openvino/yolov5s_distill_output_pytorch_int8_simple_model.json 929B
  63. yolov5_distillation/deploy/openvino/yolov5s_output_pytorch_int8_simple_model.json 904B
  64. yolov5_distillation/detect.py 13.25KB
  65. yolov5_distillation/export.py 26.25KB
  66. yolov5_distillation/hubconf.py 6.27KB
  67. yolov5_distillation/models/
  68. yolov5_distillation/models/__init__.py
  69. yolov5_distillation/models/__pycache__/
  70. yolov5_distillation/models/__pycache__/__init__.cpython-38.pyc 137B
  71. yolov5_distillation/models/__pycache__/common.cpython-38.pyc 29.08KB
  72. yolov5_distillation/models/__pycache__/experimental.cpython-38.pyc 4.76KB
  73. yolov5_distillation/models/__pycache__/yolo.cpython-38.pyc 12.35KB
  74. yolov5_distillation/models/common.py 32.09KB
  75. yolov5_distillation/models/experimental.py 4.48KB
  76. yolov5_distillation/models/hub/
  77. yolov5_distillation/models/hub/anchors.yaml 3.26KB
  78. yolov5_distillation/models/hub/yolov3-spp.yaml 1.53KB
  79. yolov5_distillation/models/hub/yolov3-tiny.yaml 1.2KB
  80. yolov5_distillation/models/hub/yolov3.yaml 1.52KB
  81. yolov5_distillation/models/hub/yolov5-bifpn.yaml 1.39KB
  82. yolov5_distillation/models/hub/yolov5-fpn.yaml 1.19KB
  83. yolov5_distillation/models/hub/yolov5-p2.yaml 1.65KB
  84. yolov5_distillation/models/hub/yolov5-p34.yaml 1.32KB
  85. yolov5_distillation/models/hub/yolov5-p6.yaml 1.7KB
  86. yolov5_distillation/models/hub/yolov5-p7.yaml 2.07KB
  87. yolov5_distillation/models/hub/yolov5-panet.yaml 1.37KB
  88. yolov5_distillation/models/hub/yolov5l6.yaml 1.78KB
  89. yolov5_distillation/models/hub/yolov5m6.yaml 1.78KB
  90. yolov5_distillation/models/hub/yolov5n6.yaml 1.78KB
  91. yolov5_distillation/models/hub/yolov5s-ghost.yaml 1.45KB
  92. yolov5_distillation/models/hub/yolov5s-transformer.yaml 1.41KB
  93. yolov5_distillation/models/hub/yolov5s6.yaml 1.78KB
  94. yolov5_distillation/models/hub/yolov5x6.yaml 1.78KB
  95. yolov5_distillation/models/tf.py 20.17KB
  96. yolov5_distillation/models/yolo.py 14.61KB
  97. yolov5_distillation/models/yolov5l.yaml 1.37KB
  98. yolov5_distillation/models/yolov5m.yaml 1.37KB
  99. yolov5_distillation/models/yolov5n.yaml 1.37KB
  100. yolov5_distillation/models/yolov5s.yaml 1.37KB
  101. yolov5_distillation/models/yolov5x.yaml 1.37KB
  102. yolov5_distillation/requirements.txt 939B
  103. yolov5_distillation/runs/
  104. yolov5_distillation/runs/train/
  105. yolov5_distillation/runs/train/exp/
  106. yolov5_distillation/runs/train/exp/events.out.tfevents.1710208916.5RKK3G3.3396.0 40B
  107. yolov5_distillation/runs/train/exp/hyp.yaml 400B
  108. yolov5_distillation/runs/train/exp/opt.yaml 625B
  109. yolov5_distillation/runs/train/exp/weights/
  110. yolov5_distillation/setup.cfg 1.24KB
  111. yolov5_distillation/train.py 32.99KB
  112. yolov5_distillation/train_distillation.py 36.14KB
  113. yolov5_distillation/tutorial.ipynb 55.14KB
  114. yolov5_distillation/utils/
  115. yolov5_distillation/utils/__init__.py 1.11KB
  116. yolov5_distillation/utils/__pycache__/
  117. yolov5_distillation/utils/__pycache__/__init__.cpython-38.pyc 1KB
  118. yolov5_distillation/utils/__pycache__/augmentations.cpython-38.pyc 8.83KB
  119. yolov5_distillation/utils/__pycache__/autoanchor.cpython-38.pyc 6.11KB
  120. yolov5_distillation/utils/__pycache__/callbacks.cpython-38.pyc 2.38KB
  121. yolov5_distillation/utils/__pycache__/datasets.cpython-38.pyc 34.93KB
  122. yolov5_distillation/utils/__pycache__/downloads.cpython-38.pyc 3.97KB
  123. yolov5_distillation/utils/__pycache__/general.cpython-38.pyc 30.99KB
  124. yolov5_distillation/utils/__pycache__/loss.cpython-38.pyc 11.22KB
  125. yolov5_distillation/utils/__pycache__/metrics.cpython-38.pyc 11KB
  126. yolov5_distillation/utils/__pycache__/plots.cpython-38.pyc 17.91KB
  127. yolov5_distillation/utils/__pycache__/torch_utils.cpython-38.pyc 12.52KB
  128. yolov5_distillation/utils/activations.py 3.69KB
  129. yolov5_distillation/utils/augmentations.py 11.46KB
  130. yolov5_distillation/utils/autoanchor.py 7KB
  131. yolov5_distillation/utils/autobatch.py 2.13KB
  132. yolov5_distillation/utils/aws/
  133. yolov5_distillation/utils/aws/__init__.py
  134. yolov5_distillation/utils/aws/mime.sh 780B
  135. yolov5_distillation/utils/aws/resume.py 1.17KB
  136. yolov5_distillation/utils/aws/userdata.sh 1.22KB
  137. yolov5_distillation/utils/benchmarks.py 3.72KB
  138. yolov5_distillation/utils/callbacks.py 2.41KB
  139. yolov5_distillation/utils/datasets.py 44.84KB
  140. yolov5_distillation/utils/downloads.py 6.14KB
  141. yolov5_distillation/utils/flask_rest_api/
  142. yolov5_distillation/utils/flask_rest_api/README.md 1.67KB
  143. yolov5_distillation/utils/flask_rest_api/example_request.py 299B
  144. yolov5_distillation/utils/flask_rest_api/restapi.py 1.05KB
  145. yolov5_distillation/utils/general.py 35.64KB
  146. yolov5_distillation/utils/google_app_engine/
  147. yolov5_distillation/utils/google_app_engine/Dockerfile 821B
  148. yolov5_distillation/utils/google_app_engine/additional_requirements.txt 105B
  149. yolov5_distillation/utils/google_app_engine/app.yaml 174B
  150. yolov5_distillation/utils/loggers/
  151. yolov5_distillation/utils/loggers/__init__.py 7.45KB
  152. yolov5_distillation/utils/loggers/__pycache__/
  153. yolov5_distillation/utils/loggers/__pycache__/__init__.cpython-38.pyc 7.16KB
  154. yolov5_distillation/utils/loggers/wandb/
  155. yolov5_distillation/utils/loggers/wandb/README.md 10.57KB
  156. yolov5_distillation/utils/loggers/wandb/__init__.py
  157. yolov5_distillation/utils/loggers/wandb/__pycache__/
  158. yolov5_distillation/utils/loggers/wandb/__pycache__/__init__.cpython-38.pyc 150B
  159. yolov5_distillation/utils/loggers/wandb/__pycache__/wandb_utils.cpython-38.pyc 19.11KB
  160. yolov5_distillation/utils/loggers/wandb/log_dataset.py 1.01KB
  161. yolov5_distillation/utils/loggers/wandb/sweep.py 1.12KB
  162. yolov5_distillation/utils/loggers/wandb/sweep.yaml 2.41KB
  163. yolov5_distillation/utils/loggers/wandb/wandb_utils.py 26.51KB
  164. yolov5_distillation/utils/loss.py 15.28KB
  165. yolov5_distillation/utils/metrics.py 13.68KB
  166. yolov5_distillation/utils/plots.py 20.04KB
  167. yolov5_distillation/utils/torch_utils.py 13.87KB
  168. yolov5_distillation/val.py 18.57KB

资源介绍:

YOLOV5知识蒸馏源码
馃摎 This guide explains how to use **Weights & Biases** (W&B) with YOLOv5 馃殌. UPDATED 29 September 2021. * [About Weights & Biases](#about-weights-&-biases) * [First-Time Setup](#first-time-setup) * [Viewing runs](#viewing-runs) * [Disabling wandb](#disabling-wandb) * [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage) * [Reports: Share your work with the world!](#reports) ## About Weights & Biases Think of [W&B](https://wandb.ai/site?utm_campaign=repo_yolo_wandbtutorial) like GitHub for machine learning models. With a few lines of code, save everything you need to debug, compare and reproduce your models 鈥� architecture, hyperparameters, git commits, model weights, GPU usage, and even datasets and predictions. Used by top researchers including teams at OpenAI, Lyft, Github, and MILA, W&B is part of the new standard of best practices for machine learning. How W&B can help you optimize your machine learning workflows: * [Debug](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Free-2) model performance in real time * [GPU usage](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#System-4) visualized automatically * [Custom charts](https://wandb.ai/wandb/customizable-charts/reports/Powerful-Custom-Charts-To-Debug-Model-Peformance--VmlldzoyNzY4ODI) for powerful, extensible visualization * [Share insights](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Share-8) interactively with collaborators * [Optimize hyperparameters](https://docs.wandb.com/sweeps) efficiently * [Track](https://docs.wandb.com/artifacts) datasets, pipelines, and production models ## First-Time Setup
Toggle Details When you first train, W&B will prompt you to create a new account and will generate an **API key** for you. If you are an existing user you can retrieve your key from https://wandb.ai/authorize. This key is used to tell W&B where to log your data. You only need to supply your key once, and then it is remembered on the same device. W&B will create a cloud **project** (default is 'YOLOv5') for your training runs, and each new training run will be provided a unique run **name** within that project as project/name. You can also manually set your project and run name as: ```shell $ python train.py --project ... --name ... ``` YOLOv5 notebook example: Open In Colab Open In Kaggle Screen Shot 2021-09-29 at 10 23 13 PM
## Viewing Runs
Toggle Details Run information streams from your environment to the W&B cloud console as you train. This allows you to monitor and even cancel runs in realtime . All important information is logged: * Training & Validation losses * Metrics: Precision, Recall, mAP@0.5, mAP@0.5:0.95 * Learning Rate over time * A bounding box debugging panel, showing the training progress over time * GPU: Type, **GPU Utilization**, power, temperature, **CUDA memory usage** * System: Disk I/0, CPU utilization, RAM memory usage * Your trained model as W&B Artifact * Environment: OS and Python types, Git repository and state, **training command**

Weights & Biases dashboard

## Disabling wandb * training after running `wandb disabled` inside that directory creates no wandb run ![Screenshot (84)](https://user-images.githubusercontent.com/15766192/143441777-c780bdd7-7cb4-4404-9559-b4316030a985.png) * To enable wandb again, run `wandb online` ![Screenshot (85)](https://user-images.githubusercontent.com/15766192/143441866-7191b2cb-22f0-4e0f-ae64-2dc47dc13078.png) ## Advanced Usage You can leverage W&B artifacts and Tables integration to easily visualize and manage your datasets, models and training evaluations. Here are some quick examples to get you started.

1: Train and Log Evaluation simultaneousy

This is an extension of the previous section, but it'll also training after uploading the dataset. This also evaluation Table Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets, so no images will be uploaded from your system more than once.
Usage Code $ python train.py --upload_data val ![Screenshot from 2021-11-21 17-40-06](https://user-images.githubusercontent.com/15766192/142761183-c1696d8c-3f38-45ab-991a-bb0dfd98ae7d.png)

2. Visualize and Version Datasets

Log, visualize, dynamically query, and understand your data with W&B Tables. You can use the following command to log your dataset as a W&B Table. This will generate a {dataset}_wandb.yaml file which can be used to train from dataset artifact.
Usage Code $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. ![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png)

3: Train using dataset artifact

When you upload a dataset as described in the first section, you get a new config file with an added `_wandb` to its name. This file contains the information that can be used to train a model directly from the dataset artifact. This also logs evaluation
Usage Code $ python train.py --data {data}_wandb.yaml ![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png)

4: Save model checkpoints as artifacts

To enable saving and versioning checkpoints of your experiment, pass `--save_period n` with the base cammand, where `n` represents checkpoint interval. You can also log both the dataset and model checkpoints simultaneously. If not passed, only the final model will be logged
Usage Code $ python train.py --save_period 1 ![Screenshot (68)](https://user-images.githubusercontent.com/15766192/128726138-ec6c1f60-639d-437d-b4ee-3acd9de47ef3.png)

5: Resume runs from checkpoint artifacts.

Any run can be resumed using artifacts if the --resume argument starts with聽wandb-artifact://聽prefix followed by the run path, i.e,聽wandb-artifact://username/project/runid . This doesn't require the model checkpoint to be present on the local system.
Usage Code $ python train.py --resume wandb-artifact://{run_path} ![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png)

6: Resume runs from dataset artifact & checkpoint artifacts.

Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device The syntax is same as the previous section, but you'll need to lof both the dataset and model checkpoints as artifacts, i.e, set bot --upload_dataset<
100+评论
captcha

    相关资源

    1. YOLOV5 PTQ，QAT量化源码

      m0_51579041#人工智能ZIP89.04MB7月前
      资源摘要:YOLOV5 PTQ，QAT量化源码

    2. Python 3.12.4 Windows 安装包

      xiaomangshe_com#后端ZIP25.26MB7月前
      资源摘要:Python 3.12.4 Windows 安装包

    3. Python 3.12.4 macOS 安装包

      xiaomangshe_com#后端ZIP43.73MB7月前
      资源摘要:Python 3.12.4 macOS 安装包

    4. C++与Mysql数据库结合开发的宿舍管理系统

      m0_75116965#数据库ZIP30.48MB7月前
      资源摘要:此资源可用于课程课设等一系列开发

    5. 伦茨ST17H66开发资源包

      qq_39724355#物联网ZIP80.74MB7月前
      资源摘要:伦茨ST17H66开发资源包

    6. Snipaste 截图贴回到屏幕上

      qq_64444051#操作系统ZIP15.63MB7月前
      资源摘要:Snipaste 是一个简单但强大的截图工具，也可以让你将截图贴回到屏幕上

    7. 黑鹰优化算法(Black eagle optimizer, BEO)

      qq_50150617#人工智能ZIP5.81KB7月前
      资源摘要:黑鹰优化算法(Black eagle optimizer, BEO)是2024年提出的一种新型的元启发式算法（智能优化算法），结合了黑鹰的生物规律和数学变换来指导粒子的搜索行为。本算法程序采用CEC2005的23个基准函数进行测试，记录多次运行的最优值、最差值、平均值和标准差等。并打印每次迭代结果。可画出函数空间分布图和算法迭代适应度收敛图。～代码完整，注释清晰，点击即可运行，可用于论文算法对比，也适用于新手学习。有问题可私聊我，看到后会回复！

    8. 混合粒子群算法求解旅行商问题的Matlab代码

      qq_50150617#大数据ZIP2.38KB7月前
      资源摘要:旅行商问题（Travelling Salesman Problem，TSP），又称货郎担问题，是组合优化中的一个NP难问题，旅行商问题可以描述为：给定一系列城市和每对城市之间的距离，求解访问每一座城市一次并回到起始城市的最短回路。从图论的角度来看，该问题实质是在一个带权完全无向图中，找一个权值最小的Hamilton回路。该混合算法为遗传算法和粒子群算法的混合算法（GAPSO）。该程序子函数全放入一个文件中，点击即可运行。~~可打印输出每次迭代结果，输出最终优化路线，画出路径图和适应度收敛图。代码完整，注释详细，点击即可运行，可根据自己的需求修改数据，适用于新手学习，也适用于算法对比。有问题可以发消息私聊我，看到后会回复。
    站长QQ:九六九五七三七