YOLOV5知识蒸馏源码

资源文件列表(大概)

文件名

大小

yolov5_distillation/

yolov5_distillation/.dockerignore

3.62KB

yolov5_distillation/.gitattributes

75B

yolov5_distillation/.github/

yolov5_distillation/.github/FUNDING.yml

118B

yolov5_distillation/.github/ISSUE_TEMPLATE/

yolov5_distillation/.github/ISSUE_TEMPLATE/bug-report.yml

2.87KB

yolov5_distillation/.github/ISSUE_TEMPLATE/config.yml

322B

yolov5_distillation/.github/ISSUE_TEMPLATE/feature-request.yml

1.76KB

yolov5_distillation/.github/ISSUE_TEMPLATE/question.yml

1.12KB

yolov5_distillation/.github/dependabot.yml

441B

yolov5_distillation/.github/workflows/

yolov5_distillation/.github/workflows/ci-testing.yml

3.42KB

yolov5_distillation/.github/workflows/codeql-analysis.yml

2KB

yolov5_distillation/.github/workflows/greetings.yml

4.95KB

yolov5_distillation/.github/workflows/rebase.yml

639B

yolov5_distillation/.github/workflows/stale.yml

1.89KB

yolov5_distillation/.gitignore

3.88KB

yolov5_distillation/.idea/

yolov5_distillation/.idea/.gitignore

50B

yolov5_distillation/.idea/inspectionProfiles/

yolov5_distillation/.idea/inspectionProfiles/Project_Default.xml

2.92KB

yolov5_distillation/.idea/inspectionProfiles/profiles_settings.xml

174B

yolov5_distillation/.idea/misc.xml

199B

yolov5_distillation/.idea/modules.xml

283B

yolov5_distillation/.idea/workspace.xml

2.96KB

yolov5_distillation/.idea/yolov5_prune.iml

496B

yolov5_distillation/1.6'

yolov5_distillation/CONTRIBUTING.md

4.87KB

yolov5_distillation/Dockerfile

1.43KB

yolov5_distillation/LICENSE

34.3KB

yolov5_distillation/README.md

7.07KB

yolov5_distillation/__pycache__/

yolov5_distillation/__pycache__/val.cpython-38.pyc

13.22KB

yolov5_distillation/data/

yolov5_distillation/data/Argoverse.yaml

2.7KB

yolov5_distillation/data/GlobalWheat2020.yaml

1.87KB

yolov5_distillation/data/Objects365.yaml

7.92KB

yolov5_distillation/data/SKU-110K.yaml

2.32KB

yolov5_distillation/data/VOC.yaml

3.33KB

yolov5_distillation/data/VisDrone.yaml

2.88KB

yolov5_distillation/data/coco.yaml

2.31KB

yolov5_distillation/data/coco128.yaml

1.68KB

yolov5_distillation/data/hyps/

yolov5_distillation/data/hyps/hyp.finetune.yaml

907B

yolov5_distillation/data/hyps/hyp.finetune_objects365.yaml

460B

yolov5_distillation/data/hyps/hyp.scratch-high.yaml

1.64KB

yolov5_distillation/data/hyps/hyp.scratch-low.yaml

1.65KB

yolov5_distillation/data/hyps/hyp.scratch-med.yaml

1.65KB

yolov5_distillation/data/hyps/hyp.scratch.yaml

1.62KB

yolov5_distillation/data/images/

yolov5_distillation/data/images/bus.jpg

476.01KB

yolov5_distillation/data/images/zidane.jpg

164.99KB

yolov5_distillation/data/scripts/

yolov5_distillation/data/scripts/download_weights.sh

523B

yolov5_distillation/data/scripts/get_coco.sh

900B

yolov5_distillation/data/scripts/get_coco128.sh

615B

yolov5_distillation/data/xView.yaml

4.98KB

yolov5_distillation/deploy/

yolov5_distillation/deploy/openvino/

yolov5_distillation/deploy/openvino/eval_openvino_yolov5.py

10.27KB

yolov5_distillation/deploy/openvino/yolov5s_distill_output_pytorch_int8_simple_model.json

929B

yolov5_distillation/deploy/openvino/yolov5s_output_pytorch_int8_simple_model.json

904B

yolov5_distillation/detect.py

13.25KB

yolov5_distillation/export.py

26.25KB

yolov5_distillation/hubconf.py

6.27KB

yolov5_distillation/models/

yolov5_distillation/models/__init__.py

yolov5_distillation/models/__pycache__/

yolov5_distillation/models/__pycache__/__init__.cpython-38.pyc

137B

yolov5_distillation/models/__pycache__/common.cpython-38.pyc

29.08KB

yolov5_distillation/models/__pycache__/experimental.cpython-38.pyc

4.76KB

yolov5_distillation/models/__pycache__/yolo.cpython-38.pyc

12.35KB

yolov5_distillation/models/common.py

32.09KB

yolov5_distillation/models/experimental.py

4.48KB

yolov5_distillation/models/hub/

yolov5_distillation/models/hub/anchors.yaml

3.26KB

yolov5_distillation/models/hub/yolov3-spp.yaml

1.53KB

yolov5_distillation/models/hub/yolov3-tiny.yaml

1.2KB

yolov5_distillation/models/hub/yolov3.yaml

1.52KB

yolov5_distillation/models/hub/yolov5-bifpn.yaml

1.39KB

yolov5_distillation/models/hub/yolov5-fpn.yaml

1.19KB

yolov5_distillation/models/hub/yolov5-p2.yaml

1.65KB

yolov5_distillation/models/hub/yolov5-p34.yaml

1.32KB

yolov5_distillation/models/hub/yolov5-p6.yaml

1.7KB

yolov5_distillation/models/hub/yolov5-p7.yaml

2.07KB

yolov5_distillation/models/hub/yolov5-panet.yaml

1.37KB

yolov5_distillation/models/hub/yolov5l6.yaml

1.78KB

yolov5_distillation/models/hub/yolov5m6.yaml

1.78KB

yolov5_distillation/models/hub/yolov5n6.yaml

1.78KB

yolov5_distillation/models/hub/yolov5s-ghost.yaml

1.45KB

yolov5_distillation/models/hub/yolov5s-transformer.yaml

1.41KB

yolov5_distillation/models/hub/yolov5s6.yaml

1.78KB

yolov5_distillation/models/hub/yolov5x6.yaml

1.78KB

yolov5_distillation/models/tf.py

20.17KB

yolov5_distillation/models/yolo.py

14.61KB

yolov5_distillation/models/yolov5l.yaml

1.37KB

yolov5_distillation/models/yolov5m.yaml

1.37KB

yolov5_distillation/models/yolov5n.yaml

1.37KB

yolov5_distillation/models/yolov5s.yaml

1.37KB

yolov5_distillation/models/yolov5x.yaml

1.37KB

yolov5_distillation/requirements.txt

939B

yolov5_distillation/runs/

yolov5_distillation/runs/train/

yolov5_distillation/runs/train/exp/

yolov5_distillation/runs/train/exp/events.out.tfevents.1710208916.5RKK3G3.3396.0

40B

yolov5_distillation/runs/train/exp/hyp.yaml

400B

yolov5_distillation/runs/train/exp/opt.yaml

625B

yolov5_distillation/runs/train/exp/weights/

yolov5_distillation/setup.cfg

1.24KB

yolov5_distillation/train.py

32.99KB

yolov5_distillation/train_distillation.py

36.14KB

yolov5_distillation/tutorial.ipynb

55.14KB

yolov5_distillation/utils/

yolov5_distillation/utils/__init__.py

1.11KB

yolov5_distillation/utils/__pycache__/

yolov5_distillation/utils/__pycache__/__init__.cpython-38.pyc

1KB

yolov5_distillation/utils/__pycache__/augmentations.cpython-38.pyc

8.83KB

yolov5_distillation/utils/__pycache__/autoanchor.cpython-38.pyc

6.11KB

yolov5_distillation/utils/__pycache__/callbacks.cpython-38.pyc

2.38KB

yolov5_distillation/utils/__pycache__/datasets.cpython-38.pyc

34.93KB

yolov5_distillation/utils/__pycache__/downloads.cpython-38.pyc

3.97KB

yolov5_distillation/utils/__pycache__/general.cpython-38.pyc

30.99KB

yolov5_distillation/utils/__pycache__/loss.cpython-38.pyc

11.22KB

yolov5_distillation/utils/__pycache__/metrics.cpython-38.pyc

11KB

yolov5_distillation/utils/__pycache__/plots.cpython-38.pyc

17.91KB

yolov5_distillation/utils/__pycache__/torch_utils.cpython-38.pyc

12.52KB

yolov5_distillation/utils/activations.py

3.69KB

yolov5_distillation/utils/augmentations.py

11.46KB

yolov5_distillation/utils/autoanchor.py

7KB

yolov5_distillation/utils/autobatch.py

2.13KB

yolov5_distillation/utils/aws/

yolov5_distillation/utils/aws/__init__.py

yolov5_distillation/utils/aws/mime.sh

780B

yolov5_distillation/utils/aws/resume.py

1.17KB

yolov5_distillation/utils/aws/userdata.sh

1.22KB

yolov5_distillation/utils/benchmarks.py

3.72KB

yolov5_distillation/utils/callbacks.py

2.41KB

yolov5_distillation/utils/datasets.py

44.84KB

yolov5_distillation/utils/downloads.py

6.14KB

yolov5_distillation/utils/flask_rest_api/

yolov5_distillation/utils/flask_rest_api/README.md

1.67KB

yolov5_distillation/utils/flask_rest_api/example_request.py

299B

yolov5_distillation/utils/flask_rest_api/restapi.py

1.05KB

yolov5_distillation/utils/general.py

35.64KB

yolov5_distillation/utils/google_app_engine/

yolov5_distillation/utils/google_app_engine/Dockerfile

821B

yolov5_distillation/utils/google_app_engine/additional_requirements.txt

105B

yolov5_distillation/utils/google_app_engine/app.yaml

174B

yolov5_distillation/utils/loggers/

yolov5_distillation/utils/loggers/__init__.py

7.45KB

yolov5_distillation/utils/loggers/__pycache__/

yolov5_distillation/utils/loggers/__pycache__/__init__.cpython-38.pyc

7.16KB

yolov5_distillation/utils/loggers/wandb/

yolov5_distillation/utils/loggers/wandb/README.md

10.57KB

yolov5_distillation/utils/loggers/wandb/__init__.py

yolov5_distillation/utils/loggers/wandb/__pycache__/

yolov5_distillation/utils/loggers/wandb/__pycache__/__init__.cpython-38.pyc

150B

yolov5_distillation/utils/loggers/wandb/__pycache__/wandb_utils.cpython-38.pyc

19.11KB

yolov5_distillation/utils/loggers/wandb/log_dataset.py

1.01KB

yolov5_distillation/utils/loggers/wandb/sweep.py

1.12KB

yolov5_distillation/utils/loggers/wandb/sweep.yaml

2.41KB

yolov5_distillation/utils/loggers/wandb/wandb_utils.py

26.51KB

yolov5_distillation/utils/loss.py

15.28KB

yolov5_distillation/utils/metrics.py

13.68KB

yolov5_distillation/utils/plots.py

20.04KB

yolov5_distillation/utils/torch_utils.py

13.87KB

yolov5_distillation/val.py

18.57KB

资源内容介绍

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 & BiasesThink 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<details open> <summary> Toggle Details </summary>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: <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> <a href="https://www.kaggle.com/ultralytics/yolov5"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a><img width="960" alt="Screen Shot 2021-09-29 at 10 23 13 PM" src="https://user-images.githubusercontent.com/26833433/135392431-1ab7920a-c49d-450a-b0b0-0c86ec86100e.png"> </details>## Viewing Runs<details open> <summary> Toggle Details </summary>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 <b>realtime</b> . 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**<p align="center"><img width="900" alt="Weights & Biases dashboard" src="https://user-images.githubusercontent.com/26833433/135390767-c28b050f-8455-4004-adb0-3b730386e2b2.png"></p></details> ## 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 UsageYou 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.<details open> <h3> 1: Train and Log Evaluation simultaneousy </h3> This is an extension of the previous section, but it'll also training after uploading the dataset. <b> This also evaluation Table</b> 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. <details open> <summary> <b>Usage</b> </summary> <b>Code</b> <code> $ python train.py --upload_data val</code>![Screenshot from 2021-11-21 17-40-06](https://user-images.githubusercontent.com/15766192/142761183-c1696d8c-3f38-45ab-991a-bb0dfd98ae7d.png) </details> <h3>2. Visualize and Version Datasets</h3> Log, visualize, dynamically query, and understand your data with <a href='https://docs.wandb.ai/guides/data-vis/tables'>W&B Tables</a>. You can use the following command to log your dataset as a W&B Table. This will generate a <code>{dataset}_wandb.yaml</code> file which can be used to train from dataset artifact. <details> <summary> <b>Usage</b> </summary> <b>Code</b> <code> $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. </code> ![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png) </details> <h3> 3: Train using dataset artifact </h3> 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. <b> This also logs evaluation </b> <details> <summary> <b>Usage</b> </summary> <b>Code</b> <code> $ python train.py --data {data}_wandb.yaml </code>![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png) </details> <h3> 4: Save model checkpoints as artifacts </h3> 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 <details> <summary> <b>Usage</b> </summary> <b>Code</b> <code> $ python train.py --save_period 1 </code>![Screenshot (68)](https://user-images.githubusercontent.com/15766192/128726138-ec6c1f60-639d-437d-b4ee-3acd9de47ef3.png) </details></details> <h3> 5: Resume runs from checkpoint artifacts. </h3>Any run can be resumed using artifacts if the <code>--resume</code> argument starts with聽<code>wandb-artifact://</code>聽prefix followed by the run path, i.e,聽<code>wandb-artifact://username/project/runid </code>. This doesn't require the model checkpoint to be present on the local system. <details> <summary> <b>Usage</b> </summary> <b>Code</b> <code> $ python train.py --resume wandb-artifact://{run_path} </code>![Screenshot (70)](https://user-images.githubusercontent.com/15766192/128728988-4e84b355-6c87-41ae-a591-14aecf45343e.png) </details> <h3> 6: Resume runs from dataset artifact & checkpoint artifacts. </h3> <b> Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device </b> 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 <code>--upload_dataset<

用户评论 (0)

发表评论

您的昵称:

评分

评论内容:

验证码:

YOLOV5知识蒸馏源码

资源文件列表(大概)

资源内容介绍

用户评论 (0)

发表评论

相关资源

YOLOV5 PTQ，QAT量化源码

Python 3.12.4 Windows 安装包

Python 3.12.4 macOS 安装包

C++与Mysql数据库结合开发的宿舍管理系统