YOLOV5知识蒸馏源码
资源文件列表:

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
资源介绍:
YOLOV5知识蒸馏源码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:
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**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

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 ..

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 evaluationUsage
Code $ python train.py --data {data}_wandb.yaml

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 loggedUsage
Code $ python train.py --save_period 1

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}

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<