Integrate with Ultralytics YOLOv5¶
Ultralytics YOLOv5 is a family of object detection architectures and models pretrained on the COCO dataset.
Comet integrates directly with the Ultralytics YOLOv5
train.py script and automatically logs your hyperparameters, command line arguments, training and validation metrics.
Setup the YOLOv5 repository¶
Clone the YOLOv5 project into your environment, and install Comet and the necessary dependencies.
git clone https://github.com/ultralytics/yolov5 # clone cd yolov5 pip install -r requirements.txt comet_ml # install
Configure Comet Credentials¶
There are two ways to configure Comet with YOLOv5.
You can either set your credentials through environment variables
export COMET_API_KEY=<Your Comet API Key> export COMET_PROJECT_NAME=<Your Comet Project Name> # This will default to 'yolov5'
Or create a
.comet.config file in your working directory and set your credentials there.
Comet Configuration File
[comet] api_key=<Your Comet API Key> project_name=<Your Comet Project Name> # This will default to 'yolov5'
Run the Training Script¶
# Train YOLOv5s on COCO128 for 5 epochs python train.py --img 640 --batch 16 --epochs 5 --data coco128.yaml --weights yolov5s.pt
Try out an Example!¶
Check out an example of a completed run here.
Or better yet, try it out yourself in this Colab Notebook:
By default, Comet will log the following items
- Box Loss, Object Loss, Classification Loss for the training and validation data
- mAP_0.5, mAP_0.5:0.95 metrics for the validation data
- Precision and Recall for the validation data
- Model Hyperparameters
- All parameters passed through the command line options
- Confusion Matrix of the model predictions on the validation data
- Plots for the PR and F1 curves across all classes
- Correlogram of the Class Labels
Configure Comet Logging¶
Comet can be configured to log additional data either through command line flags passed to the training script or through environment variables.
export COMET_MODE=online # Set whether to run Comet in 'online' or 'offline' mode. Defaults to online export COMET_MODEL_NAME=<your model name> #Set the name for the saved model. Defaults to yolov5 export COMET_LOG_CONFUSION_MATRIX=false # Set to disable logging a Comet Confusion Matrix. Defaults to true export COMET_MAX_IMAGE_UPLOADS=<number of allowed images to upload to Comet> # Controls how many total image predictions to log to Comet. Defaults to 100. export COMET_LOG_PER_CLASS_METRICS=true # Set to log evaluation metrics for each detected class at the end of training. Defaults to false export COMET_DEFAULT_CHECKPOINT_FILENAME=<your checkpoint filename> # Set this if you would like to resume training from a different checkpoint. Defaults to 'last.pt' export COMET_LOG_BATCH_LEVEL_METRICS=true # Set this if you would like to log training metrics at the batch level. Defaults to false. export COMET_LOG_PREDICTIONS=true # Set this to false to disable logging model predictions
Logging Checkpoints with Comet¶
Logging Models to Comet is disabled by default. To enable it, pass the
save-period argument to the training script. This will save the logged checkpoints to Comet based on the interval value provided by
python train.py \ --img 640 \ --batch 16 \ --epochs 5 \ --data coco128.yaml \ --weights yolov5s.pt \ --save-period 1
Logging Model Predictions¶
By default, model predictions (images, ground truth labels and bounding boxes) will be logged to Comet.
You can control the frequency of logged predictions and the associated images by passing the
bbox_interval command line argument. Predictions can be visualized using Comet's Object Detection Custom Panel. This frequency corresponds to every Nth batch of data per epoch. In the example below, we are logging every 2nd batch of data for each epoch.
Note: The YOLOv5 validation dataloader will default to a batch size of 32, so you will have to set the logging frequency accordingly.
Here is an example project using the Panel:
python train.py \ --img 640 \ --batch 16 \ --epochs 5 \ --data coco128.yaml \ --weights yolov5s.pt \ --bbox_interval 2
Controlling the number of Prediction Images logged to Comet¶
When logging predictions from YOLOv5, Comet will log the images associated with each set of predictions. By default, a maximum of 100 validation images are logged. You can increase or decrease this number using the
COMET_MAX_IMAGE_UPLOADS environment variable.
env COMET_MAX_IMAGE_UPLOADS=200 python train.py \ --img 640 \ --batch 16 \ --epochs 5 \ --data coco128.yaml \ --weights yolov5s.pt \ --bbox_interval 1
Logging Class Level Metrics¶
COMET_LOG_PER_CLASS_METRICS environment variable to log mAP, precision, recall, f1 for each class.
env COMET_LOG_PER_CLASS_METRICS=true python train.py \ --img 640 \ --batch 16 \ --epochs 5 \ --data coco128.yaml \ --weights yolov5s.pt
Uploading a Dataset to Comet Artifacts¶
If you would like to store your data using Comet Artifacts, you can do so using the
The dataset is organized in the way described in the YOLOv5 documentation. The dataset config
yaml file must follow the same format as that of the
python train.py \ --img 640 \ --batch 16 \ --epochs 5 \ --data coco128.yaml \ --weights yolov5s.pt \ --upload_dataset
Using a saved Artifact¶
If you would like to use a dataset from Comet Artifacts, set the
path variable in your dataset
yaml file to point to the following Artifact resource URL.
# contents of artifact.yaml file path: "comet://<workspace name>/<artifact name>:<artifact version or alias>"
Then pass this file to your training script in the following way
python train.py \ --img 640 \ --batch 16 \ --epochs 5 \ --data artifact.yaml \ --weights yolov5s.pt
Artifacts also allow you to track the lineage of data as it flows through your Experimentation workflow. Here you can see a graph that shows you all the experiments that have used your uploaded dataset.
Resuming a Training Run¶
If your training run is interrupted for any reason, e.g. disrupted internet connection, you can resume the run using the
resume flag and the Comet Run Path.
The Run Path has the following format
comet://<your workspace name>/<your project name>/<experiment id>.
This will restore the run to its state before the interruption, which includes restoring the model from a checkpoint, restoring all hyperparameters and training arguments and downloading Comet dataset Artifacts if they were used in the original run. The resumed run will continue logging to the existing Experiment in the Comet UI.
python train.py --resume "comet://<your run path>"
Hyperparameter Search with the Comet Optimizer¶
YOLOv5 is also integrated with Comet's Optimizer, making it simple to visualize hyperparameter sweeps in the Comet UI.
Configuring an Optimizer Sweep¶
To configure the Comet Optimizer, you will have to create a JSON file with the information about the sweep. An example file has been provided in
python utils/loggers/comet/hpo.py \ --comet_optimizer_config "utils/loggers/comet/optimizer_config.json"
hpo.py script accepts the same arguments as
train.py. If you wish to pass additional arguments to your sweep simply add them after the script.
python utils/loggers/comet/hpo.py \ --comet_optimizer_config "utils/loggers/comet/optimizer_config.json" \ --save-period 1 \ --bbox_interval 1
Running a Sweep in Parallel¶
comet optimizer -j <set number of workers> utils/loggers/comet/hpo.py \ utils/loggers/comet/optimizer_config.json"
Visualizing Hyperparameter Search Results¶
Comet provides several ways to visualize the results of your sweep. Take a look at a project with a completed sweep here.