[External Talk] Towards an Automated R&D Workflow for Edge AI Systems - Dan Malowany
This is a recording of Dan Malowany talking about how SightX uses ClearML as part of the R&D workflow.
Systems | Development | Analytics | API | Testing
Modern Software Development For Today's Systems & Applications
How To Deploy a HuggingFace Model (Seamlessly)
What if I want to serve a Huggingface model on ClearML? Where do I start? In general, machine learning engineers know by now that a good model serving engine is invaluable when serving models in production. These days, NVIDIA’s Triton inference engine is a popular option to do so, but it is lacking in some respects.
10 - Hyperdatasets Data Versioning
This video introduces Hyperdatasets. Hyperdatasets is a data management system that’s designed for unstructured data like text, audio or visual data. It is part of the ClearML paid offering, which means it brings along quite a bit of upgrades over the open source clearml-data.
YOLOv5 Now Integrates Seamlessly with ClearML
The popular object detection model and framework made by ultralytics now has ClearML built-in. It’s now easier than ever to train a YOLOv5 model and have the ClearML experiment manager track it automatically. But that’s not all, you can easily specifiy a ClearML dataset version ID as the data input and it will automatically be used to train your model on. Follow us along in this blogpost, where we talk about the possibilities and guide you through the process of implementing them.
How to Build an Automatic ML Model Retraining Loop
Fully automatic retraining loop using ClearML Data Right, so you want to create a fully automatic retraining loop, that you can set up once and then pretty much forget about. Where do we even start?!
ClearML-Data
This video covers clearml-data tool, which is meant to help you version control, share and manage your different datasets. It integrates seamlessly in the existing clearml ecosystem, so a lot of terms will feel familiar!
[MLOPS] From experiment management to model serving and back. A complete usecase, step-by-step!
The recording of our talk at the MLOps World summit. This talk covers a complete example, starting from experiment management and data versioning, building up into a pipeline and finally deploying using ClearML serving with drift monitoring. We then induce artifical drift to trigger the monitoring alerts and go back down the chain to quickly retrain a model and deploy it using canary deployment.
How SightX Uses ClearML to Build AI Drone Models
With the rise of drone usage, it’s easier to take aerial footage than ever before. The resulting data can trigger quick, effective action; removing guesswork and increasing aerial awareness, which can have profound implications on growing profits and trimming expenses. And as drone use rises, so does the usage of AI, to navigate, detect, identify, and track meaningful artifacts and objects.
[TALK] Model Serving Monitoring and Traceability: The Bigger Picture
The recording of our talk at the AI infrastructure alliance micro summit. This talk covers ClearML serving including monitoring and focuses on the importance of being able to trace the deployed model all the way back to the original experiment, code and data that were used to train it! One of the mayor advantages of a single tool end-to-end MLOps workflow.
Model Serving Monitoring and Traceability - The Bigger Picture - The AIIA Summit 2022
Watch our great evangelist Victor Sonck in the AIIA summit! How can you go in the bigger picture of model observability? Well, the short answer is complete traceability. And what does that mean? Find out for yourself in Victor's short and insightful talk. ClearML is an open source ML / DL experiment manager, versioning and ML-Ops full system solution.