🚀 Slideflow 2.0 is here! Take your #digitalpathology research to the next level with extended MIL support, expanded feature generators, and enhanced stain normalization. Deploy & visualize models with Slideflow Studio. 🔬💻 Check it out at slideflow.dev
Moving between CPU and GPU environments just got a whole lot easier. Find out more in this new blog by @_rjzamora and @quasiben: medium.com/rapids-ai/easy-cp…
Working with BERTopic and not meeting your New Year's wait loss goals? This blog by @MaartenGron and the RAPDIS team on speeding up BERTopic on CPU, and going the next mile with GPU, will meet you where you are at to keep those resolutions strong. medium.com/rapids-ai/faster-…
Anyone interested in topic modeling or #NLP should check out BERTopic. The upcoming release will include deeper support for #RAPIDS and cuML to help you get results faster and process larger datasets (among other amazing updates)!
Preview #5: Heavyweight BERTopic!
Last week was a lightweight update... this week a heavyweight💪 Better and more native integration of cuML's HDBSCAN in BERTopic! Use the full force of GPU acceleration to scale topic modeling to millions of documents.
A preview thread👇🧵
Preview #5: Heavyweight BERTopic!
Last week was a lightweight update... this week a heavyweight💪 Better and more native integration of cuML's HDBSCAN in BERTopic! Use the full force of GPU acceleration to scale topic modeling to millions of documents.
A preview thread👇🧵
Everyone knows GPUs speed up ML training but did you know they can also turbocharge your analytics workflow? Our friends from @nvidia explain how to get started with @RAPIDSai cuDF.
medium.com/google-colab/rapi…
Waiting hours for HDBSCAN soft clustering to finish processing a few hundred thousand records? The RAPIDS cuML library can do HDBSCAN soft clustering in seconds rather than hours. Get the code and latest benchmarks: nvda.ws/3BfnMQV
Very excited to announce the release of Slideflow 1.4! Our digital pathology deep learning toolkit now includes:
🏎️ 2-3x faster, GPU-accelerated slide reading with cuCIM
✅ More flexible slide QC
Learn more on our GitHub page👇
github.com/jamesdolezal/slid…
If you got back from the holiday weekend overwhelmed with managing strings in your ML pipeline, we have an early present for you in this blog from Brandon Miller on Fast Data Pipelining with String UDFs medium.com/rapids-ai/fast-da…
GPU accelerated Python libraries from @RAPIDSai can now be installed with pip! It's experimental for now -- ready for the #DataScience community to test and provide feedback! rapids.ai/pip.html
Data scientists shouldn’t have to choose between building ensemble models and fast results. Using @rapidsai cuML with @scikit_learn gives them the tools to do both.