• 12 min read
What is YOLOv8? A Complete Guide.
YOLOv8 is a computer vision model architecture that you can use for object detection, segmentation, keypoint detection, and more.
Blog
Francesco
Making Neural Networks go brum brum in the day, fighting Siths in the night
Latest Posts by Francesco
• 8 min read
Collective Communication in Distributed Systems with PyTorch
The full code for this article is on GitHub
Today, we will explore the use of PyTorch's distributed collective communication feature. When working with multiple GPUs, it is necessary to share tensors across them, which is where torch.distributed comes in. It provides a set of APIs to
• 5 min read
📸 Roboflow 100: A Multi-Domain Object Detection Benchmark
Roboflow 100 (RF100) is a crowdsourced object detection benchmark. The dataset consists of 100 datasets, 7 imagery domains, 224,714 images, and 829 class labels with over 11,170 labeling hours.
• 6 min read
Deploying Machine Learning Models with PyTorch, gRPC and asyncio
Today we're going to see how to deploy a machine-learning model behind gRPC
service running via asyncio. gRPC promises to be faster, more scalable, and more
optimized than HTTP v1.
gRPC is supported in all major programming languages and will create types
hints, client, and server code for
• 7 min read
WTF COCO - The Weird Images that Underpin Modern Computer Vision Models
COCO [https://blog.roboflow.com/coco-dataset/] is an industry standard dataset
for benchmarking the performance of object detection models. The dataset was
created by "gathering images of complex everyday scenes containing common
objects in their natural context" and contains image annotations in 91
categories, with over 1.5
• 8 min read
Develop like a Pro with NVIDIA + Docker + VS Code + PyTorch
Everybody hates installing NVIDIA drivers, you have to manually download them,
then install cuda [https://blog.roboflow.com/what-is-cuda/]
[https://search.brave.com/search?q=cuda&source=desktop], be sure to have the
correct version of everything, and change them from time to time to be updated.
Today we
Stay Connected