Bring this project to life Run on Paperspace Introduction In this article we introduce Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector addressing the issue of the high computational cost existing with the DETRs. The recent research paper DETRs Beat YOLOs on Real-Time Object Detection, a Baidu Inc., successfully analyzed the negative impact of non-maximum suppression (NMS) on real-time detectors and proposed an efficient hybrid encoder for multi-scale feature processing. The IoU-aware query selection enhances performance. RT-DETR-L achieves 53.0% AP ..read more

Bring this project to life Run on Paperspace Generating images with Deep Learning is arguably one of the greatest and most versatile applications of this generation of generative, weak AI. From generating quick marketing content to augmenting artist workflows to creating a fun learning tool for AI, we can easily see this ubiquity in action with the widespread popularity of the Stable Diffusion family of models. This is in large part to the Stability AI and Runway ML teams efforts to keep the model releases open sourced, and also owes a huge thanks to the active community of developers crea ..read more

Add speed and simplicity to your Machine Learning workflow today Get startedTalk to an expert Aleatoric uncertainty is a key part of machine learning models. It comes from the inherent randomness or noise in the data. We can't reduce it by getting more data or tweaking the model design. Visualizing aleatoric uncertainty helps us understand how the model performs and where it's unsure. In this post, we'll explore how TensorFlow Probability (TFP) can visualize aleatoric uncertainty in ML models. We will give an overview of aleatoric uncertainty concepts. We'll include clear code examples and ..read more

Bring this project to life Run on Paperspace Introduction YOLO is a state of the art object detection algorithm, and due to its processing power - it has become almost a standard way of detecting objects in the field of computer vision. Earlier, people used techniques like sliding windows, RCNN, fast RCNN, and faster RCNN for object detection.  But in 2015, YOLO (You Only Look Once) was invented, and this algorithm and its successors began outperforming all others.  In this article, we present the newest iteration of the renowned real-time object detection and image segmentation ..read more

Bring this project to life Run on Gradient Text-based image generation techniques have prevailed recently. Specifically, diffusion models have shown tremendous success in a different types of text-to-image works. Stable diffusion can generate photorealistic images by giving it text prompts. After the success of image synthesis models, the amount of focus grew on image editing research. This research focuses on editing images (either real images or images synthesized by any model) by providing text prompts on what to edit in the image. There have been many models that came out as part of im ..read more

Bring this project to life Run on Gradient Generative intelligence in the computer vision field has gotten quite a focus after the emergence of deep learning-based techniques. After the success of diffusion process-based techniques, generating images with textual data or with any random noise has become more profound. The images generated by diffusion models are photo-realistic and include details based on provided conditioning. But one of the downsides of diffusion models is that it generates the images iteratively using a Markov-chain-based diffusion process. Due to this, the time comple ..read more

Bring this project to life Run on Paperspace In this article, we compare two of the most popular cloud development platforms: Google Colab and Paperspace. We will explore several key considerations that are essential when purchasing a plan. Additionally, we will demonstrate an illustrative case study showcasing Real-ESRGAN which can run on Paperspace, with a mere click on the link provided in the article. This demo can also be easily executed on Colab, making for a simple comparison. Introduction In this blog post, we will try to show how Paperspace can be a better alternative to Google Co ..read more

Bring this project to life Run on Paperspace On this blog, we have long espoused the utility of Stable Diffusion for a wide variety of computer vision tasks, not just text to image synthesis. Namely, Stable Diffusion has also proven to be an extremely capable tool for image editing, 3D modeling, and much more. Furthermore, image upscaling and blind image restoration remain one of the most visible and utilitarian applications of AI available to a consumer today. Since last years GFPGAN and Real ESRGAN, efforts in this field have proven extremely capable in tasks like background detail resto ..read more

Add speed and simplicity to your Machine Learning workflow today Get startedTalk to an expert Introduction The authors of this paper introduce Imagen, a text-to-image diffusion model with an extraordinary level of photorealism and a deep level of language comprehension. With the objective of more thoroughly evaluating text-to-image models, the authors provide DrawBench, a comprehensive and complex benchmark for text-to-image models. Imagen relies heavily on diffusion models for high-quality image generation and on massive transformer language models for text comprehension. The main finding ..read more

Bring this project to life Run on Gradient ProGAN from the paper Progressive Growing of GANs for Improved Quality, Stability, and Variation is one of the revolutionary papers that was the first to generate really high-quality images. In this article, we will make a clean, simple, and readable implementation of it using PyTorch. (If you prefer TensorFlow/Keras you can see this amazing article written by Bharath K.)  We will try to replicate the original paper as closely as possible, so if you read the paper the implementation should be pretty much identical. If you don't read the ProGa ..read more