Github Top Repositories

✅ "DENSE_REGION_CAPTION" Feature: This feature generates rich textual descriptions for different regions of the image. In the video, it introduced excessive glittery effects. 📌 It’s better suited for single-frame usage rather than processing a sequence of video frames. ✅ "REFERRING_EXPRESSION_SEGMENTATION" Feature: This feature segments areas of the image using expressions referring to them. However, ⏱️ it is time-consuming, and in terms of accuracy and efficiency, the SAM (Segment Anything Model) performs slightly better than Florence-2. 📓 Notebook: 🔗 https://github.com/ultralytics/notebooks/blob/main/notebooks/how-to-use-florence-2-for-object-detection-image-captioning-ocr-and-segmentation.ipynb 🔍 By: https://t.me/DataScienceN5

🧠 Inference using Microsoft Florence-2 with the Ultralytics Python Package 😍 ✅ Object Detection: The model performs exceptionally well in detecting various objects and demonstrates impressive zero-shot capabilities. This means it can identify objects without needing specific training on a particular dataset. 🔹 Use case: It is highly suitable for auto-annotating datasets in object detection format. ✅ Accuracy: The model performs well in terms of accuracy, but 🔺 it requires significant processing time, making it unsuitable for real-time applications.

Ready for the most powerful foundation model for medical images/videos? 🚨 Just dropped: MedSAM2 The next-gen foundation model for 3D medical image & video segmentation — built on top of SAM 2.1. Why it matters: • Trained on 455K+ 3D image–mask pairs & 76K+ annotated video frames • >85% reduction in human annotation costs (validated in 3 studies) • Fast, accurate, and generalizes across organs, modalities, and pathologies Big impact: We used MedSAM2 to create 3 massive datasets: • 5,000 CT lesions • 3,984 liver MRI lesions • 251,550 echo video frames Plug & play: Deployable in: → 3D Slicer → JupyterLab → Gradio → Google Colab 🔖 Project site: https://medsam2.github.io/ 🔗 Paper: https://lnkd.in/gbXu6D64 🔍 By: https://t.me/DataScienceN

Cupcake Counting Project on the Production Line Using Ultralytics YOLO 🧁 🚀 With the rapid growth of the computer vision market in the bakery industry—projected to reach $23.42 billion by 2025—the practical applications of this technology are receiving increasing attention. One of the most important and common applications is the automated counting of bakery products on production lines. In this project, the development team provided a model for cupcake detection, and Ultralytics solutions were used to implement the counting process. The only necessary step for deployment was updating the region coordinates for detection, which was successfully accomplished. Advantages: ✅ Instantly detects and counts cupcakes as they move. ✅ Handles high-speed conveyor belt production effortlessly. 🔗 Complete code ➡️https://lnkd.in/d-4Zk2Q5 🔍 By: https://t.me/DataScienceN

😍😍😍😍😍😍😍😍 It’s truly fascinating — definitely worth diving deeper into and working on! 😍😍😍😍😍😍😍😍

🔖 ImageBind: One Embedding Space To Bind Them All 📝 This project is a significant step forward in understanding and connecting information from diverse sources like images, text, audio, video, and even motion sensor data. ⚙️ Supports 6 Modalities: 📷 Image 📝 Text 🔈 Audi 🎥 Video 🦴 IMU sensor data (e.g., accelerometer) 🙄 Depth/Thermal & 3D data Interestingly, only some modalities had labels, yet ImageBind learned to align them through self-supervised learning. 💫 Key Features: ..No need for paired data (e.g., images and audio don’t have to be aligned)..Leverages contrastive learning for learning joint embedding space ..Competes with CLIP and AudioCLIP, but with better accuracy and coverage..Enables zero-shot retrieval (e.g., finding relevant video using just a sentence) 📌 Repo: https://github.com/facebookresearch/ImageBind 🔍 By: https://t.me/DataScienceN 🌟 #ImageBind #MultimodalAI #MetaAI #DeepLearning #SelfSupervised

The latest and the most up-to-date cyber news will be presented on PPHM HACKER NEWS. PPHM subscribers are the first people that receive firsthand cybernews and Tech news. You won't miss any cyber news with us. https://t.me/pphm_HackerNews

🔖 Project name : Analysis of Covid-19 chest x-rays 📝 In order to diagnose patients with Covid-19, the analysis of chest X-rays is a possibility to be explored to more easily detect positive cases. If the classification through deep learning of such data proves effective in detecting positive cases, then this method can be used in hospitals and clinics when traditional testing cannot be done. 📌 Repo: https://github.com/rehabaam/ds_covid19_project 🔍 By: https://t.me/DataScienceN 🌟

📌 Project name: Cat/Dog/Fox Lightning 2024 📝 Language: #Python 🔗 Dataset Link: https://www.kaggle.com/datasets/snmahsa/animal-image-dataset-cats-dogs-and-foxes 🖋 Download the dataset offline: https://t.me/datasets1/668

We will start soon

.

This channels is for Programmers, Coders, Software Engineers. 0️⃣ Python 1️⃣ Data Science 2️⃣ Machine Learning 3️⃣ Data Visualization 4️⃣  Artificial Intelligence 5️⃣ Data Analysis 6️⃣ Statistics 7️⃣ Deep Learning 8️⃣ programming Languages ✅ https://t.me/addlist/8_rRW2scgfRhOTc0 ✅ https://t.me/codeprogrammer

I advise you to use this bot, the bot has a strong launch and I guarantee you at least 200 dollars when Airdrop. In addition, you will get free daily money whenever you invite more friends https://t.me/donot/game?startapp=418788114 The bot is quite similar to the Dogs bot and Paws

Coursera has launched a collaboration with the Stars platform to enable students to self-fund using the Stars platform. Students can now access free Coursera scholarships through Stars. Don't miss the opportunity: Click here.

Pandas Cookbook (2025) Link Download: https://best-links.org/s?468c1ea5 How to Download Books (Read it, important)

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (2023) Link Download: https://best-links.org/s?6eed180f How to Download Books (Read it, important)

We will only send books with very high rating here. Sending books directly here would be risky so we will encrypt the book download mechanism using the (content lock) mechanism. The first and most important step is that you must open the link using Chrome or any other browser other than the default Telegram browser to ensure that the content is successfully unlocked. In the pictures attached to the post, there is a way to unlock the content and download the book successfully. The mechanism may seem vague to you at first, but with time and repetition, you will adapt to this mechanism. We do this and give things away for free only to people who deserve it.

We will start at night 🌉