Find similar content

Source channel @githubtrending · Post #15365 · Dec 24

#jupyter_notebook DINOv3 offers powerful self-supervised vision models from Meta AI, like ViT up to 7B parameters and ConvNeXt, pretrained on 1.7B web or satellite images. Load them easily via PyTorch Hub, Hugging Face Transformers (v4.56+), or timm (v1.0.20+), with code examples for features, depth, detection, and segmentation. You benefit by using these top-performing, dense features without fine-tuning or labels—saving time and compute for tasks like classification, object detection, and zero-shot analysis on your images. https://github.com/facebookresearch/dinov3

Hashtags

#jupyter_notebook

Results

1 similar post found

Search: #paddlepaddle

当前筛选 #paddlepaddle清除筛选

Machinelearning

@ai_machinelearning_big_data · Post #8792 · 10/16/2025, 02:10 PM

Find similar View

📄PaddleOCR-VL (0.9B) — компактная Vision-Language модель нового поколения Команда Baidu AI представила PaddleOCR-VL (0.9B) — сверхлёгкую VLM-модель, которая достигает SOTA-точности в задачах распознавания: - текстов, - таблиц, - формул, - графиков 💡Под капотом: - NaViT - динамический vision-энкодер - ERNIE - облегчённая языковая модель от Baidu ⚡️ Поддержка 109 языков. 🟠GitHub: https://github.com/PaddlePaddle/PaddleOCR) 🟠HuggingFace: https://huggingface.co/PaddlePaddle/PaddleOCR-VL 🟠Docshttps://paddleocr.ai/latest/en/index.html @ai_machinelearning_big_data #BaiduAI#PaddlePaddle#Ernie#PaddleOCR#VisionLanguage#AI#OCR

Hashtags

#baiduai #paddlepaddle #ernie #paddleocr #visionlanguage #ai #ocr