TGINSIGHT SIMILAR POSTS
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
Search: #retaildesign
@arch_shovel · Post #439 · 06/24/2022, 04:56 PM
Do you know how many silver spheres are on the facade of the Hanjie Wanda Square in Wuhan, China? 42,333. While they all may look identical, their specific positions involving each other recreate the effect of movement and reflection in water or the sensuous folds of silk fabric. Photos: Edmon Leong / UNStudio #unstudio#facades#facadedesign#architecture#retaildesign#lightingdesign#arch_shovel