Lihi Gur Arie, PhDinTowards Data ScienceBuilding an Image Similarity Search Engine with FAISS and CLIPA guided tutorial explaining how to search your image dataset with text or photo queries, using CLIP embeddings and FAISS indexingAug 232
François PorcherinTowards Data ScienceThe Ultimate Guide to Vision TransformersA comprehensive guide to the Vision Transformer (ViT) that revolutionized computer vision.Aug 301Aug 301
Tan Pengshi AlvininTowards AIOptical Character Recognition (OCR) with CNN-LSTM Attention Seq2SeqExploring the Attention-based CNN-LSTM Seq2Seq model for effective OCR with TensorFlow6h ago16h ago1
Muhammad ArdiinTowards Data SciencePaper Walkthrough: Vision Transformer (ViT)Exploring Vision Transformer (ViT) through PyTorch Implementation from Scratch.Aug 131Aug 131
Lihi Gur Arie, PhDinTowards Data ScienceBuilding an Image Similarity Search Engine with FAISS and CLIPA guided tutorial explaining how to search your image dataset with text or photo queries, using CLIP embeddings and FAISS indexingAug 232
François PorcherinTowards Data ScienceThe Ultimate Guide to Vision TransformersA comprehensive guide to the Vision Transformer (ViT) that revolutionized computer vision.Aug 301
Tan Pengshi AlvininTowards AIOptical Character Recognition (OCR) with CNN-LSTM Attention Seq2SeqExploring the Attention-based CNN-LSTM Seq2Seq model for effective OCR with TensorFlow6h ago1
Muhammad ArdiinTowards Data SciencePaper Walkthrough: Vision Transformer (ViT)Exploring Vision Transformer (ViT) through PyTorch Implementation from Scratch.Aug 131
The Tenyks BloggerZero-Shot AI: The End of Fine-Tuning as We Know It?How YOLO-World’s zero-shot approach measures up to YOLO’s fine-tuning.Aug 30
VARUN PNMask R-CNN Inference for Simultaneous object detection and segmentation with a ResNet-50 backbone…This is a simple inference of a pretrained Mask R-CNN with Resnet50 backbone and fpn on test image for object detection and segmentation3h ago
Anindya Dey, PhDinTowards Data ScienceSpeeding Up the Vision Transformer with BatchNormHow integrating Batch Normalization in an encoder-only Transformer architecture can lead to reduced training time and inference time.Aug 6