#cplusplus #deep_learning #machine_learning #vision

https://github.com/BVLC/caffe

#python #class_activation_maps #deep_learning #grad_cam #interpretability #interpretable_ai #interpretable_deep_learning #pytorch #score_cam #vision_transformers #visualizations

https://github.com/jacobgil/pytorch-grad-cam

#other #attention_mechanism #attention_mechanisms #awesome_list #computer_vision #deep_learning #detr #papers #self_attention #transformer #transformer_architecture #transformer_awesome #transformer_cv #transformer_models #transformer_with_cv #transformers #vision_transformer #visual_transformer #vit

https://github.com/cmhungsteve/Awesome-Transformer-Attention

#python #classification #computer_vision #object_detection #pytorch #self_supervised_learning #transformers #vision_transformer

https://github.com/alibaba/EasyCV

#python #deep_learning #deep_learning_library #image_captioning #multimodal_datasets #multimodal_deep_learning #salesforce #vision_and_language #vision_framework #vision_language_pretraining #vision_language_transformer #visual_question_anwsering

https://github.com/salesforce/LAVIS

#python #computer_vision #convolutional_networks #embedding_vectors #embeddings #feature_extraction #feature_vector #image_processing #image_retrieval #machine_learning #milvus #pipeline #towhee #transformer #unstructured_data #video_processing #vision_transformer #vit

https://github.com/towhee-io/towhee

#swift #app #camera #find #ios #ocr #photos #realm #swiftui #uikit #vision

https://github.com/aheze/OpenFind

#python #foundation_models #representation_learning #vision_transformer

https://github.com/baaivision/EVA

#python #chatgpt #clip #deep_learning #gpt #hacktoberfest #hnsw #information_retrieval #knn #large_language_models #machine_learning #machinelearning #multi_modal #natural_language_processing #search_engine #semantic_search #tensor_search #transformers #vector_search #vision_language #visual_search

https://github.com/marqo-ai/marqo

#cplusplus #artificial_intelligence #computer_vision #document #document_analysis #document_intelligence #document_recognition #document_understanding #documentai #end_to_end_ocr #multimodal #multimodal_deep_learning #ocr #scene_text_detection #scene_text_detection_recognition #scene_text_recognition #text_detection #text_recognition #vision_language #vision_language_model #vision_language_transformer

https://github.com/AlibabaResearch/AdvancedLiterateMachinery

#python #augmix #convnext #distributed_training #dual_path_networks #efficientnet #image_classification #imagenet #maxvit #mixnet #mobile_deep_learning #mobilenet_v2 #mobilenetv3 #nfnets #normalization_free_training #pretrained_models #pretrained_weights #pytorch #randaugment #resnet #vision_transformer_models

PyTorch Image Models (`timm`) is a comprehensive library that includes a wide range of state-of-the-art image models, layers, utilities, optimizers, and training scripts. Here are the key benefits `timm` offers over 300 pre-trained models from various families like Vision Transformers, ResNets, EfficientNets, and more, allowing you to choose the best model for your task.
- **Pre-trained Weights** You can easily extract features at different levels of the network using `features_only=True` and `out_indices`, making it versatile for various applications.
- **Optimizers and Schedulers** It provides several augmentation techniques like AutoAugment, RandAugment, and regularization methods like DropPath and DropBlock to enhance model performance.
- **Reference Training Scripts**: Included are high-performance training, validation, and inference scripts that support multiple GPUs and mixed-precision training.

Overall, `timm` simplifies the process of working with deep learning models for image tasks by providing a unified interface and extensive tools for training and evaluation.

https://github.com/huggingface/pytorch-image-models

#python #chinese #clip #computer_vision #contrastive_loss #coreml_models #deep_learning #image_text_retrieval #multi_modal #multi_modal_learning #nlp #pretrained_models #pytorch #transformers #vision_and_language_pre_training #vision_language

This project is about a Chinese version of the CLIP (Contrastive Language-Image Pretraining) model, trained on a large dataset of Chinese text and images. Here’s what you need to know This model helps you quickly perform tasks like calculating text and image features, cross-modal retrieval (finding images based on text or vice versa), and zero-shot image classification (classifying images without any labeled examples).
- **Ease of Use** The model has been tested on various datasets and shows strong performance in zero-shot image classification and cross-modal retrieval tasks.
- **Resources**: The project includes pre-trained models, training and testing codes, and detailed tutorials on how to use the model for different tasks.

Overall, this project makes it easy to work with Chinese text and images using advanced AI techniques, saving you time and effort.

https://github.com/OFA-Sys/Chinese-CLIP

#swift #ai #android #barcode #camera #instagram #ios #javascript #jsi #library #native #qr #qrcode #react #react_native #react_native_camera #scanner #snapchat #typescript #vision #worklet

VisionCamera is a powerful camera library for React Native that offers many useful features. You can capture photos and videos, scan QR codes and barcodes, use multiple cameras, and adjust resolutions and frame rates. It also supports advanced features like facial recognition, object detection, and real-time video chats through frame processors. Additionally, you can draw shapes, text, and filters on the camera view, and it includes smooth zooming, fast pause and resume, HDR and night modes, and a custom video pipeline. Installing it is easy with npm, and there are detailed guides and examples to help you get started. Using VisionCamera can enhance your app's camera capabilities significantly.

https://github.com/mrousavy/react-native-vision-camera

#python #api #automation #browser #browser_automation #computer #gpt #llm #playwright #python #rpa #vision #workflow

Skyvern is a tool that automates browser-based workflows using Large Language Models (LLMs) and computer vision. It can interact with websites without needing custom scripts, making it resistant to website layout changes. Here’s how it benefits you Skyvern can handle tasks on websites it has never seen before, filling out forms, extracting data, and even handling 2FA authentication.
- **Flexibility** Unlike traditional automation methods, Skyvern is less likely to break when website layouts change.
- **Ease of Use**: You can create tasks and workflows through a simple API or a user-friendly UI, without needing to write complex code.

Overall, Skyvern simplifies and stabilizes the automation of web-based tasks, making it easier to manage and scale your workflows.

https://github.com/Skyvern-AI/skyvern

#rust #ai #computer_vision #llm #machine_learning #ml #multimodal #vision

ScreenPipe is an AI assistant that records your screen and voice 24/7, giving you all the context you need. It's like having a personal recorder that helps you remember everything. You can use it as a desktop app, command line tool, or even integrate it into other applications. The benefit is that you'll never miss important details again, and you can prepare for the future where data is crucial. Plus, it's open-source, so you can customize it to your needs. Downloading ScreenPipe can help you stay organized and prepared in the age of super intelligence.

https://github.com/mediar-ai/screenpipe