TNN - TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server

•    C++

---

TNN: A high-performance, lightweight neural network inference framework open sourced by Tencent Youtu Lab. It also has many outstanding advantages such as cross-platform, high performance, model compression, and code tailoring. The TNN framework further strengthens the support and performance optimization of mobile devices on the basis of the original Rapidnet and ncnn frameworks. At the same time, it refers to the high performance and good scalability characteristics of the industry's mainstream open source frameworks, and expands the support for X86 and NV GPUs. On the mobile phone, TNN has been used by many applications such as mobile QQ, weishi, and Pitu. As a basic acceleration framework for Tencent Cloud AI, TNN has provided acceleration support for the implementation of many businesses. Everyone is welcome to participate in the collaborative construction to promote the further improvement of the TNN reasoning framework. Chinese OCR demo is the TNN implementation of chineseocr_lite project. It is lightweight and supports tilted, rotated and vertical text recognition.

ocr deep-learning tensorflow inference pytorch tengine face-detection tensorrt mnn coreml ncnn openvino hairsegmentaion

OpenVINO-model-server - Inference model server implementation with Intel performance optimizations and TensorFlow Serving API

•    Python

---

Inference model server implementation with gRPC interface, compatible with TensorFlow serving API and OpenVINO™ as the execution backend. “OpenVINO™ model server” is a flexible, high-performance inference serving component for artificial intelligence models. The software makes it easy to deploy new algorithms and AI experiments, while keeping the same server architecture and APIs like in TensorFlow Serving.

openvino inference ai

object-flaw-detector-cpp

•    C++

---

Object flaw detector application detects anomalies such as color, crack and the orientation of an object moving on a conveyor belt. Anomalies are marked as defective and saved in the color, crack, orientation folders respectively. Also objects with no defects are saved in no_defect folder. These anomalies data are sent to InfluxDB* database and visualized on Grafana*. This application also measures length and width of the object in millimeters. This application accepts input from a video camera or a video file for processing.

intel computer-vision openvino deep-learning reference-implementation

inference-engine-node - Bringing the hardware accelerated deep learning inference to Node

•    Javascript

---

*Other names and brands may be claimed as the property of others. Instal Node.js.

nodejs deep-learning electronjs hardware-acceleration openvino

BMW-Anonymization-API - This repository allows you to anonymize sensitive information in images/videos

•    Python

---

Data privacy and individuals’ anonymity are and always have been a major concern for data-driven companies. To install Docker and Docker Compose on Ubuntu, please follow the link.

docker video ai computer-vision docker-compose tensorflow pytorch object-detection semantic-segmentation bmw no-code tensorflow-training privacy-enhancing-technologies privacy-protection anonymization openvino image-transformation video-anonymization anonymization-api anonymization-technique

BMW-IntelOpenVINO-Detection-Inference-API - This is a repository for a No-Code object detection inference API using the OpenVINO

•    Python

---

This is a repository for an object detection inference API using the OpenVINO. It's supported on both Windows and Linux Operating systems. Models in Intermediate Representation(IR) format, converted using the Intel® OpenVINO™ toolkit v2021.1, can be deployed in this API. Currently, OpenVINO supports conversion for Models trained in several Machine Learning frameworks including Caffe, Tensorflow etc. Please refer to the OpenVINO documentation for further details on converting your Model.

docker cpu computer-vision neural-network rest-api inference resnet deeplearning object-detection inference-engine detection-api detection-algorithm nocode openvino openvino-toolkit openvino-model-zoo

Keras_to_TF_NCS2 - Keras to Tensorflow test for Neural Compute Stick 2

•    Python

---

For that you want to have OpenVino installed and python 3.5 at least. For the python requirements, see the "Requirements" section. If you have a Keras .h5 file, use keras_to_tf.py to create a Tensorflow .pb file.

tensorflow keras openvino ncs2 model-optimizer