“Our solution is designed to employ Intel® optimized machine learning hardware and software technologies to train, test, and operationalize a model to help detect COVID-19 and 14 other thoracic diseases using chest scans. We used the Intel® DevCloud for the Edge and Intel® Distribution of OpenVINO™ toolkit to optimize and deploy our machine learning models across multiple Intel® platforms. As a result, our team was able to accelerate prototyping and deployment at lower costs on the best performing Intel® architecture for our solution.“
- Moloti Nakampe, Accrad R&D
“In the absence of a variety of hardware configurations, it is incredibly challenging to evaluate the performance of today’s AI models on CPU-driven edge compute boxes. Intel® DevCloud for the Edge hit the nail on the head when it provided us with the access and support needed to benchmark our AI models on CPUs with Intel® Distribution of OpenVINO™ toolkit. Since then, we have been using Intel® Distribution of OpenVINO™ toolkit as a default option on appropriately-sized CPU edge compute boxes for our on-premise customer deployments.“
“Using the Intel® DevCloud for Edge allows Luxonis to iterate on our products seamlessly in the physical world, with real-world experimentation and data collection, as well as in the cloud environment for fast improvement of our neural models and computer vision flow. This results in our customers typically getting their proof of concepts up and running in less than one week and products maturing for market in just a few months. DevCloud for the Edge allows us to evaluate performance without the need of hardware in hand, and can iterate across hardware, software, AI, training iterations, and overall performance easily. Leveraging these kinds of tools, we currently have over 100 customers building products off of our platform, which covers over 20 verticals, including e-mobility, cargo - air and ground, food processing, agriculture (in-field, farming and ranching), defense, safety systems (in manufacturing, oil/gas, etc.) to name just a few.“
- Brandon Gilles, CEO, Luxonis Embedded CV & AI
“Because we serve customers with so many different needs, it’s important to quickly achieve the right balance of price and performance for each of our applications. Intel® DevCloud for the Edge lets us test multiple platforms in parallel. That’s a lot of time savings—and time is money—so it’s a no-brainer.“
- Eduard Vazquez, Research Technical Manager, AnyVision
“Because developers can quickly evaluate the performance of their applications in multiple edge computing systems by using Intel® DevCloud for the Edge, they can not only shorten the inspection time to go to market, they can also expect tremendous benefits in terms of investment and maintenance in verification equipment. We are confident that Intel DevCloud for the Edge will accelerate and streamline operations and create new value for more IoT businesses and for more customers.“
- Tomohiro Nagao, Senior Manager, Hitachi, Ltd., Healthcare Business Unit
“With a high performance medical application like ours, a major share of the AI workloads are carried out by the Intel® Distribution of OpenVINO™ toolkit. As our customers' platforms don't adhere to a single hardware configuration, it is crucial that we assess various hardware platforms in advance so we can verify that the performance falls within our specifications. Intel® DevCloud for Edge serves this exact purpose and enables us to benchmark our AI workloads on a variety of platforms not found on premise.“
- Roee Shibolet, VP R&D
Nihon System Kaihatsu
"By benchmarking our trained model on Intel® hardware enabled on the Intel® DevCloud for the Edge, we could accelerate the product development and validation time. It is highly recommended to use Intel® DevCloud for the Edge for AI solution development."
- Masaki Ishihara, Chief Engineer at Nihon System Kaihatsu Co., Ltd.
"Rosmart provides automatic defects detection machines to do the visual inspection work. It can always keep the high quality standard, high inspection efficiency, and low labor cost."
- Alex Zhang, R&D director, Guangdong Rosmart Technology Co., Ltd.
"At Neurolabs, we provide computer vision solutions powered by synthetic data. Our clients expect robust on-premise deployments with fast prediction times. This is where Intel® Distribution of OpenVINO™ toolkit shines, giving us greater flexibility over different hardware configurations and standardizing the model deployment. Intel® DevCloud for the Edge enables us to quickly benchmark our models across multiple architectures and determine the best option for our customer use cases."
- Patric Fulop, Co-Founder & CTO of Neurolabs
"Because of the user experience we are trying to achieve, it is important to find the perfect balance of price and performance for each of our products. Though Intel® DevCloud for the Edge and its well prepared tools and environment, we were able to decrease the time it took to do a wide array of hardware tests on our interactive digital signage solutions, like Intelligent Label."
- Ryota Tone, Content Business Division, Business Development Department Manager, SB Creative Corp.
"Sightcorp's deep learning audience measurement products are hardware agnostic; therefore, it is very important for us to be able to rapidly test and iterate multiple Intel® platforms in parallel while still maintaining the inference speed needed to aggregate quality data in real-time. Intel® DevCloud for the Edge allows all of this to happen without dealing with physical hardware, which is perfect for the time we are currently living in and time spent working from home. For our customers, we strike the right balance between price and performance for each of our products so they can go to market faster and with a clear understanding of device capabilities."
- Joyce Caradonna, CEO of Sightcorp
"We are pushing speech technology into emerging markets where there is a lot of language diversity and a variety of hardware challenges. That means that we need to test a lot of models (for many languages and accents) on edge devices. Intel® DevCloud for the Edge gives our data scientists a way to quickly spin up a notebook and test our models in a diverse set of scenarios. We can then translate these learnings directly into real product modifications and configuration, such that our customers are happy with the performance of our multilingual dialogue products right out of the box!"
- Daniel Whitenack, Data Scientist at SIL Corporation