產品說明0
reComputer J1010-Edge AI (4G)，NVIDIA Jetson Nano 運算 Type-C供電（USB-C）,J1010 NANO 4G（110061362）
※本產品原廠代理從國外進口，有些交期較長，下訂前請詢問！
＊＊reCompute Jetson-10-1-A0 變更 reComputer J1010 變更 reComputer J1010 Nano 4G＊＊
原標題：reComputer Jetson-10-1-A0 with Jetson Nano module, M.2 Key E Slot, Type-C connectors, Aluminium case, pre-installed JetPack System
帶 Jetson Nano 模塊、M.2 Key E 插槽、Type-C 連接器、鋁製外殼、預裝 JetPack 系統（110061362）
2版 標題：reComputer J1010 -Edge AI Device（Nano 4GB+M.2 Key E+1*USB 3.0+2*USB 2.0）
reComputer J1010-Edge AI Device(4G)，NVIDIA Jetson Nano 運算Type-C
3版 新標題： reComputer J1010 -Edge AI Device with Jetson Nano module, M.2 Key E Slot, Type-C connectors, Aluminium case, pre-installed JetPack System（110061362）
Jetson（J1010） 與 Jetson Nano 2GB開發者套件幾乎相同的功能設計
【Part List／清單】
1 x Acrylic Cover 壓克力蓋
1 x Aluminium Frame 鋁製框架
1 x Jetson Nano module 模組
1 x Heatsink 散熱
1 x Carrier board 載板
我們將不包括電源線，請根據您所在的國家/地區選擇合適的形式。我們將不包括 3V TC 電池 (CR1220)
影片：https://youtu.be/9gf287AGMVQ
J1020影片：https://youtu.be/pHS_pgN-Afs
【Note】：
If use some GPIO libraries that causes floating voltage 1.2V~2V , GPIO issues on the carrier board could happen as the normal voltage should be 3V.／如果使用一些導致浮動電壓1.2V~2V的GPIO庫，載板上的GPIO可能會出現問題，因為正常電壓應該是3V。
This is a common situation on the carrier boards, for both the reComputer series and official Nvidia Jetson developer kit.／對於 reComputer 系列和官方 Nvidia Jetson 開發套件來說，這是載板上的常見情況。
Thus, aftersales / warrenty does not come into effect regarding this isssue.
For further information, refer to NVIDIA official document.
【Features／特徵】
- Hand-size edge AI built with NVIDIA Jetson Nano 4GB Production Module, with onboard rich IOs including Gigabit Ethernet port, USB 3.0 & USB 2.0 ports, HDMI port.
手掌大小的邊緣 AI 設備採用 NVIDIA Jetson Nano 4GB 生產模塊構建，板載豐富的 IO，包括千兆以太網端口、USB 3.0 和 USB 2.0 端口、HDMI 端口。。 - 128 NVIDIA CUDA® cores deliver 0.5 TFLOPs (FP16) to run AI frameworks and models for applications like image classification, object detection, segmentation, and speech processing.
128 個 NVIDIA CUDA® 內核提供 0.5 TFLOP (FP16) 來運行 AI 框架和模型，用於圖像分類、對象檢測、分割和語音處理等應用。 - Pre-installed NVIDIA JetPack: support entire Jetson software stack and various developer tools for building fast and robust AI application provided by Seeed Edge AI partners, helps develop innovative AI solution for manufacturing, logistics, retail, service, agriculture, smart city, healthcare, and life sciences, etc
預裝 NVIDIA JetPack：支持整個 Jetson 軟件堆棧和各種開發人員工具，用於構建由 Seeed Edge AI 合作夥伴提供的快速、強大的 AI 應用程序，幫助開發適用於製造、物流、零售、服務、農業、智慧城市、醫療保健、 和生命科學等。
- Incredibly power efficient: powered by Type C 5V/3A, consuming as little as 5 watts.
令人難以置信的節能：Type C 型 5V/3A 供電，功耗低至 5W。 - Expandable with the onboard interfaces and reComputer case, able to mount on the wall with mounting holes on the back.
可通過板載接口和 reComputer 機箱進行擴展，可通過背面的安裝孔安裝在牆上。
【Description】
reComputer series for Jetson are compact edge computers built with NVIDIA advanced AI embedded systems: J10 (Nano 4GB) and J20 (Jetson Xavier NX 8GB and Jetson Xavier 16GB). With rich extension modules, industrial peripherals, and thermal management, reComputer for Jetson is ready to help you accelerate and scale the next-gen AI product by deploying popular DNN models and ML frameworks to the edge and inferencing with high performance.
Jetson 的 reComputer 系列是採用 NVIDIA 高級 AI 嵌入式系統構建的緊湊型邊緣計算機：J10（Nano 4GB）和 J20（Jetson Xavier NX 8GB 和 Jetson Xavier 16GB）。 憑藉豐富的擴展模塊、工業外圍設備和熱管理，reComputer for Jetson 已準備好通過將流行的 DNN 模型和 ML 框架部署到邊緣並進行高性能推理來幫助您加速和擴展下一代 AI 產品。
At Seeed, you will find everything you want to work with NVIDIA Jetson Platform – official NVIDIA Jetson Dev Kits, Seeed-designed carrier boards, and edge devices, as well as accessories.
在 Seeed，您會找到想要與 NVIDIA Jetson 平台一起工作的一切——官方 NVIDIA Jetson 開發套件、Seeed 設計的載板、邊緣設備以及配件。
Welcome to check out our free Edge AI partner program. We are looking forward to leveraging local and global resources to accelerate next-gen AI products together with you.
歡迎查看我們的免費 Edge AI 合作夥伴計劃。 我們期待利用本地和全球資源與您一起加速下一代人工智能產品。
【Hardware overview】
參考載板／Reference carrier board
Nearly the same functional design as Jetson Nano Developer Kit. We have upgraded the carrier board with micro SD card slot.／與 Jetson Nano 開發者套件幾乎相同的功能設計。我們升級了載板，帶有微型SD卡插槽。
Jetson-10-1-A0 （J1010） is a hand-size edge AI box built with Jetson Nano module, rich set of IOs, aluminium case, passive heatsink, pre-installed JetPack System, ready for your next AI application development and deployment.
Jetson-10-1-A0 是一款手掌大小的邊緣 AI 盒子，內置 Jetson Nano 模塊、豐富的 IO 集、鋁製外殼、無源散熱器、預裝 JetPack 系統，為您的下一個 AI 應用程序開發和部署做好準備。
筆記
- 我們已經在reComputer中安裝了JetPack 4.6系統，您可以直接上電使用。
- 如果您想在恢復模式下啟動甚至重新刷機 Jetpack 系統，請查看我們的 wiki。
- 我們將不包括 RTC 電池（2 針）
Note
- Name change: 'reComputer Jetson-10-1-A0' has changed to 'reComputer J1010'.
- We have already installed JetPack 4.6 system in the reComputer and you can directly use it by powering it on.
- Please check our wiki for reflashing Jetpack and expandinging storage.
- We'd like to hear from you, welcome to join our Discord channel to share your thoughts (Jetson edge AI)
相關文件
Reference: NVIDIA, Performance of various deep learning inference networks with Jetson Nano and TensorRT, using FP16 precision and batch size 1
參考：NVIDIA，使用 Jetson Nano 和 TensorRT 的各種深度學習推理網絡的性能，使用 FP16 精度和批量大小 1
Developers can use highly accurate pre-trained models from TAO Toolkit and deploy with DeepStream. Jetson Nano can achieve 11 FPS for PeopleNet- ResNet34 of People Detection, 19 FPS for DashCamNet-ResNet18 of Vehicle Detection, and 101 FPS for FaceDetect-IR-ResNet18 of Face Detection. Benchmark details can be found on NVIDIA®’s DeepStream SDK website.
開發人員可以使用來自 TAO Toolkit 的高度準確的預訓練模型，並使用 DeepStream 進行部署。 Jetson Nano 的 PeopleNet-ResNet34 的人物檢測可以達到 11 FPS，DashCamNet-ResNet18 的車輛檢測可以達到 19 FPS，FaceDetect-IR-ResNet18 的人臉檢測可以達到 101 FPS。 基準測試詳細信息可在 NVIDIA® 的 DeepStream SDK 網站上找到。
Jetson Nano can run a wide variety of advanced networks, including the full native versions of popular ML frameworks like TensorFlow, PyTorch, Caffe/Caffe2, Keras, MXNet, and others.
Jetson Nano 可以運行各種高級網絡，包括流行 ML 框架的完整原生版本，如 TensorFlow、PyTorch、Caffe/Caffe2、Keras、MXNet 等。
reComputer Jetson series is compatible with the entire NVIDIA Jetson software stack, industry-leading AI frameworks, development platforms like Edge Impulse, AlwaysAI, and cloud-based robot development tool Nimbus.
reComputer Jetson 系列兼容整個 NVIDIA Jetson 軟件堆棧、行業領先的 AI 框架、Edge Impulse、AlwaysAI 等開發平台以及基於雲的機器人開發工具 Nimbus。
【Application: next-gen autonomous machine at the edge／應用：邊緣的下一代自主機器】
reComputer Jetson series is ideal for building autonomous machines and complex AI system tasks of image recognition, object detection and localization, pose estimation, semantic segmentation, video processing, and intelligent analytics.／reComputer Jetson 系列非常適合構建自主機器和復雜的 AI 系統任務，包括圖像識別、對象檢測和定位、姿勢估計、語義分割、視頻處理和智能分析。
Edge AI into the Wild: UAV, Drone, Wildlife protection, Agriculture／邊緣人工智能進入野外：無人機、無人機、野生動物保護、農業
Smart City: Traffic, Retail, Healthcare／智慧城市：交通、零售、醫療保健
Industry 4.0: Manufacturing, Logistics, Delivery, Service／工業 4.0：製造、物流、交付、服務
【Prebuild system for edge AI integration／用於邊緣 AI 集成的預構建系統】
All NVIDIA® Jetson™ modules and developer kits are supported by the same software stack, enabling you to develop once and deploy everywhere. Jetson Software is designed to provide end-to-end acceleration for AI applications and accelerate your time to market. We bring the same powerful NVIDIA technologies that power data center and cloud deployments to the edge.
所有 NVIDIA® Jetson™ 模塊和開發人員套件均由同一軟件堆棧支持，使您能夠一次開發並隨處部署。 Jetson Software 旨在為 AI 應用程序提供端到端加速並加快您的上市時間。 我們將支持數據中心和雲部署的強大 NVIDIA 技術帶到邊緣。
NVIDIA JetPack includes NVIDIA Container Runtime with Docker integration, enabling GPU accelerated containerized applications on Jetson platform. Jetpack also brings support for NVIDIA Triton™ Inference Server to simplify the deployment of AI models at scale.
NVIDIA JetPack 包括具有 Docker 集成的 NVIDIA Container Runtime，可在 Jetson 平台上啟用 GPU 加速的容器化應用程序。 Jetpack 還支持 NVIDIA Triton™ 推理服務器，以簡化大規模 AI 模型的部署。
【NVIDIA Jetson powered Edge AI platform at Seeed／Seeed 的 NVIDIA Jetson 支持 Edge AI 平台】
At Seeed, you will find everything you want to work with NVIDIA Jetson Platform – official NVIDIA Jetson Dev Kits, Seeed-designed carrier boards, and edge devices, as well as accessories.
在 Seeed，您會找到想要與 NVIDIA Jetson 平台一起工作的一切——官方 NVIDIA Jetson 開發套件、Seeed 設計的載板、邊緣設備以及配件。
Seeed will continue working on the Jetson product line and will be ready to combine our partners’ unique technology with Seeed’s hardware expertise for an end-to-end solution.
Seeed 將繼續致力於 Jetson 產品線，並準備將我們合作夥伴的獨特技術與 Seeed 的硬件專業知識相結合，以提供端到端的解決方案。
Application: for both beginners and experts, build your next-gen autonomous machine at the edge
Edge AI Applications
reComputer J1010 and J1020, powered by Jetson Nano, are ideal for learning AI and building AI applications for image recognition, object detection, pose estimation, video processing, and many more. Check out the following application example with tutorials!
Find in the Jetson Community Resources page tools and tutorials the community has created to power your development experience, and check out the Community Projects page to inspire your next project!
LEARN AND DOCUMENTS
Documentations
Learn
Install the SD card driver for the J101 carrier
The method is flashing NVIDIA JetPack OS to the SD card on J101 Carrier Board which is operated on the reComputer J1010. So Flash JetPack OS into reComputer J1010 first is required.
[Wiki] Maskcam: Crowd Face Mask Usage Monitoring based on NVIDIA Jetson Nano
MaskCam is a prototype reference design for a Jetson Nano-based smart camera system that measures crowd face mask usage in real-time, with all AI computation performed at the edge. MaskCam detects and tracks people in its field of view and determines whether they are wearing a mask via an object detection, tracking, and voting algorithm.
[Wiki] Knife Detection: An Object Detection Model deployed on Triton Inference Sever based on reComputer
In this wiki, we are going to deploy a Deep Learning model on reComputer J1010 that could detect prohibited items (knives) with the reComputer J1010 where we use one reComputer J1010 as our inference server.
[Wiki] Dual No code Edge AI Tool Demo: Warehouse Security & Farm Guards
We are pleased to bring you our new experience on the reComputer built with Jetson Nano for quick and easy object recognition. It includes Warehouse Security and Farm Guards two demos in is wiki.
[Wiki] Boot NVIDIA System from SD card for J101 Carrier Board
Since the J101 Carrier Board has inserted SD card slot, we provide this wiki for you to boot NVIDIA System from SD card for the carrier board. You can also change CLK frequency here.
[Wiki] Install NVIDIA System based on Seeed Studio J101 Carrier Board
This is the wiki shows you how to install NVIDIA System based on Seeed Studio J101 Carrier Board
相關資訊
【Interface-rich reference carrier board／接口豐富的參考載板】
Nearly the same functional design as Jetson Nano 2GB Developer Kit／與 Jetson Nano 2GB開發者套件幾乎相同的功能設計
Seeed reference carrier board for Jetson-10-1-A0 is （J1010） a high-performance, interface rich NVIDIA Jetson Nano compatible carrier board, providing HDMI 2.0, Gigabit Ethernet, USB 3.0, USB 2.0, CSI camera, GPIO, I2C, I2S, fans, and other rich peripheral interfaces. It has nearly the same functional design and size as the carrier board of Nvidia Jetson Nano 2GB Developer Kit | NVIDIA Developer. Take advantage of the small form factor, sensor-rich interfaces, and big performance to bring new capability to all your embedded AI and edge systems.
Seeed Jetson-10-1-A0 （J1010） 參考載板是一款高性能、接口豐富的 NVIDIA Jetson Nano 兼容載板，提供 HDMI 2.0、千兆以太網、USB 3.0、USB 2.0、CSI 攝像頭、GPIO、I2C、I2S、風扇 等豐富的外圍接口。 它的功能設計和尺寸與 Nvidia Jetson Nano 2GB 開發者套件的載板幾乎相同 | 英偉達開發者。 利用小巧的外形、豐富的傳感器接口和強大的性能，為您的所有嵌入式 AI 和邊緣系統帶來新功能。
【Desktop, Wall Mount, or fit in anywhere／桌面、壁掛式或適合任何地方】
With an overall dimension of 130mm*120mm*50mm, it is only around 1/10 of the size of an ordinary computer case which makes it possible to fit in edge AI scenarios. The back screw holes allow you to hang the product as you need. We also provide other editions case like blue, silver and silver mental, whose stackable structure allows you to stack more middle layers to create rooms very easily.
外形尺寸為130mm*120mm*50mm，只有普通電腦機箱的1/10左右，可以適應邊緣AI場景。 背面螺絲孔可讓您根據需要懸掛產品。 我們還提供其他版本的案例，如藍色、銀色和銀色金屬，其可堆疊結構讓您可以堆疊更多中間層以輕鬆創建房間。
【Work with Seeed Ecosystem／與 Seeed 生態系統合作】
Deploying an AI idea can be faster, flexible, even scalable for everyone. Seeed Jetson Platform targets on helping educators, developers and enterprises deploy ML in the real world. By consolidating Seeed’s best-in-class hardware, cutting-edge technology from our software partners and all developers from the community, we aim at emerging all kinds of AI scenarios in our open-source platform to faster industry digital transformation. We are looking for partners to join our ecosystem together to deliver solutions to different industries together. Please contact cooperation@seeed.cc for more partnership ecosystem information.
部署人工智能想法可以更快、更靈活，甚至可以為每個人擴展。 Seeed Jetson 平台旨在幫助教育工作者、開發人員和企業在現實世界中部署機器學習。 通過整合 Seeed 一流的硬件、軟件合作夥伴和社區所有開發人員的尖端技術，我們旨在在我們的開源平台中出現各種 AI 場景，以加快行業數字化轉型。 我們正在尋找合作夥伴加入我們的生態系統，共同為不同行業提供解決方案。 請聯繫合作@seeed.cc 了解更多合作生態系統信息。
