{"title":"USB","description":"\u003cp\u003eBrowse our USB collection. Hot Sale.\u003c\/p\u003e","products":[{"product_id":"right-angle-usb-c-adapter","title":"Right Angle USB-C Adapter","description":"\u003cp\u003eThis right-angle USB-C adapter is great for those scenarios where you need to shift cables from your Raspberry Pi 4 out to the side immediately. The adapter simply plugs into your Raspberry Pi 4 and you plug your usual USB-C power supply into the other end - easy!\u003c\/p\u003e\n\u003cp\u003eYou can use these with other USB-C devices too, and you don't need to worry about which way up it is as USB-C doesn't care (that's why we're big fans of USB-C!).\u003c\/p\u003e\n\u003cp\u003eNeed to 'adapt' things for your Raspberry Pi another way? Check out our power adapter section for more handy parts!\u003c\/p\u003e","brand":"The Pi Hut","offers":[{"title":"Default Title","offer_id":50555995324655,"sku":"etq1787257819730","price":3.7,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0754\/8515\/1471\/files\/right-angle-usb-c-adapter_1.jpg?v=1787257828"},{"product_id":"usb-type-c-socket-smt-inline-breakout-board-discontinued","title":"USB Type C Socket - SMT Inline Breakout Board [Discontinued]","description":"\u003cp\u003eThis USB Type C breakout is kinda interesting, it looks similar to our right angle USB C socket breakout, but it's an 'inline' style with pads for soldering to the connections. We think it could be handy for making custom cable harnesses! Unlike our breakout, it also has the true dual-row USB C connector and all pads broken out. It does \u003cstrong\u003enot\u003cem\u003e \u003c\/em\u003e\u003c\/strong\u003ehave any resistors to set direction\/current - required to have USB C enumerate. It's really \u003cem\u003ejust\u003c\/em\u003e a connector breakout. That said, it could be handy for inline connections that need a range of pin connections\u003c\/p\u003e\u003cp\u003eFor more details, we like this Introduction to USB C app note.\u003c\/p\u003e\u003cp\u003e\u003c\/p\u003e\u003ch2\u003eTechnical Details\u003c\/h2\u003e\u003cdiv id=\"tab-technical-details-content\" class=\"panel-collapse collapse in\"\u003e \u003cp\u003eProduct Dimensions: 17.0mm x 15.6mm x 3.2mm \/ 0.7\" x 0.6\" x 0.1\" \u003c\/p\u003e\n\u003cp\u003eProduct Weight: 1.0g \/ 0.0oz \u003c\/p\u003e\n\u003cul id=\"product-files\"\u003e \u003c\/ul\u003e \u003c\/div\u003e","brand":"Adafruit","offers":[{"title":"Default Title","offer_id":50555995357423,"sku":"ohs1787257819940","price":2.45,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0754\/8515\/1471\/files\/usb-type-c-socket---smt-inline-breakout-board-discontinued_1.jpg?v=1787257828"},{"product_id":"raspberry-pi-dual-band-5ghz24ghz-usb-wifi-adapter-with-antenna-discontinued","title":"Raspberry Pi Dual-Band 5GHz\/2.4GHz USB WiFi Adapter with Antenna [Discontinued]","description":"\u003cp class=\"system-title\"\u003e\u003cstrong\u003eIMPORTANT! To use this WiFi adapter with Raspberry Pi OS, you will need to install a driver.\u003c\/strong\u003e\u003cspan\u003e \u003c\/span\u003eThis adapter will not automatically work without driver installation!\u003cbr\u003e\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003e\u003cspan\u003eWe have documented the installation process for you here.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003e\u003cstrong\u003e\u003cspan\u003ePlease note that this driver works as of 18\/09\/2023 however changes to Raspberry Pi OS or the driver repository are out of our control and may break at any time.\u003c\/span\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003chr\u003e\n\u003cp\u003eIf the on-board WiFi antenna on your Raspberry Pi isn't giving you enough range, this dual-band 2.4GHz\/5GHz USB 2.0 WiFi adapter is a great option.\u003cbr\u003e\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003eThe antenna is dual-band meaning it can connect to a 2.4GHz or 5GHz network, and supports the 802.11ac standard (3 times faster than 802.11n networks).\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003eThe USB 2.0 adapter features an LED status light and a removable antenna.\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003eCompatible with both the Raspberry Pi 4 and Raspberry Pi 3B+\/3.\u003c\/p\u003e\n\u003ch2 class=\"system-title\"\u003e\u003cstrong\u003eInstallation\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp class=\"system-title\"\u003e\u003cstrong\u003eThe adapter requires driver installation\u003c\/strong\u003e which will take around 5 minutes. See our installation guide here.\u003c\/p\u003e\n\u003ch2 class=\"system-title\"\u003e\u003cstrong\u003eFeatures\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cdiv class=\"system-description\"\u003e\n\u003cul class=\"list-paddingleft-2\"\u003e\n\u003cli\u003eCompatible with Raspberry Pi 4 and Raspberry Pi 3\u003c\/li\u003e\n\u003cli\u003e150Mbps at 2.4GHz and 433Mbps at 5GHz\u003c\/li\u003e\n\u003cli\u003eThe external high gain adjustable \u0026amp; detachable antenna provides wide coverage for your wireless network\u003c\/li\u003e\n\u003cli\u003eBackwards compatible with 802.11n\/g\/b\/a\u003c\/li\u003e\n\u003cli\u003eLED status light\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003e\u003cstrong\u003eSpecifications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul class=\"list-paddingleft-2\"\u003e\n\u003cli\u003eChip: Realtek \u003cspan\u003eRTL8811cu\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003eInterface: USB 2.0\u003c\/li\u003e\n\u003cli\u003eWireless transmit power: 20dBm\u003c\/li\u003e\n\u003cli\u003eNetwork Speed: 600Mbps\u003c\/li\u003e\n\u003cli\u003eNetwork Mode: Dual Band\u003c\/li\u003e\n\u003cli\u003eApplicable System: Windows Vista \/ XP \/ 2000\/7\/8\/10, \u003cstrong\u003eLinux\u003c\/strong\u003e, Mac OS\u003c\/li\u003e\n\u003cli\u003eUSB Head Size: 4.5 x 2 x 1.2cm\u003c\/li\u003e\n\u003cli\u003eConnector (USB end): RP-SMA Female\u003c\/li\u003e\n\u003cli\u003eConnector (Antenna): RP-SMA Male\u003c\/li\u003e\n\u003cli\u003eAntenna Length: 10.8cm\u003c\/li\u003e\n\u003cli\u003eNet Weight: 12g\u003c\/li\u003e\n\u003cli\u003eDatasheet\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\n\u003ch2\u003e\u003cstrong\u003ePackage includes\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e1 x Dual Band 2.4G\/5G USB Wifi Antenna Adapter\u003c\/li\u003e\n\u003cli\u003e1 x CD \u003cem data-mce-fragment=\"1\"\u003e(because the 90s lives on!)\u003c\/em\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eNote: Does not include Raspberry Pi\u003c\/strong\u003e\u003c\/p\u003e","brand":"The Pi Hut","offers":[{"title":"Default Title","offer_id":50556008136943,"sku":"yde1787258054025","price":6.9,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0754\/8515\/1471\/files\/raspberry-pi-dual-band-5ghz24ghz-usb-wifi-adapter-with-antenna-discontinued_1.jpg?v=1787258062"},{"product_id":"raspberry-pi-dual-band-5ghz24ghz-usb-wifi-nano-adapter-discontinued","title":"Raspberry Pi Dual-Band 5GHz\/2.4GHZ USB WiFi Nano Adapter [Discontinued]","description":"\u003cp class=\"system-title\"\u003e\u003cstrong\u003eIMPORTANT! To use this WiFi adapter with Raspberry Pi OS, you will need to install a driver.\u003c\/strong\u003e This adapter will not automatically work without driver installation!\u003cbr\u003e\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003e\u003cspan style=\"color: #000000;\"\u003eWe have documented the installation process for you here.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003e\u003cstrong\u003e\u003cspan style=\"color: #000000;\"\u003ePlease note that this driver works as of 18\/09\/2023 however changes to Raspberry Pi OS or the driver repository are out of our control and may break at any time.\u003c\/span\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003chr\u003e\n\u003cp class=\"system-title\"\u003eIf the on-board WiFi antenna on your Raspberry Pi isn't giving you enough range, this dual-band 2.4GHz\/5GHz USB 2.0 WiFi adapter is a great option.\u003cbr\u003e\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003eThe adapter is dual-band meaning it can connect to a 2.4GHz or 5GHz network, and supports the 802.11ac standard (3 times faster than 802.11n networks).\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003eThe USB 2.0 adapter features an LED status light.\u003c\/p\u003e\n\u003cp class=\"system-title\"\u003eCompatible with both the Raspberry Pi 4 and Raspberry Pi 3B+\/3.\u003c\/p\u003e\n\u003ch2 class=\"system-title\"\u003e\u003cstrong\u003eInstallation\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp class=\"system-title\"\u003e\u003cstrong\u003eThe adapter requires driver installation\u003c\/strong\u003e which will take around 5 minutes.\u003cspan\u003e \u003c\/span\u003eSee our installation guide here.\u003c\/p\u003e\n\u003ch2 class=\"system-title\"\u003e\u003cstrong\u003eFeatures\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cdiv class=\"system-description\"\u003e\n\u003cul class=\"list-paddingleft-2\"\u003e\n\u003cli\u003eCompatible with Raspberry Pi 4 and Raspberry Pi 3\u003c\/li\u003e\n\u003cli\u003e\n\u003cspan style=\"font-size: 0.875rem;\"\u003e150Mbps at 2.4GHz and 433Mbps at 5GHz\u003c\/span\u003e\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003eNano size - compact, low-weight dual-band performance\u003c\/li\u003e\n\u003cli\u003eBackwards compatible with 802.11n\/g\/b\/a\u003c\/li\u003e\n\u003cli\u003eLED status light\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003e\u003cstrong\u003eSpecifications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul class=\"list-paddingleft-2\"\u003e\n\u003cli\u003eChip: Realtek RTL8811cu\u003c\/li\u003e\n\u003cli\u003eInterface: USB 2.0\u003c\/li\u003e\n\u003cli\u003eWireless transmit power: 18dBm\u003c\/li\u003e\n\u003cli\u003eNetwork Speed: 600Mbps\u003c\/li\u003e\n\u003cli\u003eNetwork Mode: Dual Band\u003c\/li\u003e\n\u003cli\u003eApplicable System: Windows Vista \/ XP \/ 2000\/7\/8\/10, \u003cstrong\u003eLinux\u003c\/strong\u003e, Mac OS\u003c\/li\u003e\n\u003cli\u003eSize: 31.7mm x 16.3mm x 7.3mm\u003c\/li\u003e\n\u003cli\u003eNet Weight: 2.5g\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\n\u003ch2\u003e\u003cstrong\u003ePackage includes\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e1 x Dual Band 2.4G\/5G USB Wifi Adapter\u003c\/li\u003e\n\u003cli\u003e1 x CD \u003cem\u003e(because the 90s lives on!)\u003c\/em\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eNote: Does not include Raspberry Pi\u003c\/strong\u003e\u003c\/p\u003e","brand":"The Pi Hut","offers":[{"title":"Default Title","offer_id":50556008169711,"sku":"llt1787258055786","price":4.88,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0754\/8515\/1471\/files\/raspberry-pi-dual-band-5ghz24ghz-usb-wifi-nano-adapter-discontinued_1.jpg?v=1787258064"},{"product_id":"straight-usb-c-to-21mm-barrel-jack-adapter","title":"Straight USB-C to 2.1mm Barrel Jack Adapter","description":"\u003cp\u003eThis handy adapter has a female 2.1mm barrel jack socket on one end and a male \u003cstrong\u003eUSB-C\u003c\/strong\u003e connector on the other, ideal for powering your Raspberry Pi 4 from a 5V 2.1mm DC power supply.\u003c\/p\u003e\n\u003cp\u003eThis adapter will pass whatever voltage you put into the barrel jack end, so \u003cstrong\u003ewhen using with a Raspberry Pi you MUST ensure it's a well-regulated 5V power supply\u003c\/strong\u003e. The barrel jack has a centre-positive tip.\u003c\/p\u003e\n\u003cp\u003eYou can of course use it for any other device that uses a USB-C connection too! We also stock an angled version if you need to lose your power cables to the side.\u003c\/p\u003e","brand":"The Pi Hut","offers":[{"title":"Default Title","offer_id":50556008202479,"sku":"uuw1787258055836","price":3.5,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0754\/8515\/1471\/files\/straight-usb-c-to-21mm-barrel-jack-adapter_1.jpg?v=1787258064"},{"product_id":"1080p-full-hd-usb-webcam-with-built-in-microphone","title":"1080p Full-HD USB Webcam with Built-in Microphone","description":"\u003cp\u003eThis 1080p Full-HD USB webcam is the perfect add-on if you want to use your Raspberry Pi for video calls - we've tested this and had great results with web versions of Google Meet, Microsoft Teams and Skype!\u003c\/p\u003e\n\u003cp\u003e(\u003cstrong\u003eNote: Does not work with Zoom\u003c\/strong\u003e. Something changed with Zoom's web-based service earlier this year which broke compatibility with the Raspberry Pi and this camera)\u003c\/p\u003e\n\u003cp\u003eCombined with the small, light and mobile Raspberry Pi, you can now meet with friends and colleagues in any room in the house! Simply plug this into your Raspberry Pi's USB port and enjoy high-definition work video calls, chats with friends...or simply take some simple photography or video clips.\u003c\/p\u003e\n\u003cp\u003eThe camera has a built-in microphone with noise-cancelling technology for clearly capturing your voice, so no additional audio capture device is necessary. It also features an anti-glare lens and a 360-degree swivel on top of a stable mounting clip which fits on top of desks, laptops and monitors.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eUpdate\u003c\/strong\u003e: We found that two different versions of this camera were in circulation, with one that didn't work well with the Raspberry Pi. We now ensure (via testing) that our stock is the version that works with the Raspberry Pi.\u003c\/p\u003e\n\u003ch2\u003eUsage Tips\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eMost online video meeting services will ask for permission to use the microphone and camera when a meeting starts. You then usually need to reload\/refresh before this permission will work properly.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003eThe Raspberry Pi isn't a £500 Intel PC (!), so you may experience a slower-than-usual experience when using some services. Remember - it's a $35 microcomputer!\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eDoes not work with Zoom\u003c\/strong\u003e - but we've tested it with great results on Teams, Google Meet and Skype. Other services are untested.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eSoftware Recommendations\u003c\/h2\u003e\n\u003ch3\u003eRaspberry Pi OS Update\u003c\/h3\u003e\n\u003cp\u003eWhilst the camera should require no software installation to work out of the box, it's advised to update your Raspberry Pi OS as most recent versions include some improvements on how audio\/video is managed.\u003c\/p\u003e\n\u003cp\u003eOpen a terminal window and run the following commands:\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003esudo apt-get update\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003esudo apt full-upgrade\u003c\/strong\u003e\u003c\/p\u003e\n\u003ch2\u003eCommunity Recommendation\u003c\/h2\u003e\n\u003cp\u003eOne of our customers has also recommended using this with Pulse Audio Utilities to enable a graphical \u003cspan data-mce-fragment=\"1\"\u003einterface on Sound \u0026amp; Video to show which devices are connected and includes volume control (thanks Mark!).\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan data-mce-fragment=\"1\"\u003eInstall via terminal using:\u003c\/span\u003e\u003cspan data-mce-fragment=\"1\"\u003e \u003cstrong\u003esudo apt install pavucontrol pulseaudio-utils\u003c\/strong\u003e\u003c\/span\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003ch2\u003eFeatures\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eModel number: A4Tech PK-910H\u003c\/li\u003e\n\u003cli\u003e1080p Full-HD Webcam\u003c\/li\u003e\n\u003cli\u003eStill images: Up to 16 Megapixels (4608x3456 software interpolated)\u003c\/li\u003e\n\u003cli\u003eVideo resolution: Up to 2 Megapixels\u003c\/li\u003e\n\u003cli\u003eFrame rate: 30fps\u003c\/li\u003e\n\u003cli\u003eInterface: USB 2.0\u003c\/li\u003e\n\u003cli\u003eMicrophone: Built-in\u003c\/li\u003e\n\u003cli\u003eCord length: 150cm\u003c\/li\u003e\n\u003cli\u003ePower rating: 5V 230mA\u003c\/li\u003e\n\u003cli\u003eWorks with Raspberry Pi, Windows and Mac\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"A4Tech","offers":[{"title":"Default Title","offer_id":50556008235247,"sku":"ihk1787258057363","price":19.84,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0754\/8515\/1471\/files\/1080p-full-hd-usb-webcam-with-built-in-microphone_1.jpg?v=1787258065"},{"product_id":"coral-usb-accelerator","title":"Coral USB Accelerator","description":"\u003cp\u003e\u003cspan\u003eThe Coral USB Accelerator is a USB accessory that brings machine learning inferencing to existing systems. It works with the Raspberry Pi and Linux, Mac, and Windows systems.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003eThe Accelerator \u003cstrong\u003eadds an Edge TPU coprocessor\u003c\/strong\u003e to your system, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port!\u003c\/p\u003e\n\u003cp class=\" small-headline mk-heading\" id=\"performs-high-speed-ml-inferencing\"\u003e\u003cstrong\u003ePerforms High-speed Machine Learning Inferencing\u003c\/strong\u003e\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003eThe on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS, in a power-efficient manner.\u003cspan\u003e See below section for performance benchmarks.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003e\u003cspan\u003e\u003c\/span\u003e\u003cstrong\u003eSupports all major platforms\u003c\/strong\u003e\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003eConnects via USB to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10.\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003e\u003cstrong\u003eSupports TensorFlow Lite\u003c\/strong\u003e\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003eNo need to build models from the ground up.\u003cspan\u003e \u003c\/span\u003eTensorFlow Lite\u003cspan\u003e \u003c\/span\u003emodels can be compiled to run on the Edge TPU.\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003e\u003cstrong\u003eSupports AutoML Vision Edge\u003c\/strong\u003e\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003eEasily build and deploy fast, high-accuracy custom image classification models to your device with\u003cspan\u003e \u003c\/span\u003eAutoML Vision Edge.\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003e\u003cstrong\u003eTech specs\u003c\/strong\u003e\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\u003c\/p\u003e\n\u003ctable class=\"table-group-table\" style=\"height: 72px;\" border=\"1\"\u003e\n\u003ctbody\u003e\n\u003ctr style=\"height: 36px;\"\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"height: 36px; width: 99px;\"\u003eML accelerator\u003c\/td\u003e\n\u003ctd style=\"height: 36px; width: 206px;\"\u003eGoogle Edge TPU coprocessor:\u003cbr\u003e4 TOPS (int8); 2 TOPS per watt\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 18px;\"\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"height: 18px; width: 99px;\"\u003eConnector\u003c\/td\u003e\n\u003ctd style=\"height: 18px; width: 206px;\"\u003eUSB 3.0 Type-C* (data\/power)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 18px;\"\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"height: 18px; width: 99px;\"\u003eDimensions\u003c\/td\u003e\n\u003ctd style=\"height: 18px; width: 206px;\"\u003e65 mm x 30 mm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003e* Compatible with USB 2.0 but inferencing speed is much slower.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eDatasheet \u0026amp; Resources\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eDatasheet\u003c\/li\u003e\n\u003cli\u003eGetting started with the USB Accelerator\u003c\/li\u003e\n\u003cli\u003eUSB Accelerator datasheet\u003c\/li\u003e\n\u003cli\u003eCoral Edge TPU Frequently asked questions (FAQ)\u003c\/li\u003e\n\u003cli\u003e\nEdge TPU Python API overview\n\u003cul\u003e\n\u003cli\u003eNote: this is NOT the TensorFlow Lite API, but an alternative API intended for users who have not used TensorFlow before and simply want to start with image classification and object detection\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003e3D CAD model (.STEP file)\u003c\/li\u003e\n\u003cli\u003eEdge TPU inferencing overview\u003c\/li\u003e\n\u003cli\u003eTensorFlow models on the Edge TPU\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003ePerformance Benchmarks\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003eAn individual Edge TPU is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). How that translates to performance for your application depends on a variety of factors. Every neural network model has different demands, and \u003cstrong\u003eif you're using the USB Accelerator device, total performance also varies based on the host CPU, USB speed, and other system resources.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003eWith that said, the table below compares the time spent to perform a single inference with several popular models on the Edge TPU. For the sake of comparison, all models running on both CPU and Edge TPU are the TensorFlow Lite versions.\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003eThis represents a small selection of model architectures that are compatible with the Edge TPU:\u003c\/p\u003e\n\u003cp class=\" body-copy mk-paragraph\"\u003e\u003cb\u003eNote:\u003c\/b\u003e\u003cspan\u003e These figures measure the time required to execute the model only. It does not include the time to process input data (such as down-scaling images to fit the input tensor), which can vary between systems and applications. These tests are also performed using C++ benchmark tests, whereas our public \u003c\/span\u003ePython benchmark scripts\u003cspan\u003e may be slower due to overhead from Python.\u003c\/span\u003e\u003c\/p\u003e\n\u003ctable border=\"1\"\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth\u003e\u003cstrong\u003eModel architecture\u003c\/strong\u003e\u003c\/th\u003e\n\u003cth class=\"blue\"\u003e\u003cstrong\u003eDesktop CPU\u003cspan\u003e \u003c\/span\u003e\u003csup\u003e1\u003c\/sup\u003e\u003c\/strong\u003e\u003c\/th\u003e\n\u003cth class=\"blue\"\u003e\n\u003cstrong\u003eDesktop CPU\u003cspan\u003e \u003c\/span\u003e\u003csup\u003e1\u003c\/sup\u003e\u003cbr\u003e+ USB Accelerator (USB 3.0)\u003c\/strong\u003e\u003cbr\u003e\u003cspan class=\"notice\"\u003ewith Edge TPU\u003c\/span\u003e\n\u003c\/th\u003e\n\u003cth class=\"green\"\u003e\u003cstrong\u003eEmbedded CPU\u003cspan\u003e \u003c\/span\u003e\u003csup\u003e2\u003c\/sup\u003e\u003c\/strong\u003e\u003c\/th\u003e\n\u003cth class=\"green\"\u003e\n\u003cstrong\u003eDev Board\u003cspan\u003e \u003c\/span\u003e\u003csup\u003e3\u003c\/sup\u003e\u003c\/strong\u003e\u003cbr\u003e\u003cspan class=\"notice\"\u003ewith Edge TPU\u003c\/span\u003e\n\u003c\/th\u003e\n\u003c\/tr\u003e\n\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eUnet Mv2\u003cbr\u003e(128x128)\u003c\/td\u003e\n\u003ctd\u003e27.7\u003c\/td\u003e\n\u003ctd\u003e3.3\u003c\/td\u003e\n\u003ctd\u003e190.7\u003c\/td\u003e\n\u003ctd\u003e5.7\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDeepLab V3\u003cbr\u003e(513x513)\u003c\/td\u003e\n\u003ctd\u003e394\u003c\/td\u003e\n\u003ctd\u003e52\u003c\/td\u003e\n\u003ctd\u003e1139\u003c\/td\u003e\n\u003ctd\u003e241\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDenseNet\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e380\u003c\/td\u003e\n\u003ctd\u003e20\u003c\/td\u003e\n\u003ctd\u003e1032\u003c\/td\u003e\n\u003ctd\u003e25\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInception v1\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e90\u003c\/td\u003e\n\u003ctd\u003e3.4\u003c\/td\u003e\n\u003ctd\u003e392\u003c\/td\u003e\n\u003ctd\u003e4.1\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInception v4\u003cbr\u003e(299x299)\u003c\/td\u003e\n\u003ctd\u003e700\u003c\/td\u003e\n\u003ctd\u003e85\u003c\/td\u003e\n\u003ctd\u003e3157\u003c\/td\u003e\n\u003ctd\u003e102\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInception-ResNet V2\u003cbr\u003e(299x299)\u003c\/td\u003e\n\u003ctd\u003e753\u003c\/td\u003e\n\u003ctd\u003e57\u003c\/td\u003e\n\u003ctd\u003e2852\u003c\/td\u003e\n\u003ctd\u003e69\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMobileNet v1\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e53\u003c\/td\u003e\n\u003ctd\u003e2.4\u003c\/td\u003e\n\u003ctd\u003e164\u003c\/td\u003e\n\u003ctd\u003e2.4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMobileNet v2\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e51\u003c\/td\u003e\n\u003ctd\u003e2.6\u003c\/td\u003e\n\u003ctd\u003e122\u003c\/td\u003e\n\u003ctd\u003e2.6\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMobileNet v1 SSD\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e109\u003c\/td\u003e\n\u003ctd\u003e6.5\u003c\/td\u003e\n\u003ctd\u003e353\u003c\/td\u003e\n\u003ctd\u003e11\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMobileNet v2 SSD\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e106\u003c\/td\u003e\n\u003ctd\u003e7.2\u003c\/td\u003e\n\u003ctd\u003e282\u003c\/td\u003e\n\u003ctd\u003e14\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eResNet-50 V1\u003cbr\u003e(299x299)\u003c\/td\u003e\n\u003ctd\u003e484\u003c\/td\u003e\n\u003ctd\u003e49\u003c\/td\u003e\n\u003ctd\u003e1763\u003c\/td\u003e\n\u003ctd\u003e56\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eResNet-50 V2\u003cbr\u003e(299x299)\u003c\/td\u003e\n\u003ctd\u003e557\u003c\/td\u003e\n\u003ctd\u003e50\u003c\/td\u003e\n\u003ctd\u003e1875\u003c\/td\u003e\n\u003ctd\u003e59\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eResNet-152 V2\u003cbr\u003e(299x299)\u003c\/td\u003e\n\u003ctd\u003e1823\u003c\/td\u003e\n\u003ctd\u003e128\u003c\/td\u003e\n\u003ctd\u003e5499\u003c\/td\u003e\n\u003ctd\u003e151\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSqueezeNet\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e55\u003c\/td\u003e\n\u003ctd\u003e2.1\u003c\/td\u003e\n\u003ctd\u003e232\u003c\/td\u003e\n\u003ctd\u003e2\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVGG16\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e867\u003c\/td\u003e\n\u003ctd\u003e296\u003c\/td\u003e\n\u003ctd\u003e4595\u003c\/td\u003e\n\u003ctd\u003e343\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVGG19\u003cbr\u003e(224x224)\u003c\/td\u003e\n\u003ctd\u003e1060\u003c\/td\u003e\n\u003ctd\u003e308\u003c\/td\u003e\n\u003ctd\u003e5538\u003c\/td\u003e\n\u003ctd\u003e357\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eEfficientNet-EdgeTpu-S*\u003c\/td\u003e\n\u003ctd\u003e5431\u003c\/td\u003e\n\u003ctd\u003e5.1\u003c\/td\u003e\n\u003ctd\u003e705\u003c\/td\u003e\n\u003ctd\u003e5.5\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eEfficientNet-EdgeTpu-M*\u003c\/td\u003e\n\u003ctd\u003e8469\u003c\/td\u003e\n\u003ctd\u003e8.7\u003c\/td\u003e\n\u003ctd\u003e1081\u003c\/td\u003e\n\u003ctd\u003e10.6\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eEfficientNet-EdgeTpu-L*\u003c\/td\u003e\n\u003ctd\u003e22258\u003c\/td\u003e\n\u003ctd\u003e25.3\u003c\/td\u003e\n\u003ctd\u003e2717\u003c\/td\u003e\n\u003ctd\u003e30.5\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp class=\" body-copy mk-paragraph small-headline\"\u003e\u003csup\u003e1\u003c\/sup\u003e\u003cspan\u003e \u003c\/span\u003e\u003ci\u003eDesktop CPU: Single 64-bit Intel(R) Xeon(R) Gold 6154 CPU @ 3.00GHz\u003c\/i\u003e\u003cbr\u003e\u003csup\u003e2\u003c\/sup\u003e\u003cspan\u003e \u003c\/span\u003e\u003ci\u003eEmbedded CPU: Quad-core Cortex-A53 @ 1.5GHz\u003c\/i\u003e\u003cbr\u003e\u003csup\u003e3\u003c\/sup\u003e\u003cspan\u003e \u003c\/span\u003e\u003ci\u003eDev Board: Quad-core Cortex-A53 @ 1.5GHz + Edge TPU\u003c\/i\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e","brand":"Google","offers":[{"title":"Default Title","offer_id":50556008399087,"sku":"pnt1787258058447","price":77.76,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0754\/8515\/1471\/files\/coral-usb-accelerator_1.jpg?v=1787258067"}],"url":"https:\/\/primechicstore.shop\/collections\/usb.oembed","provider":"My Store","version":"1.0","type":"link"}