TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Google Coral Edge TPU

136 pointsby kilovoltaireabout 6 years ago

11 comments

mark_l_watsonabout 6 years ago
It is a small turnoff that you need to use their cloud model ‘compiler’ but I still think I might get the USB Dev device.<p>I am retiring in a couple off weeks from my job managing a machine learning team and I intend on being a ‘gentleman scientist’ studying things of interest, without worrying about immediate practicality. Of most interest is local ML using tensorflow.js and devices like the Edge TPU, and also hybrid symbolic AI and deep neural net systems.<p>Anyway, good to see competition for edge devices.
评论 #19316137 未加载
wyldfireabout 6 years ago
&gt; Upload your model<p>&gt; It should take about one minute for compilation to complete.<p>...also, it should take about six months for Google to lose interest in this product, at which point the product you made when you integrated the Edge TPU -- is stuck without updates.
评论 #19315890 未加载
评论 #19314978 未加载
ipsum2about 6 years ago
Previous discussion: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=19130896" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=19130896</a><p>They mentioned previously that you had to compile your models on the cloud, and not locally on your computer. Not sure if they&#x27;ve changed this policy.
评论 #19315311 未加载
评论 #19314320 未加载
jononorabout 6 years ago
The baseboard and SOM module split looks very well done. The module includes CPU+RAM+EMMC in addition to the TPU, so a custom baseboard can be quite simple. A lot of audio input, ready for microphone arrays. Curious to see what role the M4F microcontroller will play, hopefully that is for some sleep&#x2F;low-power usage where it can wake up the beefy CPU (and TPU).
solomatovabout 6 years ago
I wish Google created a development version of TPU for inference so that it&#x27;s possible to debug models locally and then send them for training to the GCP.
评论 #19314124 未加载
评论 #19314132 未加载
评论 #19314707 未加载
评论 #19314129 未加载
评论 #19314310 未加载
评论 #19314067 未加载
syntaxingabout 6 years ago
The Edge TPU devices that Google has been promising since last year is now available under a new company called Coral. Would love to get one to compare to my Jetson TX2. The downside is that the unit can only use Tensorflow Lite.<p>E: Hah, seems like my topic got merged with this one. Interesting how I was short from OPs post by like a minute a two. Such a coincidence!
评论 #19314139 未加载
shereadsthenewsabout 6 years ago
Kinda surprised they went with the internal code name for this.
Eccoabout 6 years ago
The datasheet says it features a &quot;Cortex M4 with 16 KB of instruction cache and 16 KB of data cache&quot;. As far as I know, M4 don&#x27;t have L1 cache. Maybe they&#x27;re using an M7? Or there&#x27;s just simply no cache?<p><a href="https:&#x2F;&#x2F;coral.withgoogle.com&#x2F;tutorials&#x2F;devboard-datasheet&#x2F;" rel="nofollow">https:&#x2F;&#x2F;coral.withgoogle.com&#x2F;tutorials&#x2F;devboard-datasheet&#x2F;</a>
评论 #19314473 未加载
评论 #19314500 未加载
评论 #19314484 未加载
yRetsyMabout 6 years ago
Interesting that it&#x27;s Debian Linux support only for the peripherals. I&#x27;d be interested to see if that support grows to other os&#x27;s, especially if it&#x27;s a restriction to adoption.<p>I&#x27;m not in the space per-say but what are the predominant OS choices for ML&#x2F;AI Devs?
评论 #19314480 未加载
dheeraabout 6 years ago
They were handing the USB ones out today to attendees at the TensorFlow Dev Summit. I&#x27;ll test mine later.<p>However I <i>really</i> wish they would make something beefier, to compete with e.g. Nvidia&#x27;s Xavier.
bcatanzaroabout 6 years ago
Any details on how much this board costs? Also, how many TOPs the Edge TPU has?
评论 #19315091 未加载
评论 #19321299 未加载