TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Core ML: Integrate machine learning models into your app

171 点作者 yonilevy将近 8 年前

13 条评论

eggie5将近 8 年前
Apple's new iOS CoreML inference engine supports Keras models! Developers will be able to design and train model using Keras and then convert the architecture to run on the CoreML engine. I suppose you can run TensorFlow models too if you designed them w/ Keras.
评论 #14498847 未加载
blt将近 8 年前
Cool that the file format is officially specified as a Protocol Buffer: <a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;coreml&#x2F;converting_trained_models_to_core_ml" rel="nofollow">https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;coreml&#x2F;converting_...</a> (bottom of page)
评论 #14497825 未加载
seanmcdirmid将近 8 年前
When &quot;Core ML&quot; is no longer a mini language to reason about ML the PL semantics...
评论 #14495413 未加载
singularity2001将近 8 年前
&quot;BNNS does not do training, however. Its purpose is to provide very high performance inference on already trained neural networks.&quot; :(<p><a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;accelerate&#x2F;bnns" rel="nofollow">https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;accelerate&#x2F;bnns</a>
评论 #14495348 未加载
评论 #14496201 未加载
kensai将近 8 年前
&quot;Core ML is optimized for on-device performance, which minimizes memory footprint and power consumption.&quot;<p>This is major, if they have managed to achieve it reasonably. But before opening a Sekt, I want to see some benchmarks. :)
jamesswift3将近 8 年前
Federighi says Core ML on iPhone is 6x faster than Google Pixel and Samsung Galaxy S8.<p>How they actually compare?
评论 #14503990 未加载
hackerbot将近 8 年前
using it means need to handle Android with another framework separately
评论 #14495904 未加载
db3d将近 8 年前
Lots of options to explore, but no reinforcement learning yet.<p>Also, some converted Core ML Models ready to use here: developer.apple.com&#x2F;machine-learning
评论 #14497492 未加载
ajay-d将近 8 年前
The python package, coremltools, to convert the trained model is only for python 2.7??
评论 #14498231 未加载
dmix将近 8 年前
Having a directory of trained models to download is an interesting concept. This will certainly accelerate the adoption of ML.
OldeElk将近 8 年前
Does it support caffe&#x2F;TensorFlow&#x2F;MXnet model inferencing?
mtw将近 8 年前
Why not caffe2? And why mention libsvm, are we in the 90s?
评论 #14496615 未加载
评论 #14497214 未加载
killin_dan将近 8 年前
Machine Learning needs a new acronym. ML is already taken! Get your own!
评论 #14496939 未加载