I am trying to load a keras model to do classification task using my raspberry. But after running this code:

import keras
from keras.models import load_model

model = load_model("mobilenet_v2_3(trained).h5")

before i will be able to do some prediction, i got this error;

Using TensorFlow backend.
Instructions for updating:
Colocations handled automatically by placer.
Backend terminated(returncode: -11)
Fatal python error: Segmentation fault 
  • Bad luck. So you have a segFault. Most likely your big data is too big. Ref: Identify what's causing segmentation faults kb.iu.edu/d/aqsj – tlfong01 May 23 at 1:26
  • Do you suggest a kind of solution Please @tlfong01 – Go Deeper May 23 at 7:17
  • Well, I am a small guy, don't know nothing about big data, not even scratching surface knowledge. But now everybody is talking about AI, Neural Net and TensorFlow, etc. I am losing face because I can't even tell what is the difference between Neural Net and TensorFlow. So I am keen to dig deeper below the surface, memorize more weird names, so that my friends would respect more than I deserve. My plan is first wiki, and pretend to give an answer. Perhaps you can also pretend to give an answer, then I upvote you, and upvote me, building our reputation together, ... :) – tlfong01 May 23 at 8:00


Keras has a segFault, how to fix?

Short Answer

I don't know yet. Perhaps I can start googling and wikiing and hopefully will know later.

/ to continue, ...

Long Answer

/ to continue, ...

Reading Notes

Keras - Wikipedia


Using python (therefore newbie friendly, I hate C++ and Java!), run on top of tensorFlow (sort of standing on the shoulder of a giant, so I can instantly pretend to be sort of a giant), fast experimentation (How nice, I am impatient and too busy to learn difficult things), Google TensorFlow core library compatible (of course free, therefore poor guy friendly), can do distributed training (so I can hack into other rich guys' GPUs and TPUs, and steal their xPU time to train my cat face recognition AlphaGo), ...

Keras Home Page Introduction and Guiding Principles


A high-lvel neural networks API, written in python, running on top of TensorFlow for fast prototyping, experimentation. Suports convolutiona and recurrent networks, runs seamlessly on CPU and GPU. Compatible with Python 2.7 ~ 3.6

Guiding principles

User friendly API and error messages;

Modular (neural layers, ... are all standalone modules and can comine to create new models;

Easily extensible and suitable for advanced research;

Work with Python, not separate config file, described in python code, compact, easy to debug and extend

/ to continue, ...

Brain Storming Suggestions

/ to continue, ...

Research Notes

/ to continue, ...


Keras - Wikipedia

Keras is an open-source neural-network library written in Python. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, Theano, or PlaidML.2] Designed to enable fast experimentation with deep neural networks, it focuses on being user-friendly, modular, and extensible. It was developed as part of the research effort of project ONEIROS (Open-ended Neuro-Electronic Intelligent Robot Operating System), and its primary author and maintainer is François Chollet, a Google engineer. Chollet also is the author of the XCeption deep neural network model[4].

In 2017, Google's TensorFlow team decided to support Keras in TensorFlow's core library. Chollet explained that Keras was conceived to be an interface rather than a standalone machine-learning framework. It offers a higher-level, more intuitive set of abstractions that make it easy to develop deep learning models regardless of the computational backend used. Microsoft added a CNTK backend to Keras as well, available as of CNTK v2.0.


Keras contains numerous implementations of commonly used neural-network building blocks such as layers, objectives, activation functions, optimizers, and a host of tools to make working with image and text data easier. The code is hosted on GitHub, and community support forums include the GitHub issues page, and a Slack channel.

In addition to standard neural networks, Keras has support for convolutional and recurrent neural networks. It supports other common utility layers like dropout, batch normalization, and pooling.

Keras allows users to productize deep models on smartphones (iOS and Android), on the web, or on the Java Virtual Machine. It also allows use of distributed training of deep-learning models on clusters of Graphics Processing Units (GPU) and Tensor processing units (TPU).


Keras claims over 200,000 users as of November 2017.[10] Keras was the 10th most cited tool in the KD Nuggets 2018 software poll and registered a 22% usage.

Keras: The Python Deep Learning library

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.

Use Keras if you need a deep learning library that:

Allows for easy and fast prototyping (through user friendliness, modularity, and extensibility).

Supports both convolutional networks and recurrent networks, as well as combinations of the two.

Runs seamlessly on CPU and GPU.

Read the documentation at Keras.io.

Keras is compatible with: Python 2.7-3.6.

Guiding principles

User friendliness. Keras is an API designed for human beings, not machines. It puts user experience front and center. Keras follows best practices for reducing cognitive load: it offers consistent & simple APIs, it minimizes the number of user actions required for common use cases, and it provides clear and actionable feedback upon user error.

Modularity. A model is understood as a sequence or a graph of standalone, fully configurable modules that can be plugged together with as few restrictions as possible. In particular, neural layers, cost functions, optimizers, initialization schemes, activation functions and regularization schemes are all standalone modules that you can combine to create new models.

Easy extensibility. New modules are simple to add (as new classes and functions), and existing modules provide ample examples. To be able to easily create new modules allows for total expressiveness, making Keras suitable for advanced research.

Work with Python. No separate models configuration files in a declarative format. Models are described in Python code, which is compact, easier to debug, and allows for ease of extensibility.

Top 25 AI Chip Companies - Montaqim 2019may24


  1. Alphabet

Google’s parent company is overseeing the development of artificial intelligence technologies in a variety of sectors, including cloud computing, data centers, mobile devices, and desktop computers.

Probably most noteworthy is its Tensor Processing Unit, an ASIC specifically designed for Google’s TensorFlow programming framework, used mainly for machine learning and deep learning, two branches of AI.

Google’s Cloud TPU is a data center or cloud solution and is about the size of a credit card, but the Edge TPU is smaller than a one-cent coin and is designed for “edge” devices, referring to devices at the edge of a network, such as smartphones and tablets and machines used by the rest of us, outside of data centers.

Having said that, analysts who observe this market more closely say Google’s Edge TPU is unlikely to feature in the company’s own smartphones and tablets anytime soon, and is more likely to be used in more high-end, enterprise and expensive machines and devices.

  1. Baidu

Baidu is China’s equivalent of Google in the sense that it’s mainly known as an internet search engine. And like Google, Baidu has moved into new and interesting business sectors such as driverless cars, which, of course, need powerful microprocessors, preferably AI chips.

And to that end, Baidu last year unveiled the Kun Lun, describing it as a “cloud-to-edge AI chip”.

The company sees Kunlun’s application mainly in its existing AI ecosystem, which includes search ranking and its deep learning frameworks. But the chip has other potential applications in the new sectors Baidu is going into, including autonomous vehicles, intelligence devices for the home, voice recognition, natural language processing, and image processing.

/ to continue, ...


/ to continue, ...

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.