search

jinzishuai / learn2deeplearn

A repository of codes in learning deep learning
GNU General Public License v3.0
13 stars 1 forks source link

Karas segmentation fault loading the yolo model #34

Open jinzishuai opened 6 years ago

jinzishuai commented 6 years ago

Crashed on my Ubuntu-16

seki@seki-VirtualBox:~/src/learn2deeplearn/deeplearning.ai/C4.CNN/week3_ObjectDetection/hw/Car detection for Autonomous Driving$ lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description:    Ubuntu 16.04.3 LTS
Release:    16.04
Codename:   xenial
seki@seki-VirtualBox:~/src/learn2deeplearn/deeplearning.ai/C4.CNN/week3_ObjectDetection/hw/Car detection for Autonomous Driving$ python3
Python 3.5.2 (default, Sep 14 2017, 22:51:06) 
[GCC 5.4.0 20160609] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from keras.models import load_model
Using TensorFlow backend.
2017-11-08 22:11:42.273671: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-11-08 22:11:42.273751: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-11-08 22:11:42.273781: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
>>> yolo_model = load_model("model_data/yolo.h5")
Segmentation fault

Worked on the Coursera Debian-8

jovyan@0b94510ef5b9:~/work/week3/Car detection for Autonomous Driving$ cat /etc/os-release
PRETTY_NAME="Debian GNU/Linux 8 (jessie)"
NAME="Debian GNU/Linux"
VERSION_ID="8"
VERSION="8 (jessie)"
ID=debian
HOME_URL="http://www.debian.org/"
SUPPORT_URL="http://www.debian.org/support"
BUG_REPORT_URL="https://bugs.debian.org/"
jovyan@0b94510ef5b9:~/work/week3/Car detection for Autonomous Driving$ python3
Python 3.6.0 |Anaconda custom (64-bit)| (default, Dec 23 2016, 12:22:00)
[GCC 4.4.7 20120313 (Red Hat 4.4.7-1)] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> from keras.models import load_model
Using TensorFlow backend.
>>> yolo_model = load_model("model_data/yolo.h5")
2017-11-09 05:13:44.395903: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instruction
s, but these are available on your machine and could speed up CPU computations.
2017-11-09 05:13:44.395947: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instruction
s, but these are available on your machine and could speed up CPU computations.
2017-11-09 05:13:44.395964: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions,
but these are available on your machine and could speed up CPU computations.
/opt/conda/lib/python3.6/site-packages/keras/models.py:251: UserWarning: No training configuration found in save file: the model was *not* compi
led. Compile it manually.
  warnings.warn('No training configuration found in save file: '
>>>