The kernel appears to have died. It will restart automatically

1

I facing a common problem when loading pre-training model using PyTorch. Jupyter notebook is crashing “The kernel appears to have died. It will restart automatically”

I have followed the discussion link, link, and link but not fix, any suggestions?

The environment specifications as follows:

OS : CentOS Linux release 7.8.2003 (Core)
Python : Python 3.6.12 :: Anaconda, Inc.
Conda version : conda 4.5.4

Available resources:
ibm-game-center Thu Nov 12 14:19:05 2020 410.48
[0] GeForce RTX 2080 Ti | 46’C, 0 % | 10 / 10989 MB |
[1] GeForce RTX 2080 Ti | 49’C, 0 % | 10 / 10989 MB |

Conda list :

packages in environment at /home/aiman/anaconda3:

Name Version Build Channel

_ipyw_jlab_nb_ext_conf 0.1.0 py36he11e457_0
_libgcc_mutex 0.1 main
alabaster 0.7.10 py36h306e16b_0
anaconda 5.2.0 py36_3
anaconda-client 1.6.14 py36_0
anaconda-navigator 1.8.7 py36_0
anaconda-project 0.8.2 py36h44fb852_0
asn1crypto 0.24.0 py36_0
astroid 1.6.3 py36_0
astropy 3.0.2 py36h3010b51_1
attrs 18.1.0 py36_0
babel 2.5.3 py36_0
backcall 0.1.0 py36_0
backports 1.0 py36hfa02d7e_1
backports.shutil_get_terminal_size 1.0.0 py36hfea85ff_2
beautifulsoup4 4.6.0 py36h49b8c8c_1
bitarray 0.8.1 py36h14c3975_1
bkcharts 0.2 py36h735825a_0
blas 1.0 openblas
blaze 0.11.3 py36h4e06776_0
bleach 2.1.3 py36_0
blosc 1.14.3 hdbcaa40_0
bokeh 0.12.16 py36_0
boto 2.48.0 py36h6e4cd66_1
bottleneck 1.2.1 py36haac1ea0_0
bzip2 1.0.6 h14c3975_5
ca-certificates 2020.10.14 0
cairo 1.14.12 h7636065_2
certifi 2020.6.20 pyhd3eb1b0_3
cffi 1.11.5 py36h9745a5d_0
chardet 3.0.4 py36h0f667ec_1
click 6.7 py36h5253387_0
cloudpickle 0.5.3 py36_0
clyent 1.2.2 py36h7e57e65_1
colorama 0.3.9 py36h489cec4_0
conda 4.5.4 py36_0
conda-build 3.10.5 py36_0
conda-env 2.6.0 1
conda-verify 2.0.0 py36h98955d8_0
contextlib2 0.5.5 py36h6c84a62_0
cpuonly 1.0 0 pytorch
cryptography 2.2.2 py36h14c3975_0
curl 7.60.0 h84994c4_0
cycler 0.10.0 py36h93f1223_0
cython 0.28.2 py36h14c3975_0
cytoolz 0.9.0.1 py36h14c3975_0
dask 0.17.5 py36_0
dask-core 0.17.5 py36_0
datashape 0.5.4 py36h3ad6b5c_0
dbus 1.13.2 h714fa37_1
decorator 4.3.0 py36_0
distributed 1.21.8 py36_0
docutils 0.14 py36hb0f60f5_0
entrypoints 0.2.3 py36h1aec115_2
et_xmlfile 1.0.1 py36hd6bccc3_0
expat 2.2.5 he0dffb1_0
fastcache 1.0.2 py36h14c3975_2
filelock 3.0.4 py36_0
flask 1.0.2 py36_1
flask-cors 3.0.4 py36_0
fontconfig 2.12.6 h49f89f6_0
freetype 2.10.4 h5ab3b9f_0
gensim 3.8.3
get_terminal_size 1.0.0 haa9412d_0
gevent 1.3.0 py36h14c3975_0
glib 2.56.1 h000015b_0
glob2 0.6 py36he249c77_0
gmp 6.1.2 h6c8ec71_1
gmpy2 2.0.8 py36hc8893dd_2
graphite2 1.3.11 h16798f4_2
greenlet 0.4.13 py36h14c3975_0
gst-plugins-base 1.14.0 hbbd80ab_1
gstreamer 1.14.0 hb453b48_1
h5py 2.7.1 py36ha1f6525_2
harfbuzz 1.7.6 h5f0a787_1
hdf5 1.10.2 hba1933b_1
heapdict 1.0.0 py36_2
html5lib 1.0.1 py36h2f9c1c0_0
icu 58.2 h9c2bf20_1
idna 2.6 py36h82fb2a8_1
imageio 2.3.0 py36_0
imagesize 1.0.0 py36_0
intel-openmp 2020.2 254
ipykernel 4.8.2 py36_0
ipython 6.4.0 py36_0
ipython_genutils 0.2.0 py36hb52b0d5_0
ipywidgets 7.2.1 py36_0
isort 4.3.4 py36_0
itsdangerous 0.24 py36h93cc618_1
jbig 2.1 hdba287a_0
jdcal 1.4 py36_0
jedi 0.12.0 py36_1
jinja2 2.10 py36ha16c418_0
jpeg 9b h024ee3a_2
jsonschema 2.6.0 py36h006f8b5_0
jupyter 1.0.0 py36_4
jupyter_client 5.2.3 py36_0
jupyter_console 5.2.0 py36he59e554_1
jupyter_core 4.4.0 py36h7c827e3_0
jupyterlab 0.32.1 py36_0
jupyterlab_launcher 0.10.5 py36_0
kiwisolver 1.0.1 py36h764f252_0
lazy-object-proxy 1.3.1 py36h10fcdad_0
lcms2 2.11 h396b838_0
ld_impl_linux-64 2.33.1 h53a641e_7
libcurl 7.60.0 h1ad7b7a_0
libedit 3.1.20191231 h14c3975_1
libffi 3.3 he6710b0_2
libgcc-ng 9.1.0 hdf63c60_0
libgfortran 3.0.0 1
libgfortran-ng 8.2.0 hdf63c60_1
libpng 1.6.37 hbc83047_0
libsodium 1.0.16 h1bed415_0
libssh2 1.8.0 h9cfc8f7_4
libstdcxx-ng 9.1.0 hdf63c60_0
libtiff 4.1.0 h2733197_1
libtool 2.4.6 h544aabb_3
libxcb 1.13 h1bed415_1
libxml2 2.9.8 h26e45fe_1
libxslt 1.1.32 h1312cb7_0
llvmlite 0.23.1 py36hdbcaa40_0
locket 0.2.0 py36h787c0ad_1
lxml 4.2.1 py36h23eabaa_0
lz4-c 1.9.2 heb0550a_3
lzo 2.10 h49e0be7_2
markupsafe 1.0 py36hd9260cd_1
matplotlib 2.2.2 py36h0e671d2_1
mccabe 0.6.1 py36h5ad9710_1
mistune 0.8.3 py36h14c3975_1
mkl 2020.2 256
mkl-service 1.1.2 py36h17a0993_4
mkl_fft 1.0.1 py36h3010b51_0
mkl_random 1.0.1 py36h629b387_0
more-itertools 4.1.0 py36_0
mpc 1.0.3 hec55b23_5
mpfr 3.1.5 h11a74b3_2
mpmath 1.0.0 py36hfeacd6b_2
msgpack-python 0.5.6 py36h6bb024c_0
multipledispatch 0.5.0 py36_0
navigator-updater 0.2.1 py36_0
nbconvert 5.3.1 py36hb41ffb7_0
nbformat 4.4.0 py36h31c9010_0
ncurses 6.2 he6710b0_1
networkx 2.1 py36_0
ninja 1.10.1 py36hfd86e86_0
nltk 3.3.0 py36_0
nomkl 3.0 0
nose 1.3.7 py36hcdf7029_2
notebook 5.5.0 py36_0
numba 0.38.0 py36h637b7d7_0
numexpr 2.6.5 py36h7bf3b9c_0
numpy 1.13.1 py36_nomkl_0
numpy-base 1.14.3 py36h9be14a7_1
numpydoc 0.8.0 py36_0
odo 0.5.1 py36h90ed295_0
olefile 0.46 py_0
openblas 0.2.19 0
openpyxl 2.5.3 py36_0
openssl 1.1.1h h7b6447c_0
packaging 17.1 py36_0
pandas 0.23.0 py36h637b7d7_0
pandoc 1.19.2.1 hea2e7c5_1
pandocfilters 1.4.2 py36ha6701b7_1
pango 1.41.0 hd475d92_0
parso 0.2.0 py36_0
partd 0.3.8 py36h36fd896_0
patchelf 0.9 hf79760b_2
path.py 11.0.1 py36_0
pathlib2 2.3.2 py36_0
patsy 0.5.0 py36_0
pcre 8.42 h439df22_0
pep8 1.7.1 py36_0
pexpect 4.5.0 py36_0
pickleshare 0.7.4 py36h63277f8_0
pillow 8.0.1 py36he98fc37_0
pip 20.2.4 py36h06a4308_0
pixman 0.34.0 hceecf20_3
pkginfo 1.4.2 py36_1
pluggy 0.6.0 py36hb689045_0
ply 3.11 py36_0
prompt_toolkit 1.0.15 py36h17d85b1_0
psutil 5.4.5 py36h14c3975_0
ptyprocess 0.5.2 py36h69acd42_0
py 1.5.3 py36_0
PyArabic 0.6.10
pycodestyle 2.4.0 py36_0
pycosat 0.6.3 py36h0a5515d_0
pycparser 2.18 py36hf9f622e_1
pycrypto 2.6.1 py36h14c3975_8
pycurl 7.43.0.1 py36hb7f436b_0
pyflakes 1.6.0 py36h7bd6a15_0
pygments 2.2.0 py36h0d3125c_0
pylint 1.8.4 py36_0
pyodbc 4.0.23 py36hf484d3e_0
pyopenssl 18.0.0 py36_0
pyparsing 2.2.0 py36hee85983_1
pyqt 5.9.2 py36h751905a_0
pysocks 1.6.8 py36_0
pytables 3.4.3 py36h02b9ad4_2
pytest 3.5.1 py36_0
pytest-arraydiff 0.2 py36_0
pytest-astropy 0.3.0 py36_0
pytest-doctestplus 0.1.3 py36_0
pytest-openfiles 0.3.0 py36_0
pytest-remotedata 0.2.1 py36_0
python 3.6.12 hcff3b4d_2
python-dateutil 2.7.3 py36_0
pytorch 1.4.0 py3.6_cpu_0 [cpuonly] pytorch
pytz 2018.4 py36_0
pywavelets 0.5.2 py36he602eb0_0
pyyaml 3.12 py36hafb9ca4_1
pyzmq 17.0.0 py36h14c3975_0
qt 5.9.5 h7e424d6_0
qtawesome 0.4.4 py36h609ed8c_0
qtconsole 4.3.1 py36h8f73b5b_0
qtpy 1.4.1 py36_0
readline 8.0 h7b6447c_0
requests 2.18.4 py36he2e5f8d_1
rope 0.10.7 py36h147e2ec_0
ruamel_yaml 0.15.35 py36h14c3975_1
scikit-image 0.13.1 py36h14c3975_1
scikit-learn 0.19.1 py36h7aa7ec6_0
scipy 1.1.0 py36hfc37229_0
seaborn 0.8.1 py36hfad7ec4_0
send2trash 1.5.0 py36_0
setuptools 50.3.1 py36h06a4308_1
simplegeneric 0.8.1 py36_2
singledispatch 3.4.0.3 py36h7a266c3_0
sip 4.19.8 py36hf484d3e_0
six 1.15.0 py_0
smart-open 3.0.0
snappy 1.1.7 hbae5bb6_3
snowballstemmer 1.2.1 py36h6febd40_0
sortedcollections 0.6.1 py36_0
sortedcontainers 1.5.10 py36_0
sphinx 1.7.4 py36_0
sphinxcontrib 1.0 py36h6d0f590_1
sphinxcontrib-websupport 1.0.1 py36hb5cb234_1
spyder 3.2.8 py36_0
sqlalchemy 1.2.7 py36h6b74fdf_0
sqlite 3.33.0 h62c20be_0
statsmodels 0.9.0 py36h3010b51_0
sympy 1.1.1 py36hc6d1c1c_0
tblib 1.3.2 py36h34cf8b6_0
terminado 0.8.1 py36_1
testpath 0.3.1 py36h8cadb63_0
tk 8.6.10 hbc83047_0
toolz 0.9.0 py36_0
torchaudio 0.4.0 py36 pytorch
torchvision 0.5.0 py36_cpu [cpuonly] pytorch
tornado 5.0.2 py36_0
traitlets 4.3.2 py36h674d592_0
typing 3.7.4.3 py36_0
unicodecsv 0.14.1 py36ha668878_0
unixodbc 2.3.6 h1bed415_0
urllib3 1.22 py36hbe7ace6_0
wcwidth 0.1.7 py36hdf4376a_0
webencodings 0.5.1 py36h800622e_1
werkzeug 0.14.1 py36_0
wheel 0.35.1 py_0
widgetsnbextension 3.2.1 py36_0
wrapt 1.10.11 py36h28b7045_0
xlrd 1.1.0 py36h1db9f0c_1
xlsxwriter 1.0.4 py36_0
xlwt 1.3.0 py36h7b00a1f_0
xz 5.2.5 h7b6447c_0
yaml 0.1.7 had09818_2
zeromq 4.2.5 h439df22_0
zict 0.1.3 py36h3a3bf81_0
zlib 1.2.11 h7b6447c_3
zstd 1.4.5 h9ceee32_0
​

2

Any suggestions to fix this issue? :slight_smile:

3

Jupyter might hide the actual error message and just restart the kernel.
Could you run the script in a terminal via python scripy.py and check the error message?

1 Like
4

Yes sir you’re correct. I get the below error when I import torch

import torch
 File "/home/aiman/anaconda3/lib/python3.6/site-packages/torch/__init__.py", line 81, in <module>

from torch._C import *
ImportError: /lib64/libc.so.6: version `GLIBC_2.18' not found (required by /lib64/libstdc++.so.6)
5

Did you build PyTorch from source are have you used a conda/pip binary?
Also, did you change something in your system, which might have broken PyTorch, in case it was working before?

1 Like
6

Thank you sir for the valuable reply.

I have built Pytorch using pip:
pip install torch==1.3.1+cu100 torchvision==0.4.2+cu100 -f https://download.pytorch.org/whl/torch_stable.html

It’s setup for a new system. I’m confused if its Pytorch or a system issue.

7

I’m unsure what is causing this issue. Could you create a new virtual environment through pip or conda and reinstall PyTorch again?

1 Like
8

Thank you sir, it works now. I have reinstalled Pytorch with conda. :slight_smile:

1 Like
9

I had this same issue on a pytorch install on an older notebook with only 2 gigs of ram when I was running torch 1.4.0. I removed 1.4.0 and replaced it with 1.1.0. This config behaved perfectly. I might also add that I am having the same problem on the notebook, when trying to import Tensorflow2

1 Like
10

Thank you sir, it’s work well now.

11

Hi,
I am having a similar problem. While trying to calculate the perplexity from this code, the kernel is constantly dead when it reaches the last part of the code, i.e. perplexity computations. I also tried to run it directly in python and there is no error message except ‘Killed’. Do you have any suggestions how to solve it? Thank you.

12

You are most likely running out of memory on the host and your OS kills the process, so you might need to use a machine with more RAM.

13

I had the same issue but it turn out to be a common error in my codes. I troubleshooted my codes on CoLaB and noticed a dimension mismatch. Everything run smoothly in my local notebook after fixing the issue.