J'utilise PYTHON IDE spyder3.2.1 dans anaconda2, avec python2.7, ubuntu14.04Spyder juste "noyau est mort, le redémarrage" quand je lance net.forward dans pytorch
Codeest tout simple comme suit :
import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
"""
input:[batch_size,in_channel,height,width]
kernel:[out_channel,in_channel,kh,kw]
"""
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# 1 input image channel, 6 output channels, 5x5 square convolution
# kernel
self.conv1 = nn.Conv2d(1, 6, 5)
#(28-5+1)/2=12
self.conv2 = nn.Conv2d(6, 16, 5)
#(12-5+1)/2=4
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
# Max pooling over a (2, 2) window
x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
# If the size is a square you can only specify a single number
print "after conv1 size is {}".format(x.size())
x = F.max_pool2d(F.relu(self.conv2(x)), 2)
print "after conv2 size is {}".format(x.size())
x = x.view(-1, self.num_flat_features(x))
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
def num_flat_features(self, x):
size = x.size()[1:] # all dimensions except the batch dimension
num_features = 1
for s in size:
num_features *= s
return num_features
net = Net()
print(net)
print "hello wrold"
input = Variable(torch.Tensor(np.random.randint(1,10,size=(1,1,32,32))))
print net.forward(input)
lorsque j'utilise ordinateur portable ou une console jupyter, il fonctionne normalement, cela signifie que le code n'a pas d'erreur.
Mais quand je l'utilise de Spyder, il se planter aime ça:
As I am not allowed to embed the error image: it says "Kernel died, restarting"
J'essaie juste de réduire mon code pour trouver où le problème est.
Le problème est absolument autour du tout début F.max_pool2d()
, dans la fonction de méthode de transfert.
Mais après avoir beaucoup cherché, je n'ai toujours aucune idée de comment le réparer.
liste Conda:
alabaster 0.7.10 py27_0
anaconda 4.4.0 np112py27_0
anaconda-client 1.6.3 py27_0
anaconda-navigator 1.6.2 py27_0
anaconda-project 0.6.0 py27_0
asn1crypto 0.22.0 py27_0
astroid 1.4.9 py27_0
astroid 1.5.3 <pip>
astropy 1.3.2 np112py27_0
Babel 2.5.0 <pip>
babel 2.4.0 py27_0
backports 1.0 py27_0
backports.functools-lru-cache 1.4 <pip>
backports.weakref 1.0rc1 <pip>
backports_abc 0.5 py27_0
beautifulsoup4 4.6.0 py27_0
bitarray 0.8.1 py27_0
blaze 0.10.1 py27_0
bleach 1.5.0 py27_0
bleach 2.0.0 <pip>
bokeh 0.12.5 py27_1
boto 2.46.1 py27_0
bottleneck 1.2.1 np112py27_0
cairo 1.14.8 0
cdecimal 2.3 py27_2
certifi 2017.7.27.1 <pip>
cffi 1.10.0 py27_0
chardet 3.0.3 py27_0
chardet 3.0.4 <pip>
click 6.7 py27_0
cloudpickle 0.2.2 py27_0
clyent 1.2.2 py27_0
colorama 0.3.9 py27_0
conda 4.3.21 py27_0
conda-env 2.6.0 0
configparser 3.5.0 py27_0
contextlib2 0.5.5 py27_0
cryptography 1.8.1 py27_0
curl 7.52.1 0
cycler 0.10.0 py27_0
cython 0.25.2 py27_0
cytoolz 0.8.2 py27_0
dask 0.14.3 py27_1
datashape 0.5.4 py27_0
dbus 1.10.10 0
decorator 4.0.11 py27_0
distributed 1.16.3 py27_0
docutils 0.14 <pip>
docutils 0.13.1 py27_0
entrypoints 0.2.2 py27_1
entrypoints 0.2.3 <pip>
enum34 1.1.6 py27_0
et_xmlfile 1.0.1 py27_0
expat 2.1.0 0
fastcache 1.0.2 py27_1
flask 0.12.2 py27_0
flask-cors 3.0.2 py27_0
fontconfig 2.12.1 3
freetype 2.5.5 2
funcsigs 1.0.2 py27_0
functools32 3.2.3.2 py27_0
futures 3.1.1 py27_0
get_terminal_size 1.0.0 py27_0
gevent 1.2.1 py27_0
glib 2.50.2 1
greenlet 0.4.12 py27_0
grin 1.2.1 py27_3
gst-plugins-base 1.8.0 0
gstreamer 1.8.0 0
h5py 2.7.0 np112py27_0
harfbuzz 0.9.39 2
hdf5 1.8.17 1
heapdict 1.0.0 py27_1
html5lib 0.999999999 <pip>
html5lib 0.999 py27_0
icu 54.1 0
idna 2.5 py27_0
idna 2.6 <pip>
imagesize 0.7.1 py27_0
ipaddress 1.0.18 py27_0
ipykernel 4.6.1 py27_0
ipython 5.3.0 py27_0
ipython_genutils 0.2.0 py27_0
ipywidgets 6.0.0 py27_0
isort 4.2.5 py27_0
isort 4.2.15 <pip>
itsdangerous 0.24 py27_0
jbig 2.1 0
jdcal 1.3 py27_0
jedi 0.10.2 py27_2
jinja2 2.9.6 py27_0
jpeg 9b 0
jsonschema 2.6.0 py27_0
jupyter 1.0.0 py27_3
jupyter-client 5.1.0 <pip>
jupyter_client 5.0.1 py27_0
jupyter_console 5.1.0 py27_0
jupyter_core 4.3.0 py27_0
lazy-object-proxy 1.2.2 py27_0
lazy-object-proxy 1.3.1 <pip>
libffi 3.2.1 1
libgcc 4.8.5 2
libgfortran 3.0.0 1
libiconv 1.14 0
libpng 1.6.27 0
libsodium 1.0.10 0
libtiff 4.0.6 3
libtool 2.4.2 0
libxcb 1.12 1
libxml2 2.9.4 0
libxslt 1.1.29 0
llvmlite 0.18.0 py27_0
locket 0.2.0 py27_1
lxml 3.7.3 py27_0
Markdown 2.6.8 <pip>
markupsafe 0.23 py27_2
MarkupSafe 1.0 <pip>
matplotlib 2.0.2 np112py27_0
mccabe 0.6.1 <pip>
mistune 0.7.4 py27_0
mkl 2017.0.1 0
mkl-service 1.1.2 py27_3
mock 2.0.0 <pip>
mpmath 0.19 py27_1
msgpack-python 0.4.8 py27_0
multipledispatch 0.4.9 py27_0
navigator-updater 0.1.0 py27_0
nbconvert 5.2.1 <pip>
nbconvert 5.1.1 py27_0
nbformat 4.4.0 <pip>
nbformat 4.3.0 py27_0
networkx 1.11 py27_0
nltk 3.2.3 py27_0
nose 1.3.7 py27_1
notebook 5.0.0 py27_0
numba 0.33.0 np112py27_0
numexpr 2.6.2 np112py27_0
numpy 1.12.1 py27_0
numpy 1.13.1 <pip>
numpydoc 0.6.0 py27_0
numpydoc 0.7.0 <pip>
odo 0.5.0 py27_1
olefile 0.44 py27_0
opencv 1.0.1 <pip>
opencv-python 3.3.0.9 <pip>
openpyxl 2.4.7 py27_0
openssl 1.0.2l 0
packaging 16.8 py27_0
pandas 0.20.1 np112py27_0
pandocfilters 1.4.1 py27_0
pandocfilters 1.4.2 <pip>
pango 1.40.3 1
partd 0.3.8 py27_0
path.py 10.3.1 py27_0
pathlib2 2.3.0 <pip>
pathlib2 2.2.1 py27_0
patsy 0.4.1 py27_0
pbr 3.1.1 <pip>
pcre 8.39 1
pep8 1.7.0 py27_0
pexpect 4.2.1 py27_0
pickleshare 0.7.4 py27_0
pillow 4.1.1 py27_0
pip 9.0.1 py27_1
pixman 0.34.0 0
ply 3.10 py27_0
prompt_toolkit 1.0.14 py27_0
protobuf 3.3.0 <pip>
psutil 5.2.2 py27_0
ptyprocess 0.5.1 py27_0
py 1.4.33 py27_0
pycairo 1.10.0 py27_0
pycodestyle 2.3.1 <pip>
pycosat 0.6.2 py27_0
pycparser 2.17 py27_0
pycrypto 2.6.1 py27_6
pycurl 7.43.0 py27_2
pyflakes 1.5.0 py27_0
pyflakes 1.6.0 <pip>
pygments 2.2.0 py27_0
pylint 1.6.4 py27_1
pylint 1.7.2 <pip>
pylzma 0.4.9.post0 <pip>
pyodbc 4.0.16 py27_0
PyOpenGL 3.1.0 <pip>
pyopenssl 17.0.0 py27_0
pyparsing 2.1.4 py27_0
pyqt 5.6.0 py27_2
pytables 3.3.0 np112py27_0
pytest 3.0.7 py27_0
python 2.7.13 0
python-dateutil 2.6.1 <pip>
python-dateutil 2.6.0 py27_0
pytz 2017.2 py27_0
pywavelets 0.5.2 np112py27_0
pyyaml 3.12 py27_0
pyzmq 16.0.2 py27_0
qt 5.6.2 4
qtawesome 0.4.4 py27_0
qtconsole 4.3.0 py27_0
qtconsole 4.3.1 <pip>
qtpy 1.2.1 py27_0
QtPy 1.3.1 <pip>
readline 6.2 2
requests 2.18.4 <pip>
requests 2.14.2 py27_0
rope 0.10.7 <pip>
rope 0.9.4 py27_1
ruamel_yaml 0.11.14 py27_1
scandir 1.5 py27_0
scikit-image 0.13.0 np112py27_0
scikit-learn 0.18.1 np112py27_1
scipy 0.19.0 np112py27_0
seaborn 0.7.1 py27_0
setuptools 27.2.0 py27_0
setuptools 36.2.7 <pip>
simplegeneric 0.8.1 py27_1
singledispatch 3.4.0.3 py27_0
sip 4.18 py27_0
six 1.10.0 py27_0
snowballstemmer 1.2.1 py27_0
sortedcollections 0.5.3 py27_0
sortedcontainers 1.5.7 py27_0
Sphinx 1.6.3 <pip>
sphinx 1.5.6 py27_0
sphinxcontrib-websupport 1.0.1 <pip>
spyder 3.2.1 <pip>
spyder 3.1.4 py27_0
sqlalchemy 1.1.9 py27_0
sqlite 3.13.0 0
ssl_match_hostname 3.4.0.2 py27_1
statsmodels 0.8.0 np112py27_0
subprocess32 3.2.7 py27_0
sympy 1.0 py27_0
tblib 1.3.2 py27_0
tensorflow 1.2.1 <pip>
tensorlayer 1.6.0 <pip>
terminado 0.6 py27_0
testpath 0.3.1 <pip>
testpath 0.3 py27_0
tk 8.5.18 0
toolz 0.8.2 py27_0
torch-0.2.0 1 <pip>
torchvision 0.1.9 <pip>
tornado 4.5.1 py27_0
tqdm 4.15.0 <pip>
traitlets 4.3.2 py27_0
typing 3.6.2 <pip>
unicodecsv 0.14.1 py27_0
unixodbc 2.3.4 0
urllib3 1.22 <pip>
wcwidth 0.1.7 py27_0
webencodings 0.5.1 <pip>
werkzeug 0.12.2 py27_0
wheel 0.29.0 py27_0
widgetsnbextension 2.0.0 py27_0
wrapt 1.10.11 <pip>
wrapt 1.10.10 py27_0
xlrd 1.0.0 py27_0
xlsxwriter 0.9.6 py27_0
xlwt 1.2.0 py27_0
xz 5.2.2 1
yaml 0.1.6 0
zeromq 4.1.5 0
zict 0.1.2 py27_0
zlib 1.2.8 3
Comment avez-vous installé PyTorch? De la chaîne d'Anaconda de soumith? Avez-vous essayé d'utiliser Python 3.6 à la place? –
Je réinstalle pytorch par ** l'installation de source **, et tout va bien –