[
https://issues.apache.org/jira/browse/SINGA-369?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16477050#comment-16477050
]
SHEYUJIAN commented on SINGA-369:
---------------------------------
*4.caffe*
After using $ bash run.sh vgg16 to train and enter the input image path, it
gets an error, it is the same as vgg example.
File "predict.py", line 112, in <module>
predict(model, dev, synset_list=syn_li, topk=5)
File "predict.py", line 84, in predict
y = net.predict(x)
File "/root/miniconda3/lib/python3.6/site-packages/singa/net.py", line 249,
in predict
return tensor.softmax(xx)
File "/root/miniconda3/lib/python3.6/site-packages/singa/tensor.py", line
783, in softmax
return _call_singa_func(singa.SoftMax, t.singa_tensor)
AttributeError: 'Tensor' object has no attribute 'singa_tensor'
> the errors of examples in testing
> ---------------------------------
>
> Key: SINGA-369
> URL: https://issues.apache.org/jira/browse/SINGA-369
> Project: Singa
> Issue Type: Bug
> Environment: SINGA Version: osx-64/singa-1.1.1-py27_cpu
> OS: Mac OS 10.13.4
> SINGA Version: singa-1.1.1_GPU
> OS: Ubuntu 16.04.4 LTS
> Reporter: SHEYUJIAN
> Priority: Major
>
> 1.Cifar10
> After getting data from Cifar-10 dataset
> I use python train.py vgg cifar-10-batches-py --use_cpu to train in cpu
> and get errors:
> After revising according to SINGA-368, we can solve the probelm, but it has
> another error:
> Start intialization............
> Using CPU
> Epoch 0
> -->conv1_1_1: 0.252035
> WARNING: Logging before InitGoogleLogging() is written to STDERR
> F0516 13:19:27.929081 2490057600 batchnorm.cc:100] Trainning
> SpatialBatchNormalization has not been implemented yet...
> *** Check failure stack trace: ***
> Abort trap: 6
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
