-
Notifications
You must be signed in to change notification settings - Fork 11
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Could not open file ./prediction/deploy.prototxt #6
Comments
Try to change the folder where you execute the prediction code.
cd ~/Ask_Attend_and_Answer-master/example/
python predict_json.py
On Sep 29, 2017, at 08:09, Victoria2333 <notifications@github.com<mailto:notifications@github.com>> wrote:
I changed my caffe path to /home/han/src/caffe in./bashrc,
but when i run prediction_json.py,there is still error:
han@han:~/Ask_Attend_and_Answer-master/example/prediction$ python predict_json.py
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0929 20:04:09.720854 20851 _caffe.cpp:139] DEPRECATION WARNING - deprecated use of Python interface
W0929 20:04:09.720896 20851 _caffe.cpp:140] Use this instead (with the named "weights" parameter):
W0929 20:04:09.720903 20851 _caffe.cpp:142] Net('./prediction/deploy.prototxt', 1, weights='./prediction/mm_iter_243000.caffemodel')
Traceback (most recent call last):
File "predict_json.py", line 28, in
lstmnet = caffe.Net<http://caffe.net>(DEPLOY, MODEL, caffe.TEST)
RuntimeError: Could not open file ./prediction/deploy.prototxt
Could you please give me some advice on it?
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub<#6>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_0Nd2ii86mLImkVSuhnSFPK8S-tJks5snN3_gaJpZM4PolX2>.
|
thanks,i just tried just the minute when i got your reply,and it occurred: |
Did you use my provided caffe? It has some new layers integrated, e,g. word_sum_param.
On Sep 29, 2017, at 09:18, Victoria2333 <notifications@github.com<mailto:notifications@github.com>> wrote:
thanks,i just tried just the minute when i got your reply,and it occurred:
han@han:~/Ask_Attend_and_Answer-master/example$ python ./prediction/predict_json.py
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0929 21:15:31.683986 21642 _caffe.cpp:139] DEPRECATION WARNING - deprecated use of Python interface
W0929 21:15:31.684031 21642 _caffe.cpp:140] Use this instead (with the named "weights" parameter):
W0929 21:15:31.684039 21642 _caffe.cpp:142] Net('./prediction/deploy.prototxt', 1, weights='./prediction/mm_iter_243000.caffemodel')
[libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 2180:18: Message type "caffe.LayerParameter" has no field named "word_sum_param".
F0929 21:15:31.723026 21642 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: ./prediction/deploy.prototxt
*** Check failure stack trace: ***
Aborted (core dumped)
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#6 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_1zZQNQE-qtVwOaQYTLd36ZKnkd6ks5snO4ygaJpZM4PolX2>.
|
@ huijuan88 ,sorry to bother, I read your paper <<Ask,Attend and Answer>>, I see there are Absolute position experiment in Fig.3 , Relative position experiment in Fig.4 ,Visualization of the spatial attention weights in the SMem-VQA model in Fig.5 and Fig.6 either. |
Upload the json file to the VQA challenge server, get the evaluation result.
Huijuan
On Sep 30, 2017, at 08:29, Victoria2333 <notifications@github.com<mailto:notifications@github.com>> wrote:
@ huijuan88 ,sorry to bother, I read your paper <<Ask,Attend and Answer>>, I see there are Absolute position experiment in Fig.3 , Relative position experiment in Fig.4 ,Visualization of the spatial attention weights in the SMem-VQA model in Fig.5 and Fig.6 either.
And i couldn't find them in your project,and your test accuracy...
Waiting for your reply~Thank you~~
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub<#6 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AFOa_w7KKmo-abYz3bFTZCTJ2kZG-hAbks5snjQ9gaJpZM4PolX2>.
|
@huijuan88 ,and what about your other experiments?? |
I changed my caffe path to /home/han/src/caffe in./bashrc,
but when i run prediction_json.py,there is still error:
han@han:~/Ask_Attend_and_Answer-master/example/prediction$ python predict_json.py
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0929 20:04:09.720854 20851 _caffe.cpp:139] DEPRECATION WARNING - deprecated use of Python interface
W0929 20:04:09.720896 20851 _caffe.cpp:140] Use this instead (with the named "weights" parameter):
W0929 20:04:09.720903 20851 _caffe.cpp:142] Net('./prediction/deploy.prototxt', 1, weights='./prediction/mm_iter_243000.caffemodel')
Traceback (most recent call last):
File "predict_json.py", line 28, in
lstmnet = caffe.Net(DEPLOY, MODEL, caffe.TEST)
RuntimeError: Could not open file ./prediction/deploy.prototxt
Could you please give me some advice on it?
The text was updated successfully, but these errors were encountered: