-
Notifications
You must be signed in to change notification settings - Fork 993
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
Run FASTER_RCNN Segmentation fault #139
Comments
have you solved the issue? I met similiar error: segmentation error when run the line: |
guys, have you solved this problem, i met this problem also, can you share with me, if you solved,thank you! |
Thanks OAID teams grateful works
my platfoms is rk3399 and os is ubuntu 16.04
l run the "./examples/build/faster_rcnn/FASTER_RCNN" , using your provide "VGG16_faster_rcnn.prototxt" and "VGG16_faster_rcnn_final.caffemodel", everything is ok.
However, when l use my custom file (mynet_main_new.pt, mynet_main.caffemodel), l meet the follwoing error:
./examples/build/faster_rcnn/FASTER_RCNN -p /root/Caffe-HR T/mynet_main_new.pt -m /root/Caffe-HRT/mynet_main.caffemodel
/media/linaro/f9a0c086-b406-41d8-a375-ad1fb929f773/Tengine/examples/build/faster_rcnn/FASTER_RCNN
image file not specified,using /media/linaro/f9a0c086-b406-41d8-a375-ad1fb929f773/Tengine/tests/images/ssd_dog.jpg by default
Segmentation fault
l debug the codes and find the above error occur in
ret = prerun_graph(graph);
that is to say, the function fail to finished.
l also change the caffemodel file and run the following command:
./examples/build/faster_rcnn/FASTER_RCNN -p /root/Caffe-HRT/mynet_main_new.pt (mynet_main_new.pt is upgrate proto file)
and get following log:
/media/linaro/f9a0c086-b406-41d8-a375-ad1fb929f773/Tengine/examples/build/faster_rcnn/FASTER_RCNN
model file not specified,using /media/linaro/f9a0c086-b406-41d8-a375-ad1fb929f773/Tengine/models/VGG16_faster_rcnn_final.caffemodel by default
image file not specified,using /media/linaro/f9a0c086-b406-41d8-a375-ad1fb929f773/Tengine/tests/images/ssd_dog.jpg by default
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:604] Reading dangerously large protocol message. If the message turns out to be larger than 1073741824 bytes, parsing will be halted for security reasons. To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:81] The total number of bytes read was 548317115
height width scale225,300,0.390625
infer shaped for node: conv1 op: Convolution failed
Prerun graph failed, errno: 0
the log means the error is caused by my caffemodel file (mynet_main.caffemodel), l really don't know how to solve the problem, anyone can help me and any suggestion are welcome! thank you!
The text was updated successfully, but these errors were encountered: