About the blob's problem when I run online_recognition?

mzolfaghari / ECO-efficient-video-understanding

Code and models of paper " ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018

MIT License

437 stars 96 forks source link

Closed idealboy closed 5 years ago

idealboy commented 5 years ago

sir,

when I run online_recognition.py , when loading the model, the problem occurs such below:

blob.hpp:141] Check failed: num_axes() <= 4 (5 vs. 4) Cannot use legacy accessors on Blobs with > 4 axes

does the caffe_3d branch support C3D?

thank you very much!

And I just compile caffe by make$make pycaffe but not cmake.

idealboy commented 5 years ago

It seems that I must compile with cuDNN supporting, then the blob will be compatible with the 5 dimension tensor

mzolfaghari commented 5 years ago

@idealboy Happy to hear that you solved the problem. Closing now. Feel free to re-open it if you had any problem.