mnc doesnt recognize any object
limorbagizada opened this issue · comments
I try to run the demo, with the suggested trained MNC model and the original 5 images, but the output images getting from the algorithm are black without any recognized objects in the picture.I notice that the im_detect function return very low scores, lower than 0.1
I didn't change anything in the code, what can be the problem?
I have the same issue...
I have the same issue when working with GTX1080 GPU and cuDNN v4. Build with CuDNN V5 solved this problem.
Alternatively, a dirty solution is to disable cuDNN. In my case, inference still runs reasonably fast wihthout cuDNN.
@PangolinLE314 I sadly could not build MNC's fork of Caffe with cuDNN 5. Did you have to do anything in particular to get it to build with cuDNN 5?
@AndreiBarsan
Here is the solution from manipopopo:
cd caffe-fast-rcnn
git remote add caffe https://github.com/BVLC/caffe.git
git fetch caffe
git merge -X theirs caffe/master
Remove self_.attr("phase") = static_cast(this->phase_); from include/caffe/layers/python_layer.hpp after merging.
@PangolinLE314 awesome! That worked! I could build with cuDNN 5, all the Caffe tests passed, and inference is now considerably faster and uses less memory. Thank you very much!
@PangolinLE314
I have exactly the same problem and thanks PangolinLE.
Hi, I am having this problem working with cuDNN4. I have done what @PangolinLE314 proposes, but then I got pycaffe could not import NCCL nor Timer. If anyone has a clue about what I could do I would be extremely grateful. Cheers!