Marvin Teichmann
Marvin Teichmann
Btw. that both of you have an inference time of about 2s show, that the GPU is not the bottleneck in the current setup. One would aspect a Titan X...
People seem to love `demo.py`. As mentioned earlier, demo.py was not designed as evaluation code and is very slow. `Demo.py` is meant as a way to understand how the code...
No, sorry. Did not find the time to work on this. For a good start use the loop I have suggested in [the comment above](https://github.com/MarvinTeichmann/KittiBox/issues/15#issuecomment-301800058).
I have reuploaded it here: [ftp://mi.eng.cam.ac.uk/pub/mttt2/models/vgg16.npy](ftp://mi.eng.cam.ac.uk/pub/mttt2/models/vgg16.npy) Can you send a pull request to change this line? I could not locate it in the doku.
The reason for this comparison is that there is simply no working fullcrf implementation on gpu available. CRFasRNN, DeepLab and other segmentation systems utilizing CRFs use the very same CPU...
Yes, densecrf does bilinear downsampling internally.
Hi Alex, the performance does not improve past 13. Also, if you go bigger then 21 (I think it was 21) I ran into GPU memory issues (@ 11GB). The...
Looks like the code does not find the module annolist. It should be in the folder KittiBox. Try to locate the file and see why the code cant find it.
Is it possible to provide a link to Model A2?
The padding 'SAME' is desired to get a whole Image output after FCN upsampling. Yes, the output of FC6 is not equal the output of a VGG classification network. This...