Christopher Tensmeyer

The issue here is that the code cannot find the input image. When `cv2.imread()` loads an image from a non-existent file, it returns None rather than throwing an exception. Are...

imgList is a file that lists image paths relative to imgDir, one per line. On Tue, Feb 11, 2020 at 6:24 AM Rhutus wrote: > How to annotate for different...

You need to use my custom fork of caffe: https://github.com/ctensmeyer/caffe This has the implementation for the BilinearInterpolation Layer.

You could use a deconv layer to perform bilinear upsampling with the proper weights. That should work for input images whose dimensions are multiples of 16. That way, when you...

The code to train the models is included in the Caffe library. You point it at the model file and the solver file and it trains it. The difficult part...

It's possible I have a bug somewhere in my Caffe code that causes the illegal access on some GPUs. What GPU are you using? On Sun, Oct 21, 2018 at...

I've never tried to build on ubuntu 18, only 14 and 16. On Fri, Apr 12, 2019 at 3:31 AM justinner wrote: > Hi,Chris,I just want to install caffe ,on...

I'm also interested in reproducing Polygon RNN. @agethen, the main difficulty here is that the output of the previous two timesteps are being fed in as input to the current...

Thanks for confirming my suspicion. I think I'll just write some python code to manually unroll the LSTM in the prototxt and make a new layer to handle padding the...

I ran into this issue as well. It is a sync bug that only happens if you JIT the faster COCOeval Op. After the evaluation prediction loop and prediction gather,...