Akshay Chawla

Hi @terminator-007 I think this is happening because you might be using Python3 instead of Python2. Can you check if it works with Python 3 ? I'll try to make...

Hi Alia, The softmax layer in keras expects a tensor with the shape (batch_size, num_classes) however, the output from pool10 layer in case of squeezenet is (batch_size, num_filters, height, width)....

Hi @kinredon ! Thank you for your interest in our work. Apologies for the long delay in my response. While our code is built only for a specific one-stage detector:...

Hey @SaschaHornauer sorry for the late reply. I remember debating whether to use urllib.urlopen or urlretrieve but I forgot why I chose urlretrieve. I'll make the changes you suggested by...

Not exactly. Optical flow tracks the movements of point in 2d, however these points are actually moving in the 3d space. To get an estimate of the motion of the...