dagnichz

i'm trying to do guided backpropogation on mobilenet using your code with tensorflow 1.14. unfortunately, tensorflow does not reposnd to the override you suggested: @ops.RegisterGradient("GuidedRelu") def _GuidedReluGrad(op, grad): return tf.where(0....

training loss is stuck on high values

2

i'm trying to reproduce the results and train a temporal network based on the optical flow input you suggested. when I run your temporal_train.py code. the learning loss is not...

ANET_HOME and ANET_CFG are required

5

hi. i'm trying to run your code on linux. I see there are 2 enviorment variables that are not configured anywhere. ANET_HOME and ANET_CFG. to what folders should I point...

can you elaborate on the Propogation function. mainly on the following issues : 1. what's exactly does each iteration does ? 2. what is the flow.get_warp_label aims to do? 3....

i'm having a hard time understanding why you need FlowNet2 when performing video_inpaining.py to my understanding , FlowNet2 provides optical flow for the unmasked frames. However, in your paper you...