Mario Loaiciga

I was wondering the same... @iluvrachel did the normalization step work? I still didn't proceed to "step 5" because I wonder I will train on un-normalized labels :(

@mallorbc the original paper mentions on Section 8.3 that they used 8~17 mins of footage for their target videos. Additionally they point out: > We follow the progressive learning schedule...

I'm not familiar enough with Pix2PixHD but a new Hand-gesture detector by google researchers hit the shelf after is showcase on CVPR 2019. I suppose a step in the pipe...

Im using the same hardware as you. It will take around 2 days to estimate poses and detect the head in for a 14 min video when running [make_target.py](https://github.com/CUHKSZ-TQL/EverybodyDanceNow_reproduce_pytorch/blob/master/make_target.py) on...

@wangzhangup, @tylin pycharm requires a .py file with Flask or some other package of the sort. But the only 2 python files available are hard coded to work with Amazon...

Is the first time I see someone passing the `Keras` execution mode to `tf.Session()` as a placeholder (a `` type tensor to be precise). I'm not very knowledgeable about the...

Here I'm converting an image to a proper size np array, fetching the graph input and output tensors by name (previously y modified names by prependng "out_" )and instantiating a...

@ambr89, @bendidi, @LucasMahieu have you agreed on what is needed to do next? Do you have a list of milestones we could help with?

@JingliangGao Did you activate the `noLastConv` flag? I encountered this issue only when using the VGG16 model trained on CIFAR. There seems to be some especial condition for how this...

I will try to make this work and post if I succeed. Or did you try it, @deepakanandece? How did it go?