Hsuan

Hey @ZhongkaiZhou and @jeffbaena , Thanks for your clarification about the augmentation details about PWCNet and FlowNet 2.0. I wonder if you have successfully reproduced the results on mpi-sintel test...

@ZhongkaiZhou , Thanks for your quick and kind reply. Your reference to that project is really helpful to me, as there are few projects implementing the flow augmentation based on...

Hey, I have trained a model which work on tensorflow framework. Take a look at https://github.com/hellochick/ICNet-tensorflow

Hey, guys I have tried on tensorflow, you can take a look on it

Hey, @pjohh Did you solve this problem yet? I encounter same problem as you: Mean IoU over 150 classes: 0.0007 Pixel-wise Accuracy: 2.15% Thanks.

Hey @xhsoldier , I have tried to implement on tensorflow, and it can work with different resolution. You can take a look on it

@ThienAnh, I have tried to reproduced the model, you can take a look on it

You can simply replace it with “str”. That is an error because of different version of python.

Hi @ndujar , I've updated the script for downloading the pre-trained models. Could you check if you can download or not? Thanks.

Hey @ifangcheng, I think the problem occurs at `model.py` from `line468-482`: ``` (self.feed('conv5_3/relu') .avg_pool(h, w, h, w, name='conv5_3_pool1') .resize_bilinear(shape, name='conv5_3_pool1_interp')) (self.feed('conv5_3/relu') .avg_pool(h/2, w/2, h/2, w/2, name='conv5_3_pool2') .resize_bilinear(shape, name='conv5_3_pool2_interp')) (self.feed('conv5_3/relu') .avg_pool(h/3,...