Training on Custom data and objects besides person

[abhigoku10]

HI @oyxhust @yueruchen Thanks for wonderful code , when i train the model for custom object besides person it behaves differently , can you share some pointers what are the things i need to consider when i change the objects. Thanks in advance

[yifanjiang19]

Can you update the results you get?

[wuchenxi118]

I would like to ask why this problem occurs, thank you very much for your answer~

model [Pix2PixModel] was created WARNING:root:Setting up a new session... create web directory ./checkpoints/third_try/web... Traceback (most recent call last): File "train.py", line 35, in model.optimize_parameters(only_d) File "/home/wuchenxi/PS-gan-ori/models/pix2pix_model.py", line 179, in optimize_parameters self.backward_D_person() File "/home/wuchenxi/PS-gan-ori/models/pix2pix_model.py", line 131, in backward_D_person self.person_fake = self.netD_person.forward(self.person_crop_fake) File "/home/wuchenxi/PS-gan-ori/models/networks.py", line 470, in forward x = self.conv1(x) File "/home/wuchenxi/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call result = self.forward(*input, **kwargs) File "/home/wuchenxi/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward self.padding, self.dilation, self.groups) RuntimeError: expected stride to be a single integer value or a list of 1 values to match the convolution dimensions, but got stride=[2, 2]

[wuchenxi118]

And Is your code written in python2?

[HITxyer]

＠abhigoku10　I'd like to inquiry you how to change the data