Yilin Liu
Got this error when trying to run the demo.
`tensorflow.python.framework.errors_impl.InvalidArgumentError: Node 'worker_0/Net/conv_bn_relu/bn_/moments/mean': Unknown input node 'worker_0/Net/conv__bn_relu/conv_/conv'` I got this error occasionally during the inference. It happens by chance in different layers (ones with dropout). I suspect that it has...
Hi, I found that the teacher model's weights seem to be not updated as it performed as bad as it was first initialized. `alpha = min(1 - 1 / (global_step...
Hi all, I'm stuck on this error when I'm trying to install Mnisten on mac. Really appreciate any help! g++ -Wall -O2 -lboost_filesystem-mt -std=c++0x -o mnisten src/main.cpp Undefined symbols for...
Hi @ozgurkara99, I'm wondering, how do we train on our dataset? I tried to modify the path in "utils/path.py" but it seems like the code is only taking caring of...
Hi @Britefury, in optim_weight_ema.py, `for p, src_p in zip(self.params, self.src_params): p.data[:] = src_p.data[:]` this line doesn't seem to really deep copy the student model, so teacher and student may be...
Hi @Skydes , thank you for sharing your implementation. I am a newbie and am wondering: 1) shouldn't the ConcreteDropout layer be applied **after**convolutional layers? 2) I added the concrete_dropout.py...
Hi @perone, I found that the teacher model's weights seem to be not updated as it performed as bad as it was first initialized. def update_ema_variables(model, ema_model, alpha, global_step): alpha...