JarsOfJam-Scheduler
  • Member for 2 years, 6 months
  • Last seen more than a month ago
CUDA 8.0 is compatible with my GeForce GTX 670M Wikipedia says, but TensorFlow rises an error: GTX 670M's Compute Capability is < 3.0
Accepted answer
1 votes

CUDNN and Tensorflow require a GPU which has a compute capacity of 3.0 at least: not only the CUDA version must take account of this CC, but also these both programs. Indeed: https://stackoverflow....

View answer
SRGAN Generator Architecture: Why is it possible to do this elementwise sum?
Accepted answer
0 votes

It's possible by adding 0 as padding to the tensor. What is currently refered to "same padding" (in particular in Keras).

View answer