psychopa4 / PFNL

Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations
MIT License
138 stars 21 forks source link

OOM,when test big image such as 960*540->3840*2160 #5

Open robotzheng opened 4 years ago

robotzheng commented 4 years ago

OOM at "f = tf.matmul(theta_x, phi_x)" in the "NonLocalBlock" function. train with 32*32 's NonLocalBlock, test with a whole image, maybe not right. how to edit the code?

psychopa4 commented 4 years ago

As has been discussed in the paper, the non-local operation can require a huge GPU memory, which is exactly why we make improvements to suit it for video SR. According to your description, the best way is to use a GPU with a larger memory. If that's not applicable, you might as well choose a larger number of rescaling factor r as described in Section 3.2 in the paper.