DeepC: Implementing Deep Convolutional Neural Network in C without External Libraries for YUV video Super-Resolution
This code uses FSRCNN algorithm to upsample the Y component of each frame of the YUV 4:2:0 video with scale factor of 2.
No external liberaries are used and all required functions (including convolution, deconvolution and non-linearities) are written in main file
For more information on the code, check my post on Towards Data Sceince.
To compile the code in Linux use:
gcc source.c -o videosr
Then run the code using following command:
./videosr <input_video_name> <output_video_name>
For example, in order to upsample
./videosr foreman_qcif_146x144.yuv output_foreman_352x288.yuv