google-deepmind/c3_neural_compression

c3_neural_compression's Issues

Decoded image and/or bitstreams

Hello,

Thanks for sharing your code! Could it be possible for you to share the decoded images or the bitstreams to obtain them as well? I would like to calculate additional metrics (MS-SSIM, LPIPS etc...) and to compare the decoding times with other solutions on my machine. Thanks in advance!

Video coding results

Hi 👋

I've been doing some video encoding using C3 and I got some weird results here and there. For the context, I am using the UVG dataset with the configs/uvg.py file with the following changes:

# ... configs/uvg.py
exp.dataset.num_frames = 9         # I want to code only 9 frames
exp.opt.num_noise_steps = 10_000   # Faster encoding
exp.opt.max_num_ste_steps = 1_000  # Faster encoding

exp.dataset.video_idx = 4          # I want to code a single sequence e.g. the 4th video
exp.dataset.skip_examples = 0      # I specify explicitly the video_idx, so I can start at 0
exp.dataset.num_examples = 48      # A 1920x1080 frame has 48 non-overlapping 180x240 patches

Here are the results I obtained sequence-wise (ignore the average graph 😉). Some sequences (Bosphorus, YachtRide) failed to converge. Have I done something wrong with the parameters within the config file? Or is it due to the small patch size and the reduced number of frames which increase the relative share of the NN parameters in the overall rate?

Thanks!