This week I modified code to test the algorithm. Namely, I added command line arguments for downsampling video, outputting the result of the work as a json file, as well as calculating the speed of the algorithm. After that I tested the algorithm on my dataset. Based on the test results I made a blog post, where I put the data and charts. During the testing I changed the min_key, max_key command line parameters and made charts for each part of the dataset (documentaries, 4K and complex videos from YouTube) based on these data.
For further actions, you may consider blocking this person and/or reporting abuse
Top comments (0)