Kaiwen Duan
Kaiwen Duan
@JoJoliking if a bbox has br_y < tl_y, then we make the score as -1, which means we reject the bbox
Can I see your full log?
How many GPUs do you have?
How many GPUs, not GPU memory
Modify 'batch_size' to 3 and 'chunk_sizes' to [3] in config/CenterNet-104.json. If out of memory, then modify 'batch_size' to 2 and 'chunk_sizes' to [2]
Can I see your config/CenterNet-104.json?
Can I see your own config/CenterNet-104.json?
You said you have modified it the config/CenterNet-104.json, and I want to know what does the modified file look like. The log shows that there are some errors in config/CenterNet-104.json....
Modify 'chunk_sizes' to [2], not [2,2,2,2,2,2,2,2]
what's your version of cuda