Rex Cheng

Results 104 comments of Rex Cheng
trafficstars

1. Can you provide all the output frames up to the point of failure so that we can have a closer look? 2. What if you supply fewer objects but...

No, I haven't received anything.

Sorry I cannot check it right now. I'll get back at this later.

Hi, Similar problems are usually solved by reinstalling CUDA drivers / pytorch. See https://github.com/hkchengrex/XMem/issues/41 and https://github.com/hkchengrex/MiVOS/issues/48.

I'm afraid that I cannot debug your training setup. The general advice is to check for CPU/GPU/IO bottlenecks.

Sound like a CPU bottleneck but your CPU is not at full load. Perhaps try increasing the number of data loaders?

Always 0? That has never happened in my training. Did you change something?

Feel free to re-open if there are any updates.

I didn't time each component specifically. For pre-training/main training, each iteration took around 0.28/0.66 seconds. The GPU load should be near 99% most of the time -- which means the...