VideoReader with gpu ctx is slower than cpu ctx
- Dominant language
- C++
- Stars
- 2.5k
- Forks
- 232
- PR merge metrics
- No merged PRs in 30d
Description
I test the [tests/benchmark/bench_decord.py](https://github.com/dmlc/decord/blob/master/tests/benchmark/bench_decord.py) on TITAN Xp. The gpu version get stuck at the third benchmark and is much slower than the cpu version. Is this expected?
```bash
python tests/bench_decord.py --file data/ActivityNet256/anet_1.3_video_train/0acEl97ZBME.mp4 --width -1 --height -1
2569 frames, elapsed time for sequential read: 0.6075031757354736
300 frames, elapsed time for random access(not accurate): 1.3444850444793701
300 frames, elapsed time for random access(accurate): 45.86395478248596
```
```bash
python tests/bench_decord.py --file data/ActivityNet256/anet_1.3_video_train/0acEl97ZBME.mp4 --width -1 --height -1 --gpu 0
2569 frames, elapsed time for sequential read: 2.0776472091674805
300 frames, elapsed time for random access(not accurate): 6.072170257568359
```
The video can be downloaded here [https://www.youtube.com/watch?v=0acEl97ZBME](https://www.youtube.com/watch?v=0acEl97ZBME). I resize it to 342x256, 25fps.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.