Open irvingzhang0512 opened 3 years ago
Thanks, this is great!
I went through the codes of C3D. It turns out that we cannot modify C3D config to support other input shapes. I haven't study the codes of TPN, may take a look in April.
Maybe a table like this | model type | model name | sampling strategy | v100/1080ti/agx latency(ms) | kinetics400 accuracy | sthv2 accuracy | comments |
---|---|---|---|---|---|---|---|
PyTorch | TSM-R50 | 1x1x8 | 13/16/86 | 70.24 / 89.56 | 57.86 / 61.12 | / |
Notes: We will support Support auto_fp16
using torch.cuda.amp
in the future https://github.com/open-mmlab/mmcv/pull/791
Not really. Most info in the above table is already present in the modelzoo, or can be added to the tables (i.e. column v100/1080ti/agx latency) in modelzoo.
I think the most valuable part is the speed/accuracy benchmark for different precisions.
Something like that in GluonCV?
Description
MMAction2 provide a large number of recognizers. In order to choose the right model for our applications, maybe we need to compare all models in one table. But I don't know how to do this.
I'm open to all suggestions.
Inference time statistics
Notes:
32f, 16f, 8f
means number of frames for model inputs.(1, num_frames, 3, 224, 224)
(1, 1, 3, num_frames, 224, 224)
(1, 1, 3, 16, 112, 112)
.TODO