提交 6239506d 编写于 作者: L linjintao

Fix slowfast inference frames

上级 a1682bb5
......@@ -6,8 +6,8 @@
|config | gpus | backbone |pretrain| top1 acc| top5 acc | inference_time(video/s) | gpu_mem(M) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[slowfast_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py) |7x3| ResNet50|None |75.3|92.2|1.6 (320x3 frames)|6203|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16x1_256e_kinetics400_rgb_20200618-9a124260.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/sf_4x16.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16_75.3_92.2.log.json)|
|[slowfast_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py) |8x4| ResNet50 |None|76.36|92.56|1.3 (320x3 frames)|9062| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8x1_256e_kinetics400_rgb_20200619-ecd36535.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/sf_8x8.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8_76.36_92.56.log.json)|
|[slowfast_r50_4x16x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py) |7x3| ResNet50|None |75.3|92.2|1.6 ((32+4)x10x3 frames)|6203|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16x1_256e_kinetics400_rgb_20200618-9a124260.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/sf_4x16.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb/slowfast_r50_4x16_75.3_92.2.log.json)|
|[slowfast_r50_8x8x1_256e_kinetics400_rgb](/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py) |8x4| ResNet50 |None|76.36|92.56|1.3 ((32+8)x10x3 frames)|9062| [ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8x1_256e_kinetics400_rgb_20200619-ecd36535.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/sf_8x8.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb/slowfast_r50_8x8_76.36_92.56.log.json)|
Notes:
1. The **gpus** indicates the number of gpu we used to get the checkpoint. It is noteworthy that the configs we provide are used for 8 gpus as default.
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册