Skip to content

M
mmaction2

openvinotoolkit / mmaction2
10 个月 前同步成功

通知 2
Star 5
Fork 3
M
mmaction2

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

未验证 提交 14c4a5e1 编写于 作者: H Haodong Duan 提交者： GitHub
浏览文件
操作

update README (#98)

上级 c4a6b398
隐藏空白更改
内联 并排
Showing with 12 addition and 6 deletion
configs/localization/bmn/README.md
浏览文件 @ 14c4a5e1
...@@ -4,14 +4,17 @@ ...@@ -4,14 +4,17 @@
### ActivityNet feature ### ActivityNet feature
|config | gpus | pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json| |config |feature | gpus | pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:| |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:-:|
|[bmn_400x100_9e_2x8_activitynet_feature](/configs/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py) |2| None |75.28|67.22|5420|3.27|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature_20200619-42a3b111.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log.json)| |[bmn_400x100_9e_2x8_activitynet_feature](/configs/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py) |cuhk_mean_100 |2| None |75.28|67.22|5420|3.27|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature_20200619-42a3b111.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log.json)|
| |mmaction_video |2| None |75.43|67.22|5420|3.27|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_video/bmn_400x100_2x8_9e_mmaction_video_20200809-c9fd14d2.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_video/bmn_400x100_2x8_9e_mmaction_video_20200809.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_video/bmn_400x100_2x8_9e_mmaction_video_20200809.json) |
| |mmaction_clip |2| None |75.35|67.38|5420|3.27|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_clip/bmn_400x100_2x8_9e_mmaction_clip_20200809-10d803ce.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_clip/bmn_400x100_2x8_9e_mmaction_clip_20200809.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_clip/bmn_400x100_2x8_9e_mmaction_clip_20200809.json) |
Notes: Notes:
1. The **gpus** indicates the number of gpu we used to get the checkpoint. 1. The **gpus** indicates the number of gpu we used to get the checkpoint.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU, According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu. e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. For feature column, cuhk_mean_100 denotes the widely used cuhk activitynet feature extracted by [anet2016-cuhk](https://github.com/yjxiong/anet2016-cuhk), mmaction_video and mmaction_clip denote feature extracted by mmaction, with video-level activitynet finetuned model or clip-level activitynet finetuned model respectively.
For more details on data preparation, you can refer to ActivityNet feature in [Data Preparation](/docs/data_preparation.md). For more details on data preparation, you can refer to ActivityNet feature in [Data Preparation](/docs/data_preparation.md).
......
configs/localization/bsn/README.md
浏览文件 @ 14c4a5e1
...@@ -4,14 +4,17 @@ ...@@ -4,14 +4,17 @@
### ActivityNet feature ### ActivityNet feature
|config | gpus| pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json| |config |feature | gpus| pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:| |:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:-:|
|bsn_400x100_1x16_20e_activitynet_feature |1| None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature_20200619-cd6accc3.pth) [ckpt_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature_20200619-6111891d.pth)| [log_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log) [log_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log)| [json_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log.json) [json_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log.json)| |bsn_400x100_1x16_20e_activitynet_feature |cuhk_mean_100 |1| None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature_20200619-cd6accc3.pth) [ckpt_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature_20200619-6111891d.pth)| [log_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log) [log_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log)| [json_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log.json) [json_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log.json)|
| |mmaction_video |1| None |74.93|66.74|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_video/bsn_tem_400x100_1x16_20e_mmaction_video_20200809-ad6ec626.pth) [ckpt_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_video/bsn_pem_400x100_1x16_20e_mmaction_video_20200809-aa861b26.pth)| [log_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_video/bsn_tem_400x100_1x16_20e_mmaction_video_20200809.log) [log_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_video/bsn_pem_400x100_1x16_20e_mmaction_video_20200809.log) | [json_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_video/bsn_tem_400x100_1x16_20e_mmaction_video_20200809.json) [json_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_video/bsn_pem_400x100_1x16_20e_mmaction_video_20200809.json) |
| |mmaction_clip |1| None |75.19|66.81|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_clip/bsn_tem_400x100_1x16_20e_mmaction_clip_20200809-0a563554.pth) [ckpt_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_clip/bsn_pem_400x100_1x16_20e_mmaction_clip_20200809-e32f61e6.pth)| [log_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_clip/bsn_tem_400x100_1x16_20e_mmaction_clip_20200809.log) [log_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_clip/bsn_pem_400x100_1x16_20e_mmaction_clip_20200809.log) | [json_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_clip/bsn_tem_400x100_1x16_20e_mmaction_clip_20200809.json) [json_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_clip/bsn_pem_400x100_1x16_20e_mmaction_clip_20200809.json) |
Notes: Notes:
1. The **gpus** indicates the number of gpu we used to get the checkpoint. 1. The **gpus** indicates the number of gpu we used to get the checkpoint.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU, According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu. e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. For feature column, cuhk_mean_100 denotes the widely used cuhk activitynet feature extracted by [anet2016-cuhk](https://github.com/yjxiong/anet2016-cuhk), mmaction_video and mmaction_clip denote feature extracted by mmaction, with video-level activitynet finetuned model or clip-level activitynet finetuned model respectively.
For more details on data preparation, you can refer to ActivityNet feature in [Data Preparation](/docs/data_preparation.md). For more details on data preparation, you can refer to ActivityNet feature in [Data Preparation](/docs/data_preparation.md).
......
Markdown is supported
0% 或 .
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 或