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 >>

提交 3e3ce9b0 编写于 作者: L linjintao
浏览文件
操作

add memory value for some setting

上级 c77c1f2e
隐藏空白更改
内联 并排
Showing with 22 addition and 22 deletion
configs/localization/bsn/README.md
浏览文件 @ 3e3ce9b0
......@@ -6,7 +6,7 @@
|config | pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log|
|-|-|-|-|-|-|-|-|
|bsn_400x100_1x16_20e_activitynet_feature | None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem]() [ckpt_pem]| [log_tem]() [log_pem]()|
|bsn_400x100_1x16_20e_activitynet_feature | None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem]() [ckpt_pem]()| [log_tem]() [log_pem]()|
For more details on data preparation, you can refer to ActivityNet feature in [Data Preparation](/docs/data_preparation.md).
......
configs/recognition/i3d/README.md
浏览文件 @ 3e3ce9b0
......@@ -6,10 +6,10 @@
|config | backbone |pretrain| top1 acc| top5 acc | gpu_mem(M)| ckpt | log|
|-|-|-|-|-|-|-|-|
|[i3d_r34_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r34_32x2x1_100e_kinetics400_rgb.py) | ResNet34|ImageNet |68.37|88.15| x| [ckpt]() | [log]()|
|[i3d_r50_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py) | ResNet50|ImageNet |72.68|90.78| x |[ckpt]() | [log]()|
|[i3d_r50_dense_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb.py) | ResNet50| ImageNet|72.77|90.57| x| [ckpt]() | [log]()|
|[i3d_r50_fast_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb.py) | ResNet50 |ImageNet|72.32|90.72| x| [ckpt]() | [log]()|
|[i3d_r34_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r34_32x2x1_100e_kinetics400_rgb.py) | ResNet34|ImageNet |68.37|88.15|3176| [ckpt]() | [log]()|
|[i3d_r50_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_32x2x1_100e_kinetics400_rgb.py) | ResNet50|ImageNet |72.68|90.78|5170|[ckpt]() | [log]()|
|[i3d_r50_dense_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_dense_32x2x1_100e_kinetics400_rgb.py) | ResNet50| ImageNet|72.77|90.57|5170| [ckpt]() | [log]()|
|[i3d_r50_fast_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_fast_32x2x1_100e_kinetics400_rgb.py) | ResNet50 |ImageNet|72.32|90.72|5170| [ckpt]() | [log]()|
|[i3d_r50_video_3d_32x2x1_100e_kinetics400_rgb](/configs/recognition/i3d/i3d_r50_video_32x2x1_100e_kinetics400_rgb.py) | ResNet50| ImageNet| x | x | x| [ckpt]() | [log]()|
For more details on data preparation, you can refer to Kinetics400 in [Data Preparation](/docs/data_preparation.md).
......
configs/recognition/tin/README.md
浏览文件 @ 3e3ce9b0
......@@ -5,8 +5,8 @@
### Kinetics-400
|config | backbone| pretrain | top1 acc| top5 acc | gpu_mem(M)| ckpt | log|
|-|-|-|-|-|-|-|-|
|[tin_r50_1x1x8_35e_kinetics400_rgb](/configs/recognition/tin/tin_r50_1x1x8_35e_kinetics400_rgb.py) | ResNet50| ImageNet |69.44|89.19| x| [ckpt]() | [log]()|
|[tin_r50_finetune_1x1x8_35e_kinetics400_rgb](/configs/recognition/tin/tin_r50_finetune_1x1x8_35e_kinetics400_rgb.py) | ResNet50| ImageNet |71.00|89.98| x | [ckpt]() | [log]()|
|[tin_r50_1x1x8_35e_kinetics400_rgb](/configs/recognition/tin/tin_r50_1x1x8_35e_kinetics400_rgb.py) | ResNet50| ImageNet |69.44|89.19| 6173| [ckpt]() | [log]()|
|[tin_r50_finetune_1x1x8_35e_kinetics400_rgb](/configs/recognition/tin/tin_r50_finetune_1x1x8_35e_kinetics400_rgb.py) | ResNet50| ImageNet |71.00|89.98| 6174 | [ckpt]() | [log]()|
|[tin_r50_video_2d_1x1x8_35e_kinetics400_rgb](/configs/recognition/tin/tin_r50_video_1x1x8_35e_kinetics400_rgb.py) | ResNet50 | ImageNet | x | x | x | [ckpt]() | [log]()|
### Something-Something V1
......
configs/recognition/tsm/README.md
浏览文件 @ 3e3ce9b0
......@@ -6,16 +6,16 @@
|config | backbone | pretrain | top1 acc| top5 acc | gpu_mem(M)| ckpt | log|
|-|-|-|-|-|-|-|-|
|[tsm_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py) | ResNet50| ImageNet |70.24|89.56| x | [ckpt]() | [log]()|
|[tsm_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py) | ResNet50 | ImageNet|71.84|90.18| x | [ckpt]() | [log]()|
|[tsm_r50_1x1x16_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb.py) | ResNet50| ImageNet |71.69|90.4| x | [ckpt]() | [log]()|
|[tsm_r50_video_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_video_1x1x8_100e_kinetics400_rgb.py) | ResNet50| ImageNet | x | x | x | [ckpt]() | [log]()|
|[tsm_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_kinetics400_rgb.py) | ResNet50| ImageNet |70.24|89.56| 7079 | [ckpt]() | [log]()|
|[tsm_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_dense_1x1x8_100e_kinetics400_rgb.py) | ResNet50 | ImageNet|71.84|90.18| 7079 | [ckpt]() | [log]()|
|[tsm_r50_1x1x16_50e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_kinetics400_rgb.py) | ResNet50| ImageNet |71.69|90.4| 10404 | [ckpt]() | [log]()|
|[tsm_r50_video_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsm/tsm_r50_video_1x1x8_100e_kinetics400_rgb.py) | ResNet50| ImageNet | x | x | 7077 | [ckpt]() | [log]()|
### Something-Something V1
|config | backbone| pretrain | top1 acc| top5 acc | gpu_mem(M) | ckpt | log|
|-|-|-|-|-|-|-|-|
|[tsm_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb.py) | ResNet50 | ImageNet|44.62|75.51| x| [ckpt]() | [log]()|
|[tsm_r50_1x1x8_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv1_rgb.py) | ResNet50 | ImageNet|44.62|75.51| 7077| [ckpt]() | [log]()|
|[tsm_r50_1x1x16_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv1_rgb.py) | ResNet50 | ImageNet|43.81|74.73| x | [ckpt]() | [log]()|
|[tsm_r101_1x1x8_50e_sthv1_rgb](/configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv1_rgb.py) | ResNet101| ImageNet |46.41|74.07| x | [ckpt]() | [log]()|
......@@ -24,8 +24,8 @@
|config | backbone | pretrain| top1 acc| top5 acc | gpu_mem(M) | ckpt | log|
|-|-|-|-|-|-|-|-|
|[tsm_r50_1x1x8_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x8_50e_sthv2_rgb.py) | ResNet50| ImageNet |59.91|84.61| x| [ckpt]() | [log]()|
|[tsm_r50_1x1x16_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb.py) | ResNet50| ImageNet |56.10|84.43| x| [ckpt]() | [log]()|
|[tsm_r101_1x1x8_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb.py) | ResNet101 | ImageNet| x | x | x | [ckpt]() | [log]()|
|[tsm_r50_1x1x16_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r50_1x1x16_50e_sthv2_rgb.py) | ResNet50| ImageNet |56.10|84.43| 10400| [ckpt]() | [log]()|
|[tsm_r101_1x1x8_50e_sthv2_rgb](/configs/recognition/tsm/tsm_r101_1x1x8_50e_sthv2_rgb.py) | ResNet101 | ImageNet|59.12|85.74| 9784 | [ckpt]() | [log]()|
For more details on data preparation, you can refer to Kinetics400, Something-Something V1 and Something-Something V2 in [Data Preparation](/docs/data_preparation.md).
......
configs/recognition/tsn/README.md
浏览文件 @ 3e3ce9b0
......@@ -6,24 +6,24 @@
|config | backbone | pretrain | top1 acc| top5 acc | gpu_mem(M) | ckpt | log|
|-|-|-|-|-|-|-|-|
|[tsn_r50_1x1x3_100e_ucf101_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_80e_ucf101_rgb.py) | ResNet50 | ImageNet |80.12|96.09| x| [ckpt]() | [log]()|
|[tsn_r50_1x1x3_100e_ucf101_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_80e_ucf101_rgb.py) | ResNet50 | ImageNet |80.12|96.09|8332| [ckpt]() | [log]()|
### Kinetics-400
|config | backbone|pretrain | top1 acc| top5 acc | gpu_mem(M)| ckpt | log|
|-|-|-|-|-|-|-|-|
|[tsn_r50_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb.py) | ResNet50 | ImageNet|70.60|89.26| x | [ckpt]() | [log]()|
|[tsn_r50_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x5_50e_kinetics400_rgb.py) | ResNet50| ImageNet |68.64|88.19| x | [ckpt]() | [log]()|
|[tsn_r50_dense_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb.py) | ResNet50| ImageNet |68.59|88.31| x | [ckpt]() | [log]()|
|[tsn_r50_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x3_100e_kinetics400_rgb.py) | ResNet50 | ImageNet|70.60|89.26|8344| [ckpt]() | [log]()|
|[tsn_r50_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x5_50e_kinetics400_rgb.py) | ResNet50| ImageNet |68.64|88.19|7031| [ckpt]() | [log]()|
|[tsn_r50_dense_1x1x5_50e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x5_100e_kinetics400_rgb.py) | ResNet50| ImageNet |68.59|88.31|7028| [ckpt]() | [log]()|
|[tsn_r50_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_1x1x8_100e_kinetics400_rgb.py) | ResNet50| ImageNet |69.41|88.37| x | [ckpt]() | [log]()|
|[tsn_r50_320p_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x3_100e_kinetics400_rgb.py) | ResNet50| ImageNet |70.91|89.51| 8344 | [ckpt]() | [log]() |
|[tsn_r50_320p_1x1x3_110e_kinetics400_flow](/configs/recognition/tsn/tsn_r50_320p_1x1x3_110e_kinetics400_flow.py) | ResNet50 | ImageNet|55.70|79.85| 8471 | [ckpt]() | [log]() |
|tsn_r50_320p_1x1x3_kinetics400_twostream [1: 1]* | ResNet50 | ImageNet|72.76|90.52| x | [ckpt]() | [log]() |
|[tsn_r50_320p_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb.py) | ResNet50| ImageNet |72.41|90.55| 8344 | [ckpt]() | [log]() |
|[tsn_r50_320p_1x1x8_110e_kinetics400_flow](/configs/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow.py) | ResNet50 | ImageNet|57.76|80.99| 8473 | [ckpt]() | [log]() |
|[tsn_r50_320p_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_320p_1x1x8_100e_kinetics400_rgb.py) | ResNet50| ImageNet |72.41|90.55|8344| [ckpt]() | [log]() |
|[tsn_r50_320p_1x1x8_110e_kinetics400_flow](/configs/recognition/tsn/tsn_r50_320p_1x1x8_110e_kinetics400_flow.py) | ResNet50 | ImageNet|57.76|80.99|8473| [ckpt]() | [log]() |
|tsn_r50_320p_1x1x8_kinetics400_twostream [1: 1]* | ResNet50| ImageNet |74.64|91.77| x | [ckpt]() | [log]() |
|[tsn_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb.py) | ResNet50 | ImageNet|70.77|89.3| x | [ckpt]() | [log]()|
|[tsn_r50_video_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_1x1x3_100e_kinetics400_rgb.py) | ResNet50| ImageNet | x | x | x | [ckpt]() | [log]()|
|[tsn_r50_dense_1x1x8_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_dense_1x1x8_100e_kinetics400_rgb.py) | ResNet50 | ImageNet|70.77|89.3|8344| [ckpt]() | [log]()|
|[tsn_r50_video_1x1x3_100e_kinetics400_rgb](/configs/recognition/tsn/tsn_r50_video_1x1x3_100e_kinetics400_rgb.py) | ResNet50| ImageNet | x | x |8339| [ckpt]() | [log]()|
*We combine rgb and flow score with coefficients 1: 1 to get the two-stream prediction (without applying softmax).
......
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