diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml
new file mode 100644
index 0000000..105ce2d
--- /dev/null
+++ b/.idea/inspectionProfiles/profiles_settings.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 0000000..db7929a
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000..94a25f7
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/video-swin-transformer.iml b/.idea/video-swin-transformer.iml
new file mode 100644
index 0000000..8a05c6e
--- /dev/null
+++ b/.idea/video-swin-transformer.iml
@@ -0,0 +1,12 @@
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
new file mode 100644
index 0000000..241e973
--- /dev/null
+++ b/.idea/workspace.xml
@@ -0,0 +1,40 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ {
+ "keyToString": {
+ "RunOnceActivity.OpenProjectViewOnStart": "true",
+ "RunOnceActivity.ShowReadmeOnStart": "true",
+ "last_opened_file_path": "/Users/zilliz/PycharmProjects/operator/action_classification/video-swin-transformer",
+ "settings.editor.selected.configurable": "com.jetbrains.python.configuration.PyActiveSdkModuleConfigurable"
+ }
+}
+
+
+
+
+ 1655102030715
+
+
+ 1655102030715
+
+
+
+
\ No newline at end of file
diff --git a/README.md b/README.md
index cf4d895..dbe6444 100644
--- a/README.md
+++ b/README.md
@@ -16,7 +16,7 @@ and maps vectors with labels.
## Code Example
-Use the pretrained VideoSwinTransformer model ('swin_tiny_patch244_window877_kinetics400_1k')
+Use the pretrained VideoSwinTransformer model ('swin_t_k400_1k')
to classify and generate a vector for the given video path './archery.mp4' ([download](https://dl.fbaipublicfiles.com/pytorchvideo/projects/archery.mp4)).
*Write the pipeline in simplified style*:
@@ -27,7 +27,7 @@ import towhee
(
towhee.glob('./archery.mp4')
.video_decode.ffmpeg()
- .action_classification.video_swin_transformer(model_name='swin_t_w877_k400_1k')
+ .action_classification.video_swin_transformer(model_name='swin_t_k400_1k')
.show()
)
```
@@ -43,7 +43,7 @@ import towhee
(
towhee.glob['path']('./archery.mp4')
.video_decode.ffmpeg['path', 'frames']()
- .action_classification.video_swin_transformer['frames', ('labels', 'scores', 'features')](model_name='swin_t_w877_k400_1k')
+ .action_classification.video_swin_transformer['frames', ('labels', 'scores', 'features')](model_name='swin_t_k400_1k')
.select['path', 'labels', 'scores', 'features']()
.show(formatter={'path': 'video_path'})
)
@@ -64,10 +64,10 @@ model_name='swin_tiny_patch244_window877_kinetics400_1k', skip_preprocess=False,
***model_name***: *str*
The name of pre-trained model. Supported model names:
-- swin_b_w877_k400_1k
-- swin_s_w877_k400_1k
-- swin_t_w877_k400_1k
-- swin_b_w877_k400_22k
+- swin_b_k400_1k
+- swin_s_k400_1k
+- swin_t_k400_1k
+- swin_b_k400_22k
***skip_preprocess***: *bool*
diff --git a/video_swin_transformer.py b/video_swin_transformer.py
index 75ab8c6..2f65cf5 100644
--- a/video_swin_transformer.py
+++ b/video_swin_transformer.py
@@ -32,7 +32,7 @@ class VideoSwinTransformer(NNOperator):
The number of classification labels to be returned (ordered by possibility from high to low).
"""
def __init__(self,
- model_name: str = 'swin_t_w877_k400_1k',
+ model_name: str = 'swin_t_k400_1k',
framework: str = 'pytorch',
skip_preprocess: bool = False,
classmap: str = None,