We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 4076d7b commit 5266a72Copy full SHA for 5266a72
torchvision/datasets/kinetics.py
@@ -23,7 +23,18 @@ class Kinetics400(VisionDataset):
23
Internally, it uses a VideoClips object to handle clip creation.
24
25
Args:
26
- root (string): Root directory of the Kinetics-400 Dataset.
+ root (string): Root directory of the Kinetics-400 Dataset. Should be structured as follows:
27
+ .. code::
28
+
29
+ root/
30
+ ├── class1
31
+ │ ├── clip1.avi
32
+ │ ├── clip2.avi
33
+ │ └── ...
34
+ └── class2
35
+ ├── clipx.avi
36
+ └── ...
37
38
frames_per_clip (int): number of frames in a clip
39
step_between_clips (int): number of frames between each clip
40
transform (callable, optional): A function/transform that takes in a TxHxWxC video
0 commit comments