STAM - Pytorch
Implementation of STAM (Space Time Attention Model), yet another pure and simple SOTA attention model that bests all previous models in video classification. This corroborates the finding of TimeSformer. Attention is all we need.
Install
$ pip install stam-pytorch
Usage
import torch
from stam_pytorch import STAM
model = STAM(
dim = 512,
image_size = 256, # size of image
patch_size = 32, # patch size
num_frames = 5, # number of image frames, selected out of video
space_depth = 12, # depth of vision transformer
space_heads = 8, # heads of vision transformer
space_mlp_dim = 2048, # feedforward hidden dimension of vision transformer
time_depth = 6, # depth of time transformer (in paper, it was shallower, 6)
time_heads = 8, # heads of time transformer
time_mlp_dim = 2048, # feedforward hidden dimension of time transformer
num_classes = 100, # number of output classes
space_dim_head = 64, # space transformer head dimension
time_dim_head = 64, # time transformer head dimension
dropout = 0., # dropout
emb_dropout = 0. # embedding dropout
)
frames = torch.randn(2, 5, 3, 256, 256) # (batch x frames x channels x height x width)
pred = model(frames) # (2, 100)
Citations
@misc{sharir2021image,
title = {An Image is Worth 16x16 Words, What is a Video Worth?},
author = {Gilad Sharir and Asaf Noy and Lihi Zelnik-Manor},
year = {2021},
eprint = {2103.13915},
archivePrefix = {arXiv},
primaryClass = {cs.CV}
}
191 Dec 31, 2022
2 Jun 5, 2022
58 Dec 21, 2022
159 Dec 22, 2022
54 Nov 21, 2022
8 Oct 29, 2022
272 Dec 23, 2022
1.4k Jan 1, 2023
2 Dec 25, 2021
1 Jan 24, 2022
21 May 09, 2022
42 Nov 01, 2022
11 Dec 22, 2022
0 Feb 05, 2022
10 Feb 08, 2022
5.1k Jan 04, 2023
3 Dec 29, 2021
0 May 11, 2021
83 Nov 21, 2022
172 Dec 23, 2022
906 Dec 30, 2022
32 Nov 20, 2022
26 Oct 18, 2022
42 Dec 15, 2022
26 Oct 24, 2022
2 Mar 21, 2022
45 Jan 07, 2023
26 Dec 13, 2022