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
230 Jan 05, 2023
34 Dec 13, 2022
10 Sep 28, 2022
25 Dec 16, 2022
80 Dec 13, 2022
54 Dec 30, 2022
57 Dec 15, 2022
188 Dec 25, 2022
2 Oct 20, 2022
18 May 24, 2022
32 Oct 18, 2022
309 Dec 12, 2022
934 Dec 30, 2022
7 Nov 26, 2022
357 Jan 06, 2023
145 Dec 24, 2022
619 Jan 03, 2023
146 Dec 25, 2022
9 Feb 15, 2022
3 Oct 31, 2022