add vivit

Signed-off-by: Ryan Russell <git@ryanrussell.org>

Signed-off-by: Ryan Russell <git@ryanrussell.org>

README.md

@@ -664,7 +664,7 @@ preds = v(img) # (2, 1000)
 
 <img src="./images/nest.png" width="400px"></img>
 
-This <a href="https://arxiv.org/abs/2105.12723">paper</a> decided to process the image in hierarchical stages, with attention only within tokens of local blocks, which aggregate as it moves up the heirarchy. The aggregation is done in the image plane, and contains a convolution and subsequent maxpool to allow it to pass information across the boundary.
+This <a href="https://arxiv.org/abs/2105.12723">paper</a> decided to process the image in hierarchical stages, with attention only within tokens of local blocks, which aggregate as it moves up the hierarchy. The aggregation is done in the image plane, and contains a convolution and subsequent maxpool to allow it to pass information across the boundary.
 
 You can use it with the following code (ex. NesT-T)
 
@@ -678,7 +678,7 @@ nest = NesT(
     dim = 96,
     heads = 3,
     num_hierarchies = 3,        # number of hierarchies
-    block_repeats = (2, 2, 8),  # the number of transformer blocks at each heirarchy, starting from the bottom
+    block_repeats = (2, 2, 8),  # the number of transformer blocks at each hierarchy, starting from the bottom
     num_classes = 1000
 )
 
@@ -1022,6 +1022,34 @@ video = torch.randn(4, 3, 16, 128, 128) # (batch, channels, frames, height, widt
 preds = v(video) # (4, 1000)
 ```
 
+## ViViT
+
+<img src="./images/vivit.png" width="350px"></img>
+
+This <a href="https://arxiv.org/abs/2103.15691">paper</a> offers 3 different types of architectures for efficient attention of videos, with the main theme being factorizing the attention across space and time. This repository will offer the first variant, which is a spatial transformer followed by a temporal one.
+
+```python
+import torch
+from vit_pytorch.vivit import ViT
+
+v = ViT(
+    image_size = 128,          # image size
+    frames = 16,               # number of frames
+    image_patch_size = 16,     # image patch size
+    frame_patch_size = 2,      # frame patch size
+    num_classes = 1000,
+    dim = 1024,
+    spatial_depth = 6,         # depth of the spatial transformer
+    temporal_depth = 6,        # depth of the temporal transformer
+    heads = 8,
+    mlp_dim = 2048
+)
+
+video = torch.randn(4, 3, 16, 128, 128) # (batch, channels, frames, height, width)
+
+preds = v(video) # (4, 1000)
+```
+
 ## Parallel ViT
 
 <img src="./images/parallel-vit.png" width="350px"></img>
@@ -1805,6 +1833,16 @@ Coming from computer vision and new to transformers? Here are some resources tha
 
 ```
 
+```bibtex
+@article{Arnab2021ViViTAV,
+    title   = {ViViT: A Video Vision Transformer},
+    author  = {Anurag Arnab and Mostafa Dehghani and Georg Heigold and Chen Sun and Mario Lucic and Cordelia Schmid},
+    journal = {2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
+    year    = {2021},
+    pages   = {6816-6826}
+}
+```
+
 ```bibtex
 @misc{vaswani2017attention,
     title   = {Attention Is All You Need},

examples/cats_and_dogs.ipynb

@@ -16,7 +16,7 @@
     "\n",
     "* Dogs vs. Cats Redux: Kernels Edition - https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition\n",
     "* Base Code - https://www.kaggle.com/reukki/pytorch-cnn-tutorial-with-cats-and-dogs/\n",
-    "* Effecient Attention Implementation - https://github.com/lucidrains/vit-pytorch#efficient-attention"
+    "* Efficient Attention Implementation - https://github.com/lucidrains/vit-pytorch#efficient-attention"
    ]
   },
   {
@@ -342,7 +342,7 @@
     "id": "ZhYDJXk2SRDu"
    },
    "source": [
-    "## Image Augumentation"
+    "## Image Augmentation"
    ]
   },
   {
@@ -497,7 +497,7 @@
     "id": "TF9yMaRrSvmv"
    },
    "source": [
-    "## Effecient Attention"
+    "## Efficient Attention"
    ]
   },
   {
@@ -1307,7 +1307,7 @@
   "celltoolbar": "Edit Metadata",
   "colab": {
    "collapsed_sections": [],
-   "name": "Effecient Attention | Cats & Dogs",
+   "name": "Efficient Attention | Cats & Dogs",
    "provenance": [],
    "toc_visible": true
   },

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.36.2',
+  version = '0.37.0',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   long_description_content_type = 'text/markdown',

vit_pytorch/mobile_vit.py

@@ -13,9 +13,9 @@ def conv_1x1_bn(inp, oup):
         nn.SiLU()
     )
 
-def conv_nxn_bn(inp, oup, kernal_size=3, stride=1):
+def conv_nxn_bn(inp, oup, kernel_size=3, stride=1):
     return nn.Sequential(
-        nn.Conv2d(inp, oup, kernal_size, stride, 1, bias=False),
+        nn.Conv2d(inp, oup, kernel_size, stride, 1, bias=False),
         nn.BatchNorm2d(oup),
         nn.SiLU()
     )

vit_pytorch/nest.py

@@ -131,7 +131,7 @@ class NesT(nn.Module):
         fmap_size = image_size // patch_size
         blocks = 2 ** (num_hierarchies - 1)
 
-        seq_len = (fmap_size // blocks) ** 2   # sequence length is held constant across heirarchy
+        seq_len = (fmap_size // blocks) ** 2   # sequence length is held constant across hierarchy
         hierarchies = list(reversed(range(num_hierarchies)))
         mults = [2 ** i for i in reversed(hierarchies)]
 

vit_pytorch/vivit.py

@@ -0,0 +1,169 @@
+import torch
+from torch import nn
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def pair(t):
+    return t if isinstance(t, tuple) else (t, t)
+
+# classes
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = nn.LayerNorm(dim)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(self.norm(x), **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, hidden_dim, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Linear(dim, hidden_dim),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Linear(hidden_dim, dim),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class Attention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        project_out = not (heads == 1 and dim_head == dim)
+
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.attend = nn.Softmax(dim = -1)
+        self.dropout = nn.Dropout(dropout)
+
+        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        ) if project_out else nn.Identity()
+
+    def forward(self, x):
+        qkv = self.to_qkv(x).chunk(3, dim = -1)
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)
+
+        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
+
+        attn = self.attend(dots)
+        attn = self.dropout(attn)
+
+        out = torch.matmul(attn, v)
+        out = rearrange(out, 'b h n d -> b n (h d)')
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+            ]))
+    def forward(self, x):
+        for attn, ff in self.layers:
+            x = attn(x) + x
+            x = ff(x) + x
+        return x
+
+class ViT(nn.Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        image_patch_size,
+        frames,
+        frame_patch_size,
+        num_classes,
+        dim,
+        spatial_depth,
+        temporal_depth,
+        heads,
+        mlp_dim,
+        pool = 'cls',
+        channels = 3,
+        dim_head = 64,
+        dropout = 0.,
+        emb_dropout = 0.
+    ):
+        super().__init__()
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(image_patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+        assert frames % frame_patch_size == 0, 'Frames must be divisible by frame patch size'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width) * (frames // frame_patch_size)
+        patch_dim = channels * patch_height * patch_width * frame_patch_size
+
+        assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
+
+        self.to_patch_embedding = nn.Sequential(
+            Rearrange('b c (f pf) (h p1) (w p2) -> b f (h w) (p1 p2 pf c)', p1 = patch_height, p2 = patch_width, pf = frame_patch_size),
+            nn.Linear(patch_dim, dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+        self.spatial_cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.temporal_cls_token = nn.Parameter(torch.randn(1, 1, dim))
+
+        self.spatial_transformer = Transformer(dim, spatial_depth, heads, dim_head, mlp_dim, dropout)
+        self.temporal_transformer = Transformer(dim, temporal_depth, heads, dim_head, mlp_dim, dropout)
+
+        self.pool = pool
+        self.to_latent = nn.Identity()
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, f, n, _ = x.shape
+
+        spatial_cls_tokens = repeat(self.spatial_cls_token, '1 1 d -> b f 1 d', b = b, f = f)
+        x = torch.cat((spatial_cls_tokens, x), dim = 2)
+        x += self.pos_embedding[:, :(n + 1)]
+        x = self.dropout(x)
+
+        x = rearrange(x, 'b f n d -> (b f) n d')
+
+        # attend across space
+
+        x = self.spatial_transformer(x)
+
+        x = rearrange(x, '(b f) n d -> b f n d', b = b)
+
+        # excise out the spatial cls tokens for temporal attention
+
+        x = x[:, :, 0]
+
+        # append temporal CLS tokens
+
+        temporal_cls_tokens = repeat(self.temporal_cls_token, '1 1 d-> b 1 d', b = b)
+
+        x = torch.cat((temporal_cls_tokens, x), dim = 1)
+
+        # attend across time
+
+        x = self.temporal_transformer(x)
+
+        x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
+
+        x = self.to_latent(x)
+        return self.mlp_head(x)