be able to accept non-square patches, thanks to @FilipAndersson245

Add `use_glu` flag to `RvT`

README.md

@@ -38,6 +38,7 @@ preds = v(img) # (1, 1000)
 ```
 
 ## Parameters
+
 - `image_size`: int.  
 Image size. If you have rectangular images, make sure your image size is the maximum of the width and height
 - `patch_size`: int.  
@@ -334,6 +335,47 @@ img = torch.randn(1, 3, 224, 224)
 pred = v(img) # (1, 1000)
 ```
 
+## Twins SVT
+
+<img src="./images/twins_svt.png" width="400px"></img>
+
+This <a href="https://arxiv.org/abs/2104.13840">paper</a> proposes mixing local and global attention, along with position encoding generator (proposed in <a href="https://arxiv.org/abs/2102.10882">CPVT</a>) and global average pooling, to achieve the same results as <a href="https://arxiv.org/abs/2103.14030">Swin</a>, without the extra complexity of shifted windows, CLS tokens, nor positional embeddings.
+
+```python
+import torch
+from vit_pytorch.twins_svt import TwinsSVT
+
+model = TwinsSVT(
+    num_classes = 1000,       # number of output classes
+    s1_emb_dim = 64,          # stage 1 - patch embedding projected dimension
+    s1_patch_size = 4,        # stage 1 - patch size for patch embedding
+    s1_local_patch_size = 7,  # stage 1 - patch size for local attention
+    s1_global_k = 7,          # stage 1 - global attention key / value reduction factor, defaults to 7 as specified in paper
+    s1_depth = 1,             # stage 1 - number of transformer blocks (local attn -> ff -> global attn -> ff)
+    s2_emb_dim = 128,         # stage 2 (same as above)
+    s2_patch_size = 2,
+    s2_local_patch_size = 7,
+    s2_global_k = 7,
+    s2_depth = 1,
+    s3_emb_dim = 256,         # stage 3 (same as above)
+    s3_patch_size = 2,
+    s3_local_patch_size = 7,
+    s3_global_k = 7,
+    s3_depth = 5,
+    s4_emb_dim = 512,         # stage 4 (same as above)
+    s4_patch_size = 2,
+    s4_local_patch_size = 7,
+    s4_global_k = 7,
+    s4_depth = 4,
+    peg_kernel_size = 3,      # positional encoding generator kernel size
+    dropout = 0.              # dropout
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+pred = model(img) # (1, 1000)
+```
+
 ## Masked Patch Prediction
 
 Thanks to <a href="https://github.com/zankner">Zach</a>, you can train using the original masked patch prediction task presented in the paper, with the following code.
@@ -542,6 +584,58 @@ img = torch.randn(1, 3, 224, 224)
 v(img) # (1, 1000)
 ```
 
+## FAQ
+
+- How do I pass in non-square images?
+
+You can already pass in non-square images - you just have to make sure your height and width is less than or equal to the `image_size`, and both divisible by the `patch_size`
+
+ex.
+
+```python
+import torch
+from vit_pytorch import ViT
+
+v = ViT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 256, 128) # <-- not a square
+
+preds = v(img) # (1, 1000)
+```
+
+- How do I pass in non-square patches?
+
+```python
+import torch
+from vit_pytorch import ViT
+
+v = ViT(
+    num_classes = 1000,
+    image_size = (256, 128),  # image size is a tuple of (height, width)
+    patch_size = (32, 16),    # patch size is a tuple of (height, width)
+    dim = 1024,
+    depth = 6,
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 256, 128)
+
+preds = v(img)
+```
+
 ## Resources
 
 Coming from computer vision and new to transformers? Here are some resources that greatly accelerated my learning.
@@ -665,6 +759,17 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{chu2021twins,
+    title   = {Twins: Revisiting Spatial Attention Design in Vision Transformers},
+    author  = {Xiangxiang Chu and Zhi Tian and Yuqing Wang and Bo Zhang and Haibing Ren and Xiaolin Wei and Huaxia Xia and Chunhua Shen},
+    year    = {2021},
+    eprint  = {2104.13840},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 ```bibtex
 @misc{su2021roformer,
     title   = {RoFormer: Enhanced Transformer with Rotary Position Embedding}, 

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.16.9',
+  version = '0.17.3',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',

vit_pytorch/cvt.py

@@ -22,15 +22,25 @@ def group_by_key_prefix_and_remove_prefix(prefix, d):
 
 # classes
 
+class LayerNorm(nn.Module): # layernorm, but done in the channel dimension #1
+    def __init__(self, dim, eps = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
+        self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
+
+    def forward(self, x):
+        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (std + self.eps) * self.g + self.b
+
 class PreNorm(nn.Module):
     def __init__(self, dim, fn):
         super().__init__()
-        self.norm = nn.LayerNorm(dim)
+        self.norm = LayerNorm(dim)
         self.fn = fn
     def forward(self, x, **kwargs):
-        x = rearrange(x, 'b c h w -> b h w c')
         x = self.norm(x)
-        x = rearrange(x, 'b h w c -> b c h w')
         return self.fn(x, **kwargs)
 
 class FeedForward(nn.Module):
@@ -67,8 +77,8 @@ class Attention(nn.Module):
 
         self.attend = nn.Softmax(dim = -1)
 
-        self.to_q = DepthWiseConv2d(dim, inner_dim, 3, padding = padding, stride = 1, bias = False)
-        self.to_kv = DepthWiseConv2d(dim, inner_dim * 2, 3, padding = padding, stride = kv_proj_stride, bias = False)
+        self.to_q = DepthWiseConv2d(dim, inner_dim, proj_kernel, padding = padding, stride = 1, bias = False)
+        self.to_kv = DepthWiseConv2d(dim, inner_dim * 2, proj_kernel, padding = padding, stride = kv_proj_stride, bias = False)
 
         self.to_out = nn.Sequential(
             nn.Conv2d(inner_dim, dim, 1),
@@ -130,7 +140,7 @@ class CvT(nn.Module):
         s3_emb_stride = 2,
         s3_proj_kernel = 3,
         s3_kv_proj_stride = 2,
-        s3_heads = 4,
+        s3_heads = 6,
         s3_depth = 10,
         s3_mlp_mult = 4,
         dropout = 0.
@@ -146,6 +156,7 @@ class CvT(nn.Module):
 
             layers.append(nn.Sequential(
                 nn.Conv2d(dim, config['emb_dim'], kernel_size = config['emb_kernel'], padding = (config['emb_kernel'] // 2), stride = config['emb_stride']),
+                LayerNorm(config['emb_dim']),
                 Transformer(dim = config['emb_dim'], proj_kernel = config['proj_kernel'], kv_proj_stride = config['kv_proj_stride'], depth = config['depth'], heads = config['heads'], mlp_mult = config['mlp_mult'], dropout = dropout)
             ))
 

vit_pytorch/levit.py

@@ -53,10 +53,13 @@ class Attention(nn.Module):
 
         self.attend = nn.Softmax(dim = -1)
 
+        out_batch_norm = nn.BatchNorm2d(dim_out)
+        nn.init.zeros_(out_batch_norm.weight)
+
         self.to_out = nn.Sequential(
             nn.GELU(),
             nn.Conv2d(inner_dim_value, dim_out, 1),
-            nn.BatchNorm2d(dim_out),
+            out_batch_norm,
             nn.Dropout(dropout)
         )
 

vit_pytorch/pit.py

@@ -89,8 +89,8 @@ class DepthWiseConv2d(nn.Module):
     def __init__(self, dim_in, dim_out, kernel_size, padding, stride, bias = True):
         super().__init__()
         self.net = nn.Sequential(
-            nn.Conv2d(dim_in, dim_in, kernel_size = kernel_size, padding = padding, groups = dim_in, stride = stride, bias = bias),
-            nn.Conv2d(dim_in, dim_out, kernel_size = 1, bias = bias)
+            nn.Conv2d(dim_in, dim_out, kernel_size = kernel_size, padding = padding, groups = dim_in, stride = stride, bias = bias),
+            nn.Conv2d(dim_out, dim_out, kernel_size = 1, bias = bias)
         )
     def forward(self, x):
         return self.net(x)

vit_pytorch/rvt.py

@@ -83,11 +83,11 @@ class GEGLU(nn.Module):
         return F.gelu(gates) * x
 
 class FeedForward(nn.Module):
-    def __init__(self, dim, hidden_dim, dropout = 0.):
+    def __init__(self, dim, hidden_dim, dropout = 0., use_glu = True):
         super().__init__()
         self.net = nn.Sequential(
-            nn.Linear(dim, hidden_dim * 2),
-            GEGLU(),
+            nn.Linear(dim, hidden_dim * 2 if use_glu else hidden_dim),
+            GEGLU() if use_glu else nn.GELU(),
             nn.Dropout(dropout),
             nn.Linear(hidden_dim, dim),
             nn.Dropout(dropout)
@@ -119,7 +119,8 @@ class Attention(nn.Module):
     def forward(self, x, pos_emb, fmap_dims):
         b, n, _, h = *x.shape, self.heads
 
-        q = self.to_q(x, fmap_dims = fmap_dims) if self.use_ds_conv else self.to_q(x)
+        to_q_kwargs = {'fmap_dims': fmap_dims} if self.use_ds_conv else {}
+        q = self.to_q(x, **to_q_kwargs)
 
         qkv = (q, *self.to_kv(x).chunk(2, dim = -1))
 
@@ -153,14 +154,14 @@ class Attention(nn.Module):
         return self.to_out(out)
 
 class Transformer(nn.Module):
-    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0., use_rotary = True, use_ds_conv = True):
+    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0., use_rotary = True, use_ds_conv = True, use_glu = True):
         super().__init__()
         self.layers = nn.ModuleList([])
         self.pos_emb = AxialRotaryEmbedding(dim_head)
         for _ in range(depth):
             self.layers.append(nn.ModuleList([
                 PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout, use_rotary = use_rotary, use_ds_conv = use_ds_conv)),
-                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
+                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout, use_glu = use_glu))
             ]))
     def forward(self, x, fmap_dims):
         pos_emb = self.pos_emb(x[:, 1:])
@@ -173,7 +174,7 @@ class Transformer(nn.Module):
 # Rotary Vision Transformer
 
 class RvT(nn.Module):
-    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0., use_rotary = True, use_ds_conv = True):
+    def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0., use_rotary = True, use_ds_conv = True, use_glu = True):
         super().__init__()
         assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
         num_patches = (image_size // patch_size) ** 2
@@ -186,7 +187,7 @@ class RvT(nn.Module):
         )
 
         self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
-        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout, use_rotary, use_ds_conv)
+        self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout, use_rotary, use_ds_conv, use_glu)
 
         self.mlp_head = nn.Sequential(
             nn.LayerNorm(dim),

vit_pytorch/twins_svt.py

@@ -0,0 +1,229 @@
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helper methods
+
+def group_dict_by_key(cond, d):
+    return_val = [dict(), dict()]
+    for key in d.keys():
+        match = bool(cond(key))
+        ind = int(not match)
+        return_val[ind][key] = d[key]
+    return (*return_val,)
+
+def group_by_key_prefix_and_remove_prefix(prefix, d):
+    kwargs_with_prefix, kwargs = group_dict_by_key(lambda x: x.startswith(prefix), d)
+    kwargs_without_prefix = dict(map(lambda x: (x[0][len(prefix):], x[1]), tuple(kwargs_with_prefix.items())))
+    return kwargs_without_prefix, kwargs
+
+# classes
+
+class Residual(nn.Module):
+    def __init__(self, fn):
+        super().__init__()
+        self.fn = fn
+
+    def forward(self, x, **kwargs):
+        return self.fn(x, **kwargs) + x
+
+class LayerNorm(nn.Module):
+    def __init__(self, dim, eps = 1e-5):
+        super().__init__()
+        self.eps = eps
+        self.g = nn.Parameter(torch.ones(1, dim, 1, 1))
+        self.b = nn.Parameter(torch.zeros(1, dim, 1, 1))
+
+    def forward(self, x):
+        std = torch.var(x, dim = 1, unbiased = False, keepdim = True).sqrt()
+        mean = torch.mean(x, dim = 1, keepdim = True)
+        return (x - mean) / (std + self.eps) * self.g + self.b
+
+class PreNorm(nn.Module):
+    def __init__(self, dim, fn):
+        super().__init__()
+        self.norm = LayerNorm(dim)
+        self.fn = fn
+
+    def forward(self, x, **kwargs):
+        x = self.norm(x)
+        return self.fn(x, **kwargs)
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, mult = 4, dropout = 0.):
+        super().__init__()
+        self.net = nn.Sequential(
+            nn.Conv2d(dim, dim * mult, 1),
+            nn.GELU(),
+            nn.Dropout(dropout),
+            nn.Conv2d(dim * mult, dim, 1),
+            nn.Dropout(dropout)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+class PatchEmbedding(nn.Module):
+    def __init__(self, *, dim, dim_out, patch_size):
+        super().__init__()
+        self.dim = dim
+        self.dim_out = dim_out
+        self.patch_size = patch_size
+        self.proj = nn.Conv2d(patch_size ** 2 * dim, dim_out, 1)
+
+    def forward(self, fmap):
+        p = self.patch_size
+        fmap = rearrange(fmap, 'b c (h p1) (w p2) -> b (c p1 p2) h w', p1 = p, p2 = p)
+        return self.proj(fmap)
+
+class PEG(nn.Module):
+    def __init__(self, dim, kernel_size = 3):
+        super().__init__()
+        self.proj = Residual(nn.Conv2d(dim, dim, kernel_size = kernel_size, padding = kernel_size // 2, groups = dim, stride = 1))
+
+    def forward(self, x):
+        return self.proj(x)
+
+class LocalAttention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0., patch_size = 7):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.patch_size = patch_size
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.to_q = nn.Conv2d(dim, inner_dim, 1, bias = False)
+        self.to_kv = nn.Conv2d(dim, inner_dim * 2, 1, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, fmap):
+        shape, p = fmap.shape, self.patch_size
+        b, n, x, y, h = *shape, self.heads
+        x, y = map(lambda t: t // p, (x, y))
+
+        fmap = rearrange(fmap, 'b c (x p1) (y p2) -> (b x y) c p1 p2', p1 = p, p2 = p)
+
+        q, k, v = (self.to_q(fmap), *self.to_kv(fmap).chunk(2, dim = 1))
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) p1 p2 -> (b h) (p1 p2) d', h = h), (q, k, v))
+
+        dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
+
+        attn = dots.softmax(dim = - 1)
+
+        out = einsum('b i j, b j d -> b i d', attn, v)
+        out = rearrange(out, '(b x y h) (p1 p2) d -> b (h d) (x p1) (y p2)', h = h, x = x, y = y, p1 = p, p2 = p)
+        return self.to_out(out)
+
+class GlobalAttention(nn.Module):
+    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0., k = 7):
+        super().__init__()
+        inner_dim = dim_head *  heads
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.to_q = nn.Conv2d(dim, inner_dim, 1, bias = False)
+        self.to_kv = nn.Conv2d(dim, inner_dim * 2, k, stride = k, bias = False)
+
+        self.to_out = nn.Sequential(
+            nn.Conv2d(inner_dim, dim, 1),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x):
+        shape = x.shape
+        b, n, _, y, h = *shape, self.heads
+        q, k, v = (self.to_q(x), *self.to_kv(x).chunk(2, dim = 1))
+
+        q, k, v = map(lambda t: rearrange(t, 'b (h d) x y -> (b h) (x y) d', h = h), (q, k, v))
+
+        dots = einsum('b i d, b j d -> b i j', q, k) * self.scale
+
+        attn = dots.softmax(dim = -1)
+
+        out = einsum('b i j, b j d -> b i d', attn, v)
+        out = rearrange(out, '(b h) (x y) d -> b (h d) x y', h = h, y = y)
+        return self.to_out(out)
+
+class Transformer(nn.Module):
+    def __init__(self, dim, depth, heads = 8, dim_head = 64, mlp_mult = 4, local_patch_size = 7, global_k = 7, dropout = 0., has_local = True):
+        super().__init__()
+        self.layers = nn.ModuleList([])
+        for _ in range(depth):
+            self.layers.append(nn.ModuleList([
+                Residual(PreNorm(dim, LocalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, patch_size = local_patch_size))) if has_local else nn.Identity(),
+                Residual(PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout))) if has_local else nn.Identity(),
+                Residual(PreNorm(dim, GlobalAttention(dim, heads = heads, dim_head = dim_head, dropout = dropout, k = global_k))),
+                Residual(PreNorm(dim, FeedForward(dim, mlp_mult, dropout = dropout)))
+            ]))
+    def forward(self, x):
+        for local_attn, ff1, global_attn, ff2 in self.layers:
+            x = local_attn(x)
+            x = ff1(x)
+            x = global_attn(x)
+            x = ff2(x)
+        return x
+
+class TwinsSVT(nn.Module):
+    def __init__(
+        self,
+        *,
+        num_classes,
+        s1_emb_dim = 64,
+        s1_patch_size = 4,
+        s1_local_patch_size = 7,
+        s1_global_k = 7,
+        s1_depth = 1,
+        s2_emb_dim = 128,
+        s2_patch_size = 2,
+        s2_local_patch_size = 7,
+        s2_global_k = 7,
+        s2_depth = 1,
+        s3_emb_dim = 256,
+        s3_patch_size = 2,
+        s3_local_patch_size = 7,
+        s3_global_k = 7,
+        s3_depth = 5,
+        s4_emb_dim = 512,
+        s4_patch_size = 2,
+        s4_local_patch_size = 7,
+        s4_global_k = 7,
+        s4_depth = 4,
+        peg_kernel_size = 3,
+        dropout = 0.
+    ):
+        super().__init__()
+        kwargs = dict(locals())
+
+        dim = 3
+        layers = []
+
+        for prefix in ('s1', 's2', 's3', 's4'):
+            config, kwargs = group_by_key_prefix_and_remove_prefix(f'{prefix}_', kwargs)
+            is_last = prefix == 's4'
+
+            dim_next = config['emb_dim']
+
+            layers.append(nn.Sequential(
+                PatchEmbedding(dim = dim, dim_out = dim_next, patch_size = config['patch_size']),
+                Transformer(dim = dim_next, depth = 1, local_patch_size = config['local_patch_size'], global_k = config['global_k'], dropout = dropout, has_local = not is_last),
+                PEG(dim = dim_next, kernel_size = peg_kernel_size),
+                Transformer(dim = dim_next, depth = config['depth'],  local_patch_size = config['local_patch_size'], global_k = config['global_k'], dropout = dropout, has_local = not is_last)
+            ))
+
+            dim = dim_next
+
+        self.layers = nn.Sequential(
+            *layers,
+            nn.AdaptiveAvgPool2d(1),
+            Rearrange('... () () -> ...'),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, x):
+        return self.layers(x)

vit_pytorch/vit.py

@@ -5,6 +5,13 @@ import torch.nn.functional as F
 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__()
@@ -74,13 +81,17 @@ class Transformer(nn.Module):
 class ViT(nn.Module):
     def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
         super().__init__()
-        assert image_size % patch_size == 0, 'Image dimensions must be divisible by the patch size.'
-        num_patches = (image_size // patch_size) ** 2
-        patch_dim = channels * patch_size ** 2
+        image_height, image_width = pair(image_size)
+        patch_height, patch_width = pair(patch_size)
+
+        assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
+
+        num_patches = (image_height // patch_height) * (image_width // patch_width)
+        patch_dim = channels * patch_height * patch_width
         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 (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_size, p2 = patch_size),
+            Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
             nn.Linear(patch_dim, dim),
         )