offer hard distillation as well

README.md

@@ -93,7 +93,8 @@ distiller = DistillWrapper(
     student = v,
     teacher = teacher,
     temperature = 3,           # temperature of distillation
-    alpha = 0.5                # trade between main loss and distillation loss
+    alpha = 0.5,               # trade between main loss and distillation loss
+    hard = False               # whether to use soft or hard distillation
 )
 
 img = torch.randn(2, 3, 256, 256)
@@ -143,6 +144,36 @@ img = torch.randn(1, 3, 256, 256)
 preds = v(img) # (1, 1000)
 ```
 
+## CaiT
+
+<a href="https://arxiv.org/abs/2103.17239">This paper</a> also notes difficulty in training vision transformers at greater depths and proposes two solutions. First it proposes to do per-channel multiplication of the output of the residual block. Second, it proposes to have the patches attend to one another, and only allow the CLS token to attend to the patches in the last few layers.
+
+They also add <a href="https://github.com/lucidrains/x-transformers#talking-heads-attention">Talking Heads</a>, noting improvements
+
+You can use this scheme as follows
+
+```python
+import torch
+from vit_pytorch.cait import CaiT
+
+v = CaiT(
+    image_size = 256,
+    patch_size = 32,
+    num_classes = 1000,
+    dim = 1024,
+    depth = 12,         # depth of transformer for patch to patch attention only
+    cls_depth = 2,      # depth of cross attention of CLS tokens to patch
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+preds = v(img) # (1, 1000)
+```
+
 ## Token-to-Token ViT
 
 <img src="./images/t2t.png" width="400px"></img>
@@ -164,7 +195,116 @@ v = T2TViT(
 )
 
 img = torch.randn(1, 3, 224, 224)
-v(img) # (1, 1000)
+
+preds = v(img) # (1, 1000)
+```
+
+## Cross ViT
+
+<img src="./images/cross_vit.png" width="400px"></img>
+
+<a href="https://arxiv.org/abs/2103.14899">This paper</a> proposes to have two vision transformers processing the image at different scales, cross attending to one every so often. They show improvements on top of the base vision transformer.
+
+```python
+import torch
+from vit_pytorch.cross_vit import CrossViT
+
+v = CrossViT(
+    image_size = 256,
+    num_classes = 1000,
+    depth = 4,               # number of multi-scale encoding blocks
+    sm_dim = 192,            # high res dimension
+    sm_patch_size = 16,      # high res patch size (should be smaller than lg_patch_size)
+    sm_enc_depth = 2,        # high res depth
+    sm_enc_heads = 8,        # high res heads
+    sm_enc_mlp_dim = 2048,   # high res feedforward dimension
+    lg_dim = 384,            # low res dimension
+    lg_patch_size = 64,      # low res patch size
+    lg_enc_depth = 3,        # low res depth
+    lg_enc_heads = 8,        # low res heads
+    lg_enc_mlp_dim = 2048,   # low res feedforward dimensions
+    cross_attn_depth = 2,    # cross attention rounds
+    cross_attn_heads = 8,    # cross attention heads
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+img = torch.randn(1, 3, 256, 256)
+
+pred = v(img) # (1, 1000)
+```
+
+## PiT
+
+<img src="./images/pit.png" width="400px"></img>
+
+<a href="https://arxiv.org/abs/2103.16302">This paper</a> proposes to downsample the tokens through a pooling procedure using depth-wise convolutions.
+
+```python
+import torch
+from vit_pytorch.pit import PiT
+
+v = PiT(
+    image_size = 224,
+    patch_size = 14,
+    dim = 256,
+    num_classes = 1000,
+    depth = (3, 3, 3),     # list of depths, indicating the number of rounds of each stage before a downsample
+    heads = 16,
+    mlp_dim = 2048,
+    dropout = 0.1,
+    emb_dropout = 0.1
+)
+
+# forward pass now returns predictions and the attention maps
+
+img = torch.randn(1, 3, 224, 224)
+
+preds = v(img) # (1, 1000)
+```
+
+## CvT
+
+<img src="./images/cvt.png" width="400px"></img>
+
+<a href="https://arxiv.org/abs/2103.15808">This paper</a> proposes mixing convolutions and attention. Specifically, convolutions are used to embed and downsample the image / feature map in three stages. Depthwise-convoltion is also used to project the queries, keys, and values for attention.
+
+```python
+import torch
+from vit_pytorch.cvt import CvT
+
+v = CvT(
+    num_classes = 1000,
+    s1_emb_dim = 64,        # stage 1 - dimension
+    s1_emb_kernel = 7,      # stage 1 - conv kernel
+    s1_emb_stride = 4,      # stage 1 - conv stride
+    s1_proj_kernel = 3,     # stage 1 - attention ds-conv kernel size
+    s1_kv_proj_stride = 2,  # stage 1 - attention key / value projection stride
+    s1_heads = 1,           # stage 1 - heads
+    s1_depth = 1,           # stage 1 - depth
+    s1_mlp_mult = 4,        # stage 1 - feedforward expansion factor
+    s2_emb_dim = 192,       # stage 2 - (same as above)
+    s2_emb_kernel = 3,
+    s2_emb_stride = 2,
+    s2_proj_kernel = 3,
+    s2_kv_proj_stride = 2,
+    s2_heads = 3,
+    s2_depth = 2,
+    s2_mlp_mult = 4,
+    s3_emb_dim = 384,       # stage 3 - (same as above)
+    s3_emb_kernel = 3,
+    s3_emb_stride = 2,
+    s3_proj_kernel = 3,
+    s3_kv_proj_stride = 2,
+    s3_heads = 4,
+    s3_depth = 10,
+    s3_mlp_mult = 4,
+    dropout = 0.
+)
+
+img = torch.randn(1, 3, 224, 224)
+
+pred = v(img) # (1, 1000)
 ```
 
 ## Masked Patch Prediction
@@ -432,6 +572,17 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{touvron2021going,
+    title   = {Going deeper with Image Transformers}, 
+    author  = {Hugo Touvron and Matthieu Cord and Alexandre Sablayrolles and Gabriel Synnaeve and Hervé Jégou},
+    year    = {2021},
+    eprint  = {2103.17239},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 ```bibtex
 @misc{chen2021crossvit,
     title   = {CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification},
@@ -454,6 +605,17 @@ Coming from computer vision and new to transformers? Here are some resources tha
 }
 ```
 
+```bibtex
+@misc{heo2021rethinking,
+    title   = {Rethinking Spatial Dimensions of Vision Transformers}, 
+    author  = {Byeongho Heo and Sangdoo Yun and Dongyoon Han and Sanghyuk Chun and Junsuk Choe and Seong Joon Oh},
+    year    = {2021},
+    eprint  = {2103.16302},
+    archivePrefix = {arXiv},
+    primaryClass = {cs.CV}
+}
+```
+
 ```bibtex
 @misc{vaswani2017attention,
     title   = {Attention Is All You Need},

setup.py

@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
   name = 'vit-pytorch',
   packages = find_packages(exclude=['examples']),
-  version = '0.11.0',
+  version = '0.14.3',
   license='MIT',
   description = 'Vision Transformer (ViT) - Pytorch',
   author = 'Phil Wang',

vit_pytorch/cait.py

@@ -0,0 +1,155 @@
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def exists(val):
+    return val is not None
+
+# classes
+
+class LayerScale(nn.Module):
+    def __init__(self, dim, fn, depth):
+        super().__init__()
+        if depth <= 18:  # epsilon detailed in section 2 of paper
+            init_eps = 0.1
+        elif depth > 18 and depth <= 24:
+            init_eps = 1e-5
+        else:
+            init_eps = 1e-6
+
+        scale = torch.zeros(1, 1, dim).fill_(init_eps)
+        self.scale = nn.Parameter(scale)
+        self.fn = fn
+    def forward(self, x, **kwargs):
+        return self.fn(x, **kwargs) * self.scale
+
+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
+        self.heads = heads
+        self.scale = dim_head ** -0.5
+
+        self.to_q = nn.Linear(dim, inner_dim, bias = False)
+        self.to_kv = nn.Linear(dim, inner_dim * 2, bias = False)
+
+        self.attend = nn.Softmax(dim = -1)
+
+        self.mix_heads_pre_attn = nn.Parameter(torch.randn(heads, heads))
+        self.mix_heads_post_attn = nn.Parameter(torch.randn(heads, heads))
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, dim),
+            nn.Dropout(dropout)
+        )
+
+    def forward(self, x, context = None):
+        b, n, _, h = *x.shape, self.heads
+
+        context = x if not exists(context) else torch.cat((x, context), dim = 1)
+
+        qkv = (self.to_q(x), *self.to_kv(context).chunk(2, dim = -1))
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
+
+        dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
+
+        dots = einsum('b h i j, h g -> b g i j', dots, self.mix_heads_pre_attn)    # talking heads, pre-softmax
+        attn = self.attend(dots)
+        attn = einsum('b h i j, h g -> b g i j', attn, self.mix_heads_post_attn)   # talking heads, post-softmax
+
+        out = einsum('b h i j, b h j d -> b h i d', 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 ind in range(depth):
+            self.layers.append(nn.ModuleList([
+                LayerScale(dim, PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)), depth = ind + 1),
+                LayerScale(dim, PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout)), depth = ind + 1)
+            ]))
+    def forward(self, x, context = None):
+        for attn, ff in self.layers:
+            x = attn(x, context = context) + x
+            x = ff(x) + x
+        return x
+
+class CaiT(nn.Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        patch_size,
+        num_classes,
+        dim,
+        depth,
+        cls_depth,
+        heads,
+        mlp_dim,
+        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 = 3 * patch_size ** 2
+
+        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),
+            nn.Linear(patch_dim, dim),
+        )
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        self.patch_transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
+        self.cls_transformer = Transformer(dim, cls_depth, heads, dim_head, mlp_dim, dropout)
+
+        self.mlp_head = nn.Sequential(
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        x += self.pos_embedding[:, :n]
+        x = self.dropout(x)
+
+        x = self.patch_transformer(x)
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = self.cls_transformer(cls_tokens, context = x)
+
+        return self.mlp_head(x[:, 0])

vit_pytorch/cvt.py

@@ -46,6 +46,17 @@ class FeedForward(nn.Module):
     def forward(self, x):
         return self.net(x)
 
+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.BatchNorm2d(dim_in),
+            nn.Conv2d(dim_in, dim_out, kernel_size = 1, bias = bias)
+        )
+    def forward(self, x):
+        return self.net(x)
+
 class Attention(nn.Module):
     def __init__(self, dim, proj_kernel, kv_proj_stride, heads = 8, dim_head = 64, dropout = 0.):
         super().__init__()
@@ -56,8 +67,8 @@ class Attention(nn.Module):
 
         self.attend = nn.Softmax(dim = -1)
 
-        self.to_q = nn.Conv2d(dim, inner_dim, 3, padding = padding, stride = 1, bias = False)
-        self.to_kv = nn.Conv2d(dim, inner_dim * 2, 3, padding = padding, stride = kv_proj_stride, bias = False)
+        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_out = nn.Sequential(
             nn.Conv2d(inner_dim, dim, 1),

vit_pytorch/distill.py

@@ -104,7 +104,8 @@ class DistillWrapper(nn.Module):
         teacher,
         student,
         temperature = 1.,
-        alpha = 0.5
+        alpha = 0.5,
+        hard = False
     ):
         super().__init__()
         assert (isinstance(student, (DistillableViT, DistillableT2TViT, DistillableEfficientViT))) , 'student must be a vision transformer'
@@ -116,6 +117,7 @@ class DistillWrapper(nn.Module):
         num_classes = student.num_classes
         self.temperature = temperature
         self.alpha = alpha
+        self.hard = hard
 
         self.distillation_token = nn.Parameter(torch.randn(1, 1, dim))
 
@@ -137,11 +139,15 @@ class DistillWrapper(nn.Module):
 
         loss = F.cross_entropy(student_logits, labels)
 
-        distill_loss = F.kl_div(
-            F.log_softmax(distill_logits / T, dim = -1),
-            F.softmax(teacher_logits / T, dim = -1).detach(),
-        reduction = 'batchmean')
+        if not self.hard:
+            distill_loss = F.kl_div(
+                F.log_softmax(distill_logits / T, dim = -1),
+                F.softmax(teacher_logits / T, dim = -1).detach(),
+            reduction = 'batchmean')
+
+        else:
+            teacher_labels = teacher_logits.argmax(dim = -1)
+            distill_loss = F.cross_entropy(student_logits, teacher_labels)
 
         distill_loss *= T ** 2
-
         return loss * alpha + distill_loss * (1 - alpha)

vit_pytorch/pit.py

@@ -0,0 +1,180 @@
+from math import sqrt
+
+import torch
+from torch import nn, einsum
+import torch.nn.functional as F
+
+from einops import rearrange, repeat
+from einops.layers.torch import Rearrange
+
+# helpers
+
+def cast_tuple(val, num):
+    return val if isinstance(val, tuple) else (val,) * num
+
+def conv_output_size(image_size, kernel_size, stride, padding = 0):
+    return int(((image_size - kernel_size + (2 * padding)) / stride) + 1)
+
+# 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.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):
+        b, n, _, h = *x.shape, self.heads
+        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 = h), qkv)
+
+        dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
+
+        attn = self.attend(dots)
+
+        out = einsum('b h i j, b h j d -> b h i d', 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
+
+# depthwise convolution, for pooling
+
+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)
+        )
+    def forward(self, x):
+        return self.net(x)
+
+# pooling layer
+
+class Pool(nn.Module):
+    def __init__(self, dim):
+        super().__init__()
+        self.downsample = DepthWiseConv2d(dim, dim * 2, kernel_size = 3, stride = 2, padding = 1)
+        self.cls_ff = nn.Linear(dim, dim * 2)
+
+    def forward(self, x):
+        cls_token, tokens = x[:, :1], x[:, 1:]
+
+        cls_token = self.cls_ff(cls_token)
+
+        tokens = rearrange(tokens, 'b (h w) c -> b c h w', h = int(sqrt(tokens.shape[1])))
+        tokens = self.downsample(tokens)
+        tokens = rearrange(tokens, 'b c h w -> b (h w) c')
+
+        return torch.cat((cls_token, tokens), dim = 1)
+
+# main class
+
+class PiT(nn.Module):
+    def __init__(
+        self,
+        *,
+        image_size,
+        patch_size,
+        num_classes,
+        dim,
+        depth,
+        heads,
+        mlp_dim,
+        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.'
+        assert isinstance(depth, tuple), 'depth must be a tuple of integers, specifying the number of blocks before each downsizing'
+        heads = cast_tuple(heads, len(depth))
+
+        patch_dim = 3 * patch_size ** 2
+
+        self.to_patch_embedding = nn.Sequential(
+            nn.Unfold(kernel_size = patch_size, stride = patch_size // 2),
+            Rearrange('b c n -> b n c'),
+            nn.Linear(patch_dim, dim)
+        )
+
+        output_size = conv_output_size(image_size, patch_size, patch_size // 2)
+        num_patches = output_size ** 2
+
+        self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
+        self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
+        self.dropout = nn.Dropout(emb_dropout)
+
+        layers = []
+
+        for ind, (layer_depth, layer_heads) in enumerate(zip(depth, heads)):
+            not_last = ind < (len(depth) - 1)
+            
+            layers.append(Transformer(dim, layer_depth, layer_heads, dim_head, mlp_dim, dropout))
+
+            if not_last:
+                layers.append(Pool(dim))
+                dim *= 2
+
+        self.layers = nn.Sequential(
+            *layers,
+            nn.LayerNorm(dim),
+            nn.Linear(dim, num_classes)
+        )
+
+    def forward(self, img):
+        x = self.to_patch_embedding(img)
+        b, n, _ = x.shape
+
+        cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
+        x = torch.cat((cls_tokens, x), dim=1)
+        x += self.pos_embedding
+        x = self.dropout(x)
+
+        return self.layers(x)