Upload New File

人工智能系统实战第三期/实战代码/深度学习项目实战/基于transformer的花朵识别/ViTFlowerClassification/model.py

+from functools import partial
+from functools import partial
+from collections import OrderedDict
+
+import torch
+import torch.nn as nn
+
+
+def drop_path(x, drop_prob: float = 0., training: bool = False):
+    """https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 有讨论到关于Drop Connect的一些歧义。
+    此处采用了一种网友给出的优化方式，以下为其原注释内容：
+    Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
+    This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
+    the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
+    See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
+    changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
+    'survival rate' as the argument.
+    """
+    if drop_prob == 0. or not training:
+        return x
+    keep_prob = 1 - drop_prob
+    shape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
+    random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
+    random_tensor.floor_()  # binarize
+    output = x.div(keep_prob) * random_tensor
+
+    return output
+
+
+class DropPath(nn.Module):
+    """
+    Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
+    """
+
+    def __init__(self, drop_prob=None):
+        super(DropPath, self).__init__()
+        self.drop_prob = drop_prob
+
+    def forward(self, x):
+        # 随机drop一个完整的block，
+        return drop_path(x, self.drop_prob, self.training)
+
+
+class PatchEmbed(nn.Module):
+    """
+    2D 图像 Patch Embedding
+    """
+
+    def __init__(self, image_size=224, patch_size=16, in_c=3, embed_dim=768, norm_layer=None):
+        """
+        Map input tensor to patch.
+        Args:
+            image_size: 输入图片的大小
+            patch_size: patch的大小
+            in_c: 输入的通道数
+            embed_dim: 编码维度. dimension = patch_size * patch_size * in_c
+            norm_layer: layer_normalization的方法
+        """
+        super().__init__()
+        image_size = (image_size, image_size)
+        patch_size = (patch_size, patch_size)
+        self.image_size = image_size
+        self.patch_size = patch_size
+        self.grid_size = (image_size[0] // patch_size[0], image_size[1] // patch_size[1])
+        self.num_patches = self.grid_size[0] * self.grid_size[1]
+
+        # 使用16x16的卷积核将输入的tensor切成多个patches
+        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=patch_size, stride=patch_size)
+        self.norm = norm_layer(embed_dim) if norm_layer else nn.Identity()
+
+    def forward(self, x):
+        B, C, H, W = x.shape
+        assert H == self.image_size[0] and W == self.image_size[1], \
+            f"Input image size ({H}*{W}) doesn't match model ({self.image_size[0]}*{self.image_size[1]})."
+
+        # 打平: [B, C, H, W] -> [B, C, HW]
+        # 维度变换: [B, C, HW] -> [B, HW, C]
+        x = self.proj(x).flatten(2).transpose(1, 2)
+        x = self.norm(x)
+
+        return x
+
+
+class Attention(nn.Module):
+    def __init__(self,
+                 dim,  # 输入token的dim
+                 num_heads=8, # 多投资注意力的头数
+                 qkv_bias=False,
+                 qk_scale=None,
+                 attn_drop_ratio=0.,
+                 proj_drop_ratio=0.):
+        super(Attention, self).__init__()
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = qk_scale or head_dim ** -0.5      # 根号d，缩放因子
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop = nn.Dropout(attn_drop_ratio)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop_ratio)
+
+    def forward(self, x):
+        """
+        code#############################################################################
+        """
+
+        return x
+
+
+class MLP(nn.Module):
+
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+
+        return x
+
+
+class Block(nn.Module):
+    def __init__(self,
+                 dim,
+                 num_heads,
+                 mlp_ratio=4.,
+                 qkv_bias=False,
+                 qk_scale=None,
+                 drop_ratio=0.,
+                 attn_drop_ratio=0.,
+                 drop_path_ratio=0.,
+                 act_layer=nn.GELU,
+                 norm_layer=nn.LayerNorm):
+        super(Block, self).__init__()
+        self.norm1 = norm_layer(dim)
+        self.attn = Attention(dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale,
+                              attn_drop_ratio=attn_drop_ratio, proj_drop_ratio=drop_ratio)
+        # NOTE: 对随即深度的路径丢弃
+        self.drop_path = DropPath(drop_path_ratio) if drop_path_ratio > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = MLP(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop_ratio)
+
+    def forward(self, x):
+        x = x + self.drop_path(self.attn(self.norm1(x)))
+        x = x + self.drop_path(self.mlp(self.norm2(x)))
+
+        return x
+
+
+class VisionTransformer(nn.Module):
+    def __init__(self, image_size=224, patch_size=16, in_c=3, num_classes=1000,
+                 embed_dim=768, depth=12, num_heads=12, mlp_ratio=4.0, qkv_bias=True,
+                 qk_scale=None, representation_size=None, distilled=False, drop_ratio=0.,
+                 attn_drop_ratio=0., drop_path_ratio=0.5, embed_layer=PatchEmbed, norm_layer=None,
+                 act_layer=None):
+        """
+        Args:
+            image_size (int, tuple): 输入图片的尺寸
+            patch_size (int, tuple): patch 尺寸
+            in_c (int): 输入的通道数
+            num_classes (int): 分类类别数
+            embed_dim (int): 编码维度, dim = patch_size * patch_size * in_c
+            depth (int): transformer深度
+            num_heads (int): 多头自注意力的头数
+            mlp_ratio (int): ratio of mlp hidden dim to embedding dim
+            qkv_bias (bool): 如果为True，则使用qkv的偏置
+            qk_scale (float): 更改原qk的缩放大小
+            representation_size (Optional[int]): enable and set representation layer (pre-logits) to this value if set
+            distilled (bool): 是否使用蒸馏法来优化模型(ViTal的变体模型：DeiT)
+            drop_ratio (float): dropout rate
+            attn_drop_ratio (float): attention dropout rate
+            drop_path_ratio (float): stochastic depth rate
+            embed_layer (nn.Module): patch embedding layer
+            norm_layer: (nn.Module): normalization layer
+        """
+        super(VisionTransformer, self).__init__()
+        self.num_classes = num_classes
+        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
+        self.num_tokens = 2 if distilled else 1
+        norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)  # partial类似闭包函数，第一个参数是函数对象，后面的参数是第一个函数对象的实参
+        act_layer = act_layer or nn.GELU
+
+        self.patch_embed = embed_layer(image_size=image_size, patch_size=patch_size, in_c=in_c, embed_dim=embed_dim)
+        num_patches = self.patch_embed.num_patches
+
+        self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))     # nn.Parameter转换函数，把参数转换为可训练变量
+        self.dist_token = nn.Parameter(torch.zeros(1, 1, embed_dim)) if distilled else None
+        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + self.num_tokens, embed_dim))
+        self.pos_drop = nn.Dropout(p=drop_ratio)
+
+        dpr = [x.item() for x in torch.linspace(0, drop_path_ratio, depth)]  # stochastic depth decay rule
+        self.blocks = nn.Sequential(*[
+            Block(dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, qk_scale=qk_scale,
+                  drop_ratio=drop_ratio, attn_drop_ratio=attn_drop_ratio, drop_path_ratio=dpr[i],
+                  norm_layer=norm_layer, act_layer=act_layer)
+            for i in range(depth)
+        ])
+        self.norm = norm_layer(embed_dim)
+
+        # Representation layer
+        if representation_size and not distilled:
+            self.has_logits = True
+            self.num_features = representation_size
+            self.pre_logits = nn.Sequential(OrderedDict([
+                ("fc", nn.Linear(embed_dim, representation_size)),
+                ("act", nn.Tanh())
+            ]))
+        else:
+            self.has_logits = False
+            self.pre_logits = nn.Identity()     # placeholder
+
+        # Classifier head(s)
+        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()
+        self.head_dist = None
+        if distilled:
+            self.head_dist = nn.Linear(self.embed_dim, self.num_classes) if num_classes > 0 else nn.Identity()
+
+        # Weight init
+        nn.init.trunc_normal_(self.pos_embed, std=0.02)
+        if self.dist_token is not None:
+            nn.init.trunc_normal_(self.dist_token, std=0.02)
+
+        nn.init.trunc_normal_(self.cls_token, std=0.02)
+        self.apply(_init_vit_weights)
+
+    def forward_features(self, x):
+        # [B, C, H, W] -> [B, num_patches, embed_dim]
+        x = self.patch_embed(x)  # [B, 196, 768]
+        # [1, 1, 768] -> [B, 1, 768]
+        cls_token = self.cls_token.expand(x.shape[0], -1, -1)
+        if self.dist_token is None:
+            x = torch.cat((cls_token, x), dim=1)  # [B, 197, 768]
+        else:
+            x = torch.cat((cls_token, self.dist_token.expand(x.shape[0], -1, -1), x), dim=1)
+
+        x = self.pos_drop(x + self.pos_embed)
+        x = self.blocks(x)
+        x = self.norm(x)
+        if self.dist_token is None:
+            return self.pre_logits(x[:, 0])
+        else:
+            return x[:, 0], x[:, 1]
+
+    def forward(self, x):
+        x = self.forward_features(x)
+        if self.head_dist is not None:
+            x, x_dist = self.head(x[0]), self.head_dist(x[1])
+            if self.training and not torch.jit.is_scripting():
+                return x, x_dist
+            else:
+                return (x + x_dist) / 2
+        else:
+            x = self.head(x)
+
+        return x
+
+
+def _init_vit_weights(m):
+    """
+    ViT weight initialization
+    :param m: module
+    """
+    if isinstance(m, nn.Linear):
+        nn.init.trunc_normal_(m.weight, std=.01)
+        if m.bias is not None:
+            nn.init.zeros_(m.bias)
+    elif isinstance(m, nn.Conv2d):
+        nn.init.kaiming_normal_(m.weight, mode="fan_out")
+        if m.bias is not None:
+            nn.init.zeros_(m.bias)
+    elif isinstance(m, nn.LayerNorm):
+        nn.init.zeros_(m.bias)
+        nn.init.ones_(m.weight)
+
+
+def vit_base_patch16_224_in21k(num_classes: int = 21843, has_logits: bool = True):
+    """
+    ViT-Base model (ViT-B/16) from original paper (https://arxiv.org/abs/2010.11929).
+    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
+    weights ported from official Google JAX impl:
+    https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_patch16_224_in21k-e5005f0a.pth
+    """
+    model = VisionTransformer(image_size=224,
+                              patch_size=16,
+                              embed_dim=768,
+                              depth=12,
+                              num_heads=12,
+                              representation_size=768 if has_logits else None,
+                              num_classes=num_classes)
+
+    return model
+
+
+def vit_base_patch32_224_in21k(num_classes: int = 21843, has_logits: bool = True):
+    """
+    ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929).
+    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
+    weights ported from official Google JAX impl:
+    https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_patch32_224_in21k-8db57226.pth
+    """
+    model = VisionTransformer(image_size=224,
+                              patch_size=32,
+                              embed_dim=768,
+                              depth=12,
+                              num_heads=12,
+                              representation_size=768 if has_logits else None,
+                              num_classes=num_classes)
+
+    return model
+
+
+def vit_large_patch16_224_in21k(num_classes: int = 21843, has_logits: bool = True):
+    """
+    ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929).
+    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
+    weights ported from official Google JAX impl:
+    https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch16_224_in21k-606da67d.pth
+    """
+    model = VisionTransformer(image_size=224,
+                              patch_size=16,
+                              embed_dim=1024,
+                              depth=24,
+                              num_heads=16,
+                              representation_size=1024 if has_logits else None,
+                              num_classes=num_classes)
+
+    return model
+
+
+def vit_large_patch32_224_in21k(num_classes: int = 21843, has_logits: bool = True):
+    """
+    ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929).
+    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
+    weights ported from official Google JAX impl:
+    https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_patch32_224_in21k-9046d2e7.pth
+    """
+    model = VisionTransformer(image_size=224,
+                              patch_size=32,
+                              embed_dim=1024,
+                              depth=24,
+                              num_heads=16,
+                              representation_size=1024 if has_logits else None,
+                              num_classes=num_classes)
+
+    return model
+
+
+def vit_huge_patch14_224_in21k(num_classes: int = 21843, has_logits: bool = True):
+    """
+    ViT-Huge model (ViT-H/14) from original paper (https://arxiv.org/abs/2010.11929).
+    ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer.
+    NOTE: converted weights not currently available, too large for github release hosting.
+    """
+    model = VisionTransformer(image_size=224,
+                              patch_size=14,
+                              embed_dim=1280,
+                              depth=32,
+                              num_heads=16,
+                              representation_size=1280 if has_logits else None,
+                              num_classes=num_classes)
+
+    return model