面试复盘需要准备什么，Swin Transformer，泪目

B = int(windows.shape[0] / (H * W / window_size / window_size))

x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)

x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)

return x

class WindowAttention(nn.Module):

r"“” Window based multi-head self attention (W-MSA) module with relative position bias.

It supports both of shifted and non-shifted window.

Args:

dim (int): Number of input channels.

window_size (tuple[int]): The height and width of the window.

num_heads (int): Number of attention heads.

qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True

attn_drop (float, optional): Dropout ratio of attention weight. Default: 0.0

proj_drop (float, optional): Dropout ratio of output. Default: 0.0

“”"

def init(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.):

super().init()

self.dim = dim

self.window_size = window_size # Wh, Ww

self.num_heads = num_heads

head_dim = dim // num_heads

self.scale = head_dim ** -0.5

define a parameter table of relative position bias

self.relative_position_bias_table = nn.Parameter(

torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads)) # 2Wh-1 * 2Ww-1, nH

get pair-wise relative position index for each token inside the window

coords_h = torch.arange(self.window_size[0])

coords_w = torch.arange(self.window_size[1])

coords = torch.stack(torch.meshgrid([coords_h, coords_w])) # 2, Wh, Ww

coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww

relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :] # 2, WhWw, WhWw

relative_coords = relative_coords.permute(1, 2, 0).contiguous() # WhWw, WhWw, 2

relative_coords[:, :, 0] += self.window_size[0] - 1 # shift to start from 0

relative_coords[:, :, 1] += self.window_size[1] - 1

relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1

relative_position_index = relative_coords.sum(-1) # WhWw, WhWw

self.register_buffer(“relative_position_index”, relative_position_index)

self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)

self.attn_drop = nn.Dropout(attn_drop)

self.proj = nn.Linear(dim, dim)

self.proj_drop = nn.Dropout(proj_drop)

trunc_normal_(self.relative_position_bias_table, std=.02)

self.softmax = nn.Softmax(dim=-1)

def forward(self, x, mask: Optional[torch.Tensor] = None):

“”"

Args:

x: input features with shape of (num_windows*B, N, C)

mask: (0/-inf) mask with shape of (num_windows, WhWw, WhWw) or None

“”"

B_, N, C = x.shape

qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)

q, k, v = qkv.unbind(0) # make torchscript happy (cannot use tensor as tuple)

q = q * self.scale

attn = (q @ k.transpose(-2, -1))

relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(

self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1) # WhWw,WhWw,nH

relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous() # nH, WhWw, WhWw

attn = attn + relative_position_bias.unsqueeze(0)

if mask is not None:

nW = mask.shape[0]

attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)

attn = attn.view(-1, self.num_heads, N, N)

attn = self.softmax(attn)

else:

attn = self.softmax(attn)

attn = self.attn_drop(attn)

x = (attn @ v).transpose(1, 2).reshape(B_, N, C)

x = self.proj(x)

x = self.proj_drop(x)

return x

class SwinTransformerBlock(nn.Module):

r"“” Swin Transformer Block.

Args:

dim (int): Number of input channels.

input_resolution (tuple[int]): Input resulotion.

num_heads (int): Number of attention heads.

window_size (int): Window size.

shift_size (int): Shift size for SW-MSA.

mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.

qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True

drop (float, optional): Dropout rate. Default: 0.0

attn_drop (float, optional): Attention dropout rate. Default: 0.0

drop_path (float, optional): Stochastic depth rate. Default: 0.0

act_layer (nn.Module, optional): Activation layer. Default: nn.GELU

norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm

“”"

def init(self, dim, input_resolution, num_heads, window_size=7, shift_size=0,

mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0.,

act_layer=nn.GELU, norm_layer=nn.LayerNorm):

super().init()

self.dim = dim

self.input_resolution = input_resolution

self.num_heads = num_heads

self.window_size = window_size

self.shift_size = shift_size

self.mlp_ratio = mlp_ratio

if min(self.input_resolution) <= self.window_size:

if window size is larger than input resolution, we don’t partition windows

self.shift_size = 0

self.window_size = min(self.input_resolution)

assert 0 <= self.shift_size < self.window_size, “shift_size must in 0-window_size”

self.norm1 = norm_layer(dim)

self.attn = WindowAttention(

dim, window_size=to_2tuple(self.window_size), num_heads=num_heads, qkv_bias=qkv_bias,

attn_drop=attn_drop, proj_drop=drop)

self.drop_path = DropPath(drop_path) if drop_path > 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)

if self.shift_size > 0:

calculate attention mask for SW-MSA

H, W = self.input_resolution

img_mask = torch.zeros((1, H, W, 1)) # 1 H W 1

h_slices = (slice(0, -self.window_size),

slice(-self.window_size, -self.shift_size),

slice(-self.shift_size, None))

w_slices = (slice(0, -self.window_size),

slice(-self.window_size, -self.shift_size),

slice(-self.shift_size, None))

cnt = 0

for h in h_slices:

for w in w_slices:

img_mask[:, h, w, :] = cnt

cnt += 1

mask_windows = window_partition(img_mask, self.window_size) # nW, window_size, window_size, 1

mask_windows = mask_windows.view(-1, self.window_size * self.window_size)

attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)

attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))

else:

attn_mask = None

self.register_buffer(“attn_mask”, attn_mask)

def forward(self, x):

H, W = self.input_resolution

B, L, C = x.shape

_assert(L == H * W, “input feature has wrong size”)

shortcut = x

x = self.norm1(x)

x = x.view(B, H, W, C)

cyclic shift

if self.shift_size > 0:

shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))

else:

shifted_x = x

partition windows

x_windows = window_partition(shifted_x, self.window_size) # nW*B, window_size, window_size, C

x_windows = x_windows.view(-1, self.window_size * self.window_size, C) # nWB, window_sizewindow_size, C

W-MSA/SW-MSA

attn_windows = self.attn(x_windows, mask=self.attn_mask) # nWB, window_sizewindow_size, C

merge windows

attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)

shifted_x = window_reverse(attn_windows, self.window_size, H, W) # B H’ W’ C

reverse cyclic shift

if self.shift_size > 0:

x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))

else:

x = shifted_x

x = x.view(B, H * W, C)

FFN

x = shortcut + self.drop_path(x)

x = x + self.drop_path(self.mlp(self.norm2(x)))

return x

class PatchMerging(nn.Module):

r"“” Patch Merging Layer.

Args:

input_resolution (tuple[int]): Resolution of input feature.

dim (int): Number of input channels.

norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm

“”"

def init(self, input_resolution, dim, norm_layer=nn.LayerNorm):

super().init()

self.input_resolution = input_resolution

self.dim = dim

self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)

self.norm = norm_layer(4 * dim)

def forward(self, x):

“”"

x: B, H*W, C

“”"

H, W = self.input_resolution

B, L, C = x.shape

_assert(L == H * W, “input feature has wrong size”)

_assert(H % 2 == 0 and W % 2 == 0, f"x size ({H}*{W}) are not even.")

x = x.view(B, H, W, C)

x0 = x[:, 0::2, 0::2, :] # B H/2 W/2 C

x1 = x[:, 1::2, 0::2, :] # B H/2 W/2 C

x2 = x[:, 0::2, 1::2, :] # B H/2 W/2 C

x3 = x[:, 1::2, 1::2, :] # B H/2 W/2 C

x = torch.cat([x0, x1, x2, x3], -1) # B H/2 W/2 4*C

x = x.view(B, -1, 4 * C) # B H/2W/2 4C

x = self.norm(x)

x = self.reduction(x)

return x

def extra_repr(self) -> str:

return f"input_resolution={self.input_resolution}, dim={self.dim}"

def flops(self):

H, W = self.input_resolution

flops = H * W * self.dim

flops += (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim

return flops

class BasicLayer(nn.Module):

“”" A basic Swin Transformer layer for one stage.

Args:

dim (int): Number of input channels.

input_resolution (tuple[int]): Input resolution.

depth (int): Number of blocks.

num_heads (int): Number of attention heads.

window_size (int): Local window size.

mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.

qkv_bias (bool, optional): If True, add a learnable bias to query, key, value. Default: True

drop (float, optional): Dropout rate. Default: 0.0

attn_drop (float, optional): Attention dropout rate. Default: 0.0

drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0

norm_layer (nn.Module, optional): Normalization layer. Default: nn.LayerNorm

自我介绍一下，小编13年上海交大毕业，曾经在小公司待过，也去过华为、OPPO等大厂，18年进入阿里一直到现在。

深知大多数Python工程师，想要提升技能，往往是自己摸索成长或者是报班学习，但对于培训机构动则几千的学费，着实压力不小。自己不成体系的自学效果低效又漫长，而且极易碰到天花板技术停滞不前！

因此收集整理了一份《2024年Python开发全套学习资料》，初衷也很简单，就是希望能够帮助到想自学提升又不知道该从何学起的朋友，同时减轻大家的负担。

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上Python开发知识点，真正体系化！

由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新

如果你觉得这些内容对你有帮助，可以添加V获取：vip1024c （备注Python）

一、Python所有方向的学习路线

Python所有方向路线就是把Python常用的技术点做整理，形成各个领域的知识点汇总，它的用处就在于，你可以按照上面的知识点去找对应的学习资源，保证自己学得较为全面。

二、学习软件

工欲善其事必先利其器。学习Python常用的开发软件都在这里了，给大家节省了很多时间。

三、入门学习视频

我们在看视频学习的时候，不能光动眼动脑不动手，比较科学的学习方法是在理解之后运用它们，这时候练手项目就很适合了。

一个人可以走的很快，但一群人才能走的更远。不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎扫码加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！

发软件都在这里了，给大家节省了很多时间。

三、入门学习视频

我们在看视频学习的时候，不能光动眼动脑不动手，比较科学的学习方法是在理解之后运用它们，这时候练手项目就很适合了。

一个人可以走的很快，但一群人才能走的更远。不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎扫码加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！
[外链图片转存中…(img-DFmVvW92-1712597809994)]