先自我介绍一下,小编浙江大学毕业,去过华为、字节跳动等大厂,目前阿里P7
深知大多数程序员,想要提升技能,往往是自己摸索成长,但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年最新Python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。
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,涵盖了95%以上Python知识点,真正体系化!
由于文件比较多,这里只是将部分目录截图出来,全套包含大厂面经、学习笔记、源码讲义、实战项目、大纲路线、讲解视频,并且后续会持续更新
如果你需要这些资料,可以添加V获取:vip1024c (备注Python)
正文
from .fx_features import register_notrace_function
from .helpers import build_model_with_cfg, overlay_external_default_cfg
from .layers import PatchEmbed, Mlp, DropPath, to_2tuple, trunc_normal_
from .layers import _assert
from .registry import register_model
from .vision_transformer import checkpoint_filter_fn, _init_vit_weights
_logger = logging.getLogger(name)
def _cfg(url=‘’, **kwargs):
return {
‘url’: url,
‘num_classes’: 1000, ‘input_size’: (3, 224, 224), ‘pool_size’: None,
‘crop_pct’: .9, ‘interpolation’: ‘bicubic’, ‘fixed_input_size’: True,
‘mean’: IMAGENET_DEFAULT_MEAN, ‘std’: IMAGENET_DEFAULT_STD,
‘first_conv’: ‘patch_embed.proj’, ‘classifier’: ‘head’,
**kwargs
}
default_cfgs = {
patch models (my experiments)
‘swin_base_patch4_window12_384’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384_22kto1k.pth’,
input_size=(3, 384, 384), crop_pct=1.0),
‘swin_base_patch4_window7_224’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22kto1k.pth’,
),
‘swin_large_patch4_window12_384’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22kto1k.pth’,
input_size=(3, 384, 384), crop_pct=1.0),
‘swin_large_patch4_window7_224’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window7_224_22kto1k.pth’,
),
‘swin_small_patch4_window7_224’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth’,
),
‘swin_tiny_patch4_window7_224’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth’,
),
‘swin_base_patch4_window12_384_in22k’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384_22k.pth’,
input_size=(3, 384, 384), crop_pct=1.0, num_classes=21841),
‘swin_base_patch4_window7_224_in22k’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22k.pth’,
num_classes=21841),
‘swin_large_patch4_window12_384_in22k’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22k.pth’,
input_size=(3, 384, 384), crop_pct=1.0, num_classes=21841),
‘swin_large_patch4_window7_224_in22k’: _cfg(
url=‘https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window7_224_22k.pth’,
num_classes=21841),
}
def window_partition(x, window_size: int):
“”"
Args:
x: (B, H, W, C)
window_size (int): window size
Returns:
windows: (num_windows*B, window_size, window_size, C)
“”"
B, H, W, C = x.shape
x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
return windows
@register_notrace_function # reason: int argument is a Proxy
def window_reverse(windows, window_size: int, H: int, W: int):
“”"
Args:
windows: (num_windows*B, window_size, window_size, C)
window_size (int): Window size
H (int): Height of image
W (int): Width of image
Returns:
x: (B, H, W, C)
“”"
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
downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
“”"
def init(self, dim, input_resolution, depth, num_heads, window_size,
mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0.,
drop_path=0., norm_layer=nn.LayerNorm, downsample=None, use_checkpoint=False):
super().init()
self.dim = dim
self.input_resolution = input_resolution
self.depth = depth
self.use_checkpoint = use_checkpoint
build blocks
self.blocks = nn.ModuleList([
SwinTransformerBlock(
dim=dim, input_resolution=input_resolution, num_heads=num_heads, window_size=window_size,
shift_size=0 if (i % 2 == 0) else window_size // 2, mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias, drop=drop, attn_drop=attn_drop,
drop_path=drop_path[i] if isinstance(drop_path, list) else drop_path, norm_layer=norm_layer)
for i in range(depth)])
patch merging layer
if downsample is not None:
self.downsample = downsample(input_resolution, dim=dim, norm_layer=norm_layer)
else:
self.downsample = None
def forward(self, x):
for blk in self.blocks:
if not torch.jit.is_scripting() and self.use_checkpoint:
x = checkpoint.checkpoint(blk, x)
else:
x = blk(x)
if self.downsample is not None:
x = self.downsample(x)
return x
做了那么多年开发,自学了很多门编程语言,我很明白学习资源对于学一门新语言的重要性,这些年也收藏了不少的Python干货,对我来说这些东西确实已经用不到了,但对于准备自学Python的人来说,或许它就是一个宝藏,可以给你省去很多的时间和精力。
别在网上瞎学了,我最近也做了一些资源的更新,只要你是我的粉丝,这期福利你都可拿走。
我先来介绍一下这些东西怎么用,文末抱走。
(1)Python所有方向的学习路线(新版)
这是我花了几天的时间去把Python所有方向的技术点做的整理,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。
最近我才对这些路线做了一下新的更新,知识体系更全面了。
(2)Python学习视频
包含了Python入门、爬虫、数据分析和web开发的学习视频,总共100多个,虽然没有那么全面,但是对于入门来说是没问题的,学完这些之后,你可以按照我上面的学习路线去网上找其他的知识资源进行进阶。
(3)100多个练手项目
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,只是里面的项目比较多,水平也是参差不齐,大家可以挑自己能做的项目去练练。
(4)200多本电子书
这些年我也收藏了很多电子书,大概200多本,有时候带实体书不方便的话,我就会去打开电子书看看,书籍可不一定比视频教程差,尤其是权威的技术书籍。
基本上主流的和经典的都有,这里我就不放图了,版权问题,个人看看是没有问题的。
(5)Python知识点汇总
知识点汇总有点像学习路线,但与学习路线不同的点就在于,知识点汇总更为细致,里面包含了对具体知识点的简单说明,而我们的学习路线则更为抽象和简单,只是为了方便大家只是某个领域你应该学习哪些技术栈。
(6)其他资料
还有其他的一些东西,比如说我自己出的Python入门图文类教程,没有电脑的时候用手机也可以学习知识,学会了理论之后再去敲代码实践验证,还有Python中文版的库资料、MySQL和HTML标签大全等等,这些都是可以送给粉丝们的东西。
这些都不是什么非常值钱的东西,但对于没有资源或者资源不是很好的学习者来说确实很不错,你要是用得到的话都可以直接抱走,关注过我的人都知道,这些都是可以拿到的。
网上学习资料一大堆,但如果学到的知识不成体系,遇到问题时只是浅尝辄止,不再深入研究,那么很难做到真正的技术提升。
需要这份系统化的资料的朋友,可以添加V获取:vip1024c (备注python)
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!
书不方便的话,我就会去打开电子书看看,书籍可不一定比视频教程差,尤其是权威的技术书籍。
基本上主流的和经典的都有,这里我就不放图了,版权问题,个人看看是没有问题的。
(5)Python知识点汇总
知识点汇总有点像学习路线,但与学习路线不同的点就在于,知识点汇总更为细致,里面包含了对具体知识点的简单说明,而我们的学习路线则更为抽象和简单,只是为了方便大家只是某个领域你应该学习哪些技术栈。
(6)其他资料
还有其他的一些东西,比如说我自己出的Python入门图文类教程,没有电脑的时候用手机也可以学习知识,学会了理论之后再去敲代码实践验证,还有Python中文版的库资料、MySQL和HTML标签大全等等,这些都是可以送给粉丝们的东西。
这些都不是什么非常值钱的东西,但对于没有资源或者资源不是很好的学习者来说确实很不错,你要是用得到的话都可以直接抱走,关注过我的人都知道,这些都是可以拿到的。
网上学习资料一大堆,但如果学到的知识不成体系,遇到问题时只是浅尝辄止,不再深入研究,那么很难做到真正的技术提升。
需要这份系统化的资料的朋友,可以添加V获取:vip1024c (备注python)
[外链图片转存中…(img-QhPLZafQ-1713189848349)]
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!