PyTorch框架——基于深度学习FasterNet神经网络幼苗图像识别分类系统
发布时间
阅读量：
阅读量
PyTorch框架——基于深度学习FasterNet神经网络幼苗图像识别分类系统
第一步：准备数据
幼苗数据集，英文为 plant seedlings dataset。
https://www.kaggle.com/competitions/plant-seedlings-classification/data
train 目录下有 221 张 Common wheat 的图片。
共十二种植物的幼苗图片集。
具体信息如下：
第二步：搭建模型
FasterNet 是一种高效的神经网络架构，旨在提高计算速度而不牺牲准确性 ，特别是在视觉任务中。它通过一种称为部分卷积（PConv）的新技术来减少冗余计算和内存访问。这种方法使得FasterNet在多种设备上速度比其他网络快得多，同时在各种视觉任务中保持高准确率。例如，FasterNet在ImageNet-1k数据集上的表现超过了其他模型，如 MobileViT-XXS，展现了其在速度和准确度方面的优势。
🔥计算机视觉、图像处理、毕业辅导、作业帮助、代码获取，远程协助，代码定制，私聊会回复!
✍🏻作者简介：机器学习，深度学习，卷积神经网络处理，图像处理
🚀B站项目实战：https://space.bilibili.com/364224477
😄 如果文章对你有帮助的话， 欢迎评论 💬点赞👍🏻 收藏 📂加关注+
🤵♂代做需求：@个人主页
FasterNet的基本原理可以总结为以下几点：
1. 部分卷积（PConv）: FasterNet引入了部分卷积（PConv），这是一种新型的卷积方法，它通过只处理输入通道的一部分来减少计算量和内存访问。
2. 加速神经网络 : FasterNet利用PConv的优势，实现了在多种设备上比其他现有神经网络更快的速度，同时保持了较高的准确度。
下面为大家展示的是FasterNet的整体架构 。
它包括四个层次化的阶段，每个阶段由一系列FasterNet块组成，并由嵌入或合并层开头。最后三层用于特征分类。在每个FasterNet块中，PConv层之后是两个点状卷积（PWConv）层。为了保持特征多样性并实现更低的延迟，仅在中间层之后放置了归一化和激活层。
第三步：训练代码
1）损失函数为：交叉熵损失函数
2）FasterNet 代码：
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import torch
import torch.nn as nn
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
from functools import partial
from typing import List
from torch import Tensor
import copy
import os
try:
from mmdet.models.builder import BACKBONES as det_BACKBONES
from mmdet.utils import get_root_logger
from mmcv.runner import _load_checkpoint
has_mmdet = True
except ImportError:
print("If for detection, please install mmdetection first")
has_mmdet = False
class Partial_conv3(nn.Module):
def __init__(self, dim, n_div, forward):
super().__init__()
self.dim_conv3 = dim // n_div
self.dim_untouched = dim - self.dim_conv3
self.partial_conv3 = nn.Conv2d(self.dim_conv3, self.dim_conv3, 3, 1, 1, bias=False)
if forward == 'slicing':
self.forward = self.forward_slicing
elif forward == 'split_cat':
self.forward = self.forward_split_cat
else:
raise NotImplementedError
def forward_slicing(self, x: Tensor) -> Tensor:
# only for inference
x = x.clone() # !!! Keep the original input intact for the residual connection later
x[:, :self.dim_conv3, :, :] = self.partial_conv3(x[:, :self.dim_conv3, :, :])
return x
def forward_split_cat(self, x: Tensor) -> Tensor:
# for training/inference
x1, x2 = torch.split(x, [self.dim_conv3, self.dim_untouched], dim=1)
x1 = self.partial_conv3(x1)
x = torch.cat((x1, x2), 1)
return x
class MLPBlock(nn.Module):
def __init__(self,
dim,
n_div,
mlp_ratio,
drop_path,
layer_scale_init_value,
act_layer,
norm_layer,
pconv_fw_type
):
super().__init__()
self.dim = dim
self.mlp_ratio = mlp_ratio
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
self.n_div = n_div
mlp_hidden_dim = int(dim * mlp_ratio)
mlp_layer: List[nn.Module] = [
nn.Conv2d(dim, mlp_hidden_dim, 1, bias=False),
norm_layer(mlp_hidden_dim),
act_layer(),
nn.Conv2d(mlp_hidden_dim, dim, 1, bias=False)
]
self.mlp = nn.Sequential(*mlp_layer)
self.spatial_mixing = Partial_conv3(
dim,
n_div,
pconv_fw_type
)
if layer_scale_init_value > 0:
self.layer_scale = nn.Parameter(layer_scale_init_value * torch.ones((dim)), requires_grad=True)
self.forward = self.forward_layer_scale
else:
self.forward = self.forward
def forward(self, x: Tensor) -> Tensor:
shortcut = x
x = self.spatial_mixing(x)
x = shortcut + self.drop_path(self.mlp(x))
return x
def forward_layer_scale(self, x: Tensor) -> Tensor:
shortcut = x
x = self.spatial_mixing(x)
x = shortcut + self.drop_path(
self.layer_scale.unsqueeze(-1).unsqueeze(-1) * self.mlp(x))
return x
class BasicStage(nn.Module):
def __init__(self,
dim,
depth,
n_div,
mlp_ratio,
drop_path,
layer_scale_init_value,
norm_layer,
act_layer,
pconv_fw_type
):
super().__init__()
blocks_list = [
MLPBlock(
dim=dim,
n_div=n_div,
mlp_ratio=mlp_ratio,
drop_path=drop_path[i],
layer_scale_init_value=layer_scale_init_value,
norm_layer=norm_layer,
act_layer=act_layer,
pconv_fw_type=pconv_fw_type
)
for i in range(depth)
]
self.blocks = nn.Sequential(*blocks_list)
def forward(self, x: Tensor) -> Tensor:
x = self.blocks(x)
return x
class PatchEmbed(nn.Module):
def __init__(self, patch_size, patch_stride, in_chans, embed_dim, norm_layer):
super().__init__()
self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_stride, bias=False)
if norm_layer is not None:
self.norm = norm_layer(embed_dim)
else:
self.norm = nn.Identity()
def forward(self, x: Tensor) -> Tensor:
x = self.norm(self.proj(x))
return x
class PatchMerging(nn.Module):
def __init__(self, patch_size2, patch_stride2, dim, norm_layer):
super().__init__()
self.reduction = nn.Conv2d(dim, 2 * dim, kernel_size=patch_size2, stride=patch_stride2, bias=False)
if norm_layer is not None:
self.norm = norm_layer(2 * dim)
else:
self.norm = nn.Identity()
def forward(self, x: Tensor) -> Tensor:
x = self.norm(self.reduction(x))
return x
class FasterNet(nn.Module):
def __init__(self,
in_chans=3,
num_classes=1000,
embed_dim=96,
depths=(1, 2, 8, 2),
mlp_ratio=2.,
n_div=4,
patch_size=4,
patch_stride=4,
patch_size2=2, # for subsequent layers
patch_stride2=2,
patch_norm=True,
feature_dim=1280,
drop_path_rate=0.1,
layer_scale_init_value=0,
norm_layer='BN',
act_layer='RELU',
fork_feat=False,
init_cfg=None,
pretrained=None,
pconv_fw_type='split_cat',
**kwargs):
super().__init__()
if norm_layer == 'BN':
norm_layer = nn.BatchNorm2d
else:
raise NotImplementedError
if act_layer == 'GELU':
act_layer = nn.GELU
elif act_layer == 'RELU':
act_layer = partial(nn.ReLU, inplace=True)
else:
raise NotImplementedError
if not fork_feat:
self.num_classes = num_classes
self.num_stages = len(depths)
self.embed_dim = embed_dim
self.patch_norm = patch_norm
self.num_features = int(embed_dim * 2 ** (self.num_stages - 1))
self.mlp_ratio = mlp_ratio
self.depths = depths
# split image into non-overlapping patches
self.patch_embed = PatchEmbed(
patch_size=patch_size,
patch_stride=patch_stride,
in_chans=in_chans,
embed_dim=embed_dim,
norm_layer=norm_layer if self.patch_norm else None
)
# stochastic depth decay rule
dpr = [x.item()
for x in torch.linspace(0, drop_path_rate, sum(depths))]
# build layers
stages_list = []
for i_stage in range(self.num_stages):
stage = BasicStage(dim=int(embed_dim * 2 ** i_stage),
n_div=n_div,
depth=depths[i_stage],
mlp_ratio=self.mlp_ratio,
drop_path=dpr[sum(depths[:i_stage]):sum(depths[:i_stage + 1])],
layer_scale_init_value=layer_scale_init_value,
norm_layer=norm_layer,
act_layer=act_layer,
pconv_fw_type=pconv_fw_type
)
stages_list.append(stage)
# patch merging layer
if i_stage < self.num_stages - 1:
stages_list.append(
PatchMerging(patch_size2=patch_size2,
patch_stride2=patch_stride2,
dim=int(embed_dim * 2 ** i_stage),
norm_layer=norm_layer)
)
self.stages = nn.Sequential(*stages_list)
self.fork_feat = fork_feat
if self.fork_feat:
self.forward = self.forward_det
# add a norm layer for each output
self.out_indices = [0, 2, 4, 6]
for i_emb, i_layer in enumerate(self.out_indices):
if i_emb == 0 and os.environ.get('FORK_LAST3', None):
raise NotImplementedError
else:
layer = norm_layer(int(embed_dim * 2 ** i_emb))
layer_name = f'norm{i_layer}'
self.add_module(layer_name, layer)
else:
self.forward = self.forward_cls
# Classifier head
self.avgpool_pre_head = nn.Sequential(
nn.AdaptiveAvgPool2d(1),
nn.Conv2d(self.num_features, feature_dim, 1, bias=False),
act_layer()
)
self.head = nn.Linear(feature_dim, num_classes) \
if num_classes > 0 else nn.Identity()
self.apply(self.cls_init_weights)
self.init_cfg = copy.deepcopy(init_cfg)
if self.fork_feat and (self.init_cfg is not None or pretrained is not None):
self.init_weights()
def cls_init_weights(self, m):
if isinstance(m, nn.Linear):
trunc_normal_(m.weight, std=.02)
if isinstance(m, nn.Linear) and m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, (nn.Conv1d, nn.Conv2d)):
trunc_normal_(m.weight, std=.02)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, (nn.LayerNorm, nn.GroupNorm)):
nn.init.constant_(m.bias, 0)
nn.init.constant_(m.weight, 1.0)
# init for mmdetection by loading imagenet pre-trained weights
def init_weights(self, pretrained=None):
logger = get_root_logger()
if self.init_cfg is None and pretrained is None:
logger.warn(f'No pre-trained weights for '
f'{self.__class__.__name__}, '
f'training start from scratch')
pass
else:
assert 'checkpoint' in self.init_cfg, f'Only support ' \
f'specify `Pretrained` in ' \
f'`init_cfg` in ' \
f'{self.__class__.__name__} '
if self.init_cfg is not None:
ckpt_path = self.init_cfg['checkpoint']
elif pretrained is not None:
ckpt_path = pretrained
ckpt = _load_checkpoint(
ckpt_path, logger=logger, map_location='cpu')
if 'state_dict' in ckpt:
_state_dict = ckpt['state_dict']
elif 'model' in ckpt:
_state_dict = ckpt['model']
else:
_state_dict = ckpt
state_dict = _state_dict
missing_keys, unexpected_keys = \
self.load_state_dict(state_dict, False)
# show for debug
print('missing_keys: ', missing_keys)
print('unexpected_keys: ', unexpected_keys)
def forward_cls(self, x):
# output only the features of last layer for image classification
x = self.patch_embed(x)
x = self.stages(x)
x = self.avgpool_pre_head(x) # B C 1 1
x = torch.flatten(x, 1)
x = self.head(x)
return x
def forward_det(self, x: Tensor) -> Tensor:
# output the features of four stages for dense prediction
x = self.patch_embed(x)
outs = []
for idx, stage in enumerate(self.stages):
x = stage(x)
if self.fork_feat and idx in self.out_indices:
norm_layer = getattr(self, f'norm{idx}')
x_out = norm_layer(x)
outs.append(x_out)
return outs
第四步：统计训练过程中验证集准确率和loss变化
第五步：搭建GUI界面
第六步：整个工程的内容
有训练代码和训练好的模型以及训练过程，提供数据，提供GUI界面代码
🔥计算机视觉、图像处理、毕业辅导、作业帮助、代码获取，远程协助，代码定制，私聊会回复!
✍🏻作者简介：机器学习，深度学习，卷积神经网络处理，图像处理
🚀B站项目实战：https://space.bilibili.com/364224477
😄 如果文章对你有帮助的话， 欢迎评论 💬点赞👍🏻 收藏 📂加关注+
🤵♂代做需求：@个人主页
全部评论 (0)
还没有任何评论哟~