pytorch_预训练vggm_自定义类别数量_源码分享

系列文章目录

9种经典图片分类卷积模型系列合集（推荐程度依次递减）：

Imagenet的预训练vggm是1000个类别，根据笔者添加了一个bottleneck层和一个head层使得可以进行自定义类别训练。

源码

from __future__ import print_function, division, absolute_import
import torch
import torch.nn as nn
from torch.autograd import Variable
# from torch.legacy import nn as nnl
import torch.utils.model_zoo as model_zoo

__all__ = ['vggm']

pretrained_settings = {
   
   
    'vggm': {
   
   
        True: {
   
   
            'url': 'http://data.lip6.fr/cadene/pretrainedmodels/vggm-786f2434.pth',
            'input_space': 'BGR',
            'input_size': [3, 221, 221],
            'input_range': [0, 255],
            'mean': [123.68, 116.779, 103.939],
            'std': [1, 1, 1],
            'num_classes': 1000
        }
    }
}


def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=dilation, groups=groups, bias=False, dilation=dilation)


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)


class BasicBlock(nn.Module):
    expansion = 1
    __constants__ = ['downsample']

    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
                 base_width=64, dilation=1, norm_layer=None):
        super(BasicBlock, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

        out = self