search

open-mmlab / mmrotate

OpenMMLab Rotated Object Detection Toolbox and Benchmark
https://mmrotate.readthedocs.io/en/latest/
Apache License 2.0
1.88k stars 559 forks source link

TypeError: S2ANet: MobileNet: __init__() got an unexpected keyword argument 'pretrained' #224

Closed milamiqi closed 2 years ago

milamiqi commented 2 years ago

I used mobilenet's backbone in s2anet, but the following error will be reported. This is my settings and mobilenet's file

https://github.com/xiaolai-sqlai/mobilenetv3

    type='S2ANet',
    backbone=dict(
        type='MobileNet',
),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_input',
        num_outs=5),

I have imported the corresponding library in mobilenet and used @ROTATED_BACKBONES.register_module()

milamiqi commented 2 years ago 
import torch.nn as nn

from mmrotate.models.builder import ROTATED_BACKBONES

import torch.nn.functional as F
from torch.nn import init

class hswish(nn.Module):
    def forward(self, x):
        out = x * F.relu6(x + 3, inplace=True) / 6
        return out

class hsigmoid(nn.Module):
    def forward(self, x):
        out = F.relu6(x + 3, inplace=True) / 6
        return out

class SeModule(nn.Module):
    def __init__(self, in_size, reduction=4):
        super(SeModule, self).__init__()
        self.se = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(in_size, in_size // reduction, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(in_size // reduction),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_size // reduction, in_size, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(in_size),
            hsigmoid()
        )

    def forward(self, x):
        return x * self.se(x)

class Block(nn.Module):
    '''expand + depthwise + pointwise'''
    def __init__(self, kernel_size, in_size, expand_size, out_size, nolinear, semodule, stride):
        super(Block, self).__init__()
        self.stride = stride
        self.se = semodule

        self.conv1 = nn.Conv2d(in_size, expand_size, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn1 = nn.BatchNorm2d(expand_size)
        self.nolinear1 = nolinear
        self.conv2 = nn.Conv2d(expand_size, expand_size, kernel_size=kernel_size, stride=stride, padding=kernel_size//2, groups=expand_size, bias=False)
        self.bn2 = nn.BatchNorm2d(expand_size)
        self.nolinear2 = nolinear
        self.conv3 = nn.Conv2d(expand_size, out_size, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn3 = nn.BatchNorm2d(out_size)

        self.shortcut = nn.Sequential()
        if stride == 1 and in_size != out_size:
            self.shortcut = nn.Sequential(
                nn.Conv2d(in_size, out_size, kernel_size=1, stride=1, padding=0, bias=False),
                nn.BatchNorm2d(out_size),
            )

    def forward(self, x):
        out = self.nolinear1(self.bn1(self.conv1(x)))
        out = self.nolinear2(self.bn2(self.conv2(out)))
        out = self.bn3(self.conv3(out))
        if self.se != None:
            out = self.se(out)
        out = out + self.shortcut(x) if self.stride==1 else out
        return out
@ROTATED_BACKBONES.register_module()
class MobileNet(nn.Module):
    def __init__(self, num_classes=1000):
        super(MobileNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=2, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(16)
        self.hs1 = hswish()
        self.bneck = nn.Sequential(
            Block(3, 16, 16, 16, nn.ReLU(inplace=True), SeModule(16), 2),
            Block(3, 16, 72, 24, nn.ReLU(inplace=True), None, 2),
            Block(3, 24, 88, 24, nn.ReLU(inplace=True), None, 1),
            Block(5, 24, 96, 40, hswish(), SeModule(40), 2),
            Block(5, 40, 240, 40, hswish(), SeModule(40), 1),
            Block(5, 40, 240, 40, hswish(), SeModule(40), 1),
            Block(5, 40, 120, 48, hswish(), SeModule(48), 1),
            Block(5, 48, 144, 48, hswish(), SeModule(48), 1),
            Block(5, 48, 288, 96, hswish(), SeModule(96), 2),
            Block(5, 96, 576, 96, hswish(), SeModule(96), 1),
            Block(5, 96, 576, 96, hswish(), SeModule(96), 1),
        )

        self.conv2 = nn.Conv2d(96, 576, kernel_size=1, stride=1, padding=0, bias=False)
        self.bn2 = nn.BatchNorm2d(576)
        self.hs2 = hswish()
        self.linear3 = nn.Linear(576, 1280)
        self.bn3 = nn.BatchNorm1d(1280)
        self.hs3 = hswish()
        self.linear4 = nn.Linear(1280, num_classes)
        self.init_params()

    def init_params(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal_(m.weight, mode='fan_out')
                if m.bias is not None:
                    init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                init.constant_(m.weight, 1)
                init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                init.normal_(m.weight, std=0.001)
                if m.bias is not None:
                    init.constant_(m.bias, 0)

    def forward(self, x):
        out = self.hs1(self.bn1(self.conv1(x)))
        out = self.bneck(out)
        out = self.hs2(self.bn2(self.conv2(out)))
        out = F.avg_pool2d(out, 7)
        out = out.view(out.size(0), -1)
        out = self.hs3(self.bn3(self.linear3(out)))
        out = self.linear4(out)
        return out

THIS IS MOBILENET

yangxue0827 commented 2 years ago

Some references: https://github.com/open-mmlab/mmdetection/pull/7586 https://github.com/open-mmlab/mmdetection/pull/5122

zytx121 commented 2 years ago

It's Cool! @milamiqi

You could try to add _delete_=True in your config, just like:

    backbone=dict(
         _delete_=True,
        type='MobileNet'
    ),

Refer to https://mmdetection.readthedocs.io/en/latest/tutorials/config.html#ignore-some-fields-in-the-base-configs

yangxue0827 commented 2 years ago

You are welcome to add mobilenet usage examples to mmrotate via PR. @milamiqi

milamiqi commented 2 years ago

It's Cool! @milamiqi

You could try to add _delete_=True in your config, just like:

    backbone=dict(
         _delete_=True,
        type='MobileNet'
    ),

Refer to https://mmdetection.readthedocs.io/en/latest/tutorials/config.html#ignore-some-fields-in-the-base-configs

but new problem appear RuntimeError: mat1 and mat2 shapes cannot be multiplied (2x9216 and 576x1280)

@ROTATED_BACKBONES.register_module() class MobileNet(nn.Module): def init(self, num_classes=1000,pretrained=None): super(MobileNet, self).init() self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=2, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(16) self.hs1 = hswish() self.bneck = nn.Sequential( Block(3, 16, 16, 16, nn.ReLU(inplace=True), SeModule(16), 2), Block(3, 16, 72, 24, nn.ReLU(inplace=True), None, 2), Block(3, 24, 88, 24, nn.ReLU(inplace=True), None, 1), Block(5, 24, 96, 40, hswish(), SeModule(40), 2), Block(5, 40, 240, 40, hswish(), SeModule(40), 1), Block(5, 40, 240, 40, hswish(), SeModule(40), 1), Block(5, 40, 120, 48, hswish(), SeModule(48), 1), Block(5, 48, 144, 48, hswish(), SeModule(48), 1), Block(5, 48, 288, 96, hswish(), SeModule(96), 2), Block(5, 96, 576, 96, hswish(), SeModule(96), 1), Block(5, 96, 576, 96, hswish(), SeModule(96), 1), )

    self.conv2 = nn.Conv2d(96, 576, kernel_size=1, stride=1, padding=0, bias=False)
    self.bn2 = nn.BatchNorm2d(576)
    self.hs2 = hswish()
    self.linear3 = nn.Linear(576, 1280)
    self.bn3 = nn.BatchNorm1d(1280)
    self.hs3 = hswish()
    self.linear4 = nn.Linear(1280, num_classes)
    self.init_params()

def init_params(self):
    for m in self.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal_(m.weight, mode='fan_out')
            if m.bias is not None:
                init.constant_(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant_(m.weight, 1)
            init.constant_(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal_(m.weight, std=0.001)
            if m.bias is not None:
                init.constant_(m.bias, 0)

thisis my mobile net

milamiqi commented 2 years ago 
def forward(self, x):
    out = self.hs1(self.bn1(self.conv1(x)))
    out = self.bneck(out)
    out = self.hs2(self.bn2(self.conv2(out)))
    out = F.avg_pool2d(out, 7)
    out = out.view(out.size(0), -1)
    # out = out.view(576,1280)
    out = self.hs3(self.bn3(self.linear3(out)))
    out = self.linear4(out)
    return out