resnext.py

'''
New for ResNeXt:
1. Wider bottleneck
2. Add group for conv2
'''
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from model.utils.config import cfg
from model.faster_rcnn.faster_rcnn import _fasterRCNN

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import math
import torch.utils.model_zoo as model_zoo
import pdb

__all__ = ['ResNeXt', 'resnext18', 'resnext34', 'resnext50', 'resnext101',
           'resnext152']

# model_urls = {
#   'resnext101_32x4d': 'https://data.lip6.fr/cadene/pretrainedmodels/resnext101_32x4d-29e315fa.pth',
#   'resnext101_64x4d': 'https://data.lip6.fr/cadene/pretrainedmodels/resnext101_64x4d-e77a0586.pth',
# }

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

class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None, num_group=32):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes*2, stride)
        self.bn1 = nn.BatchNorm2d(planes*2)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes*2, planes*2, groups=num_group)
        self.bn2 = nn.BatchNorm2d(planes*2)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None, num_group=32):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes*2, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes*2)
        self.conv2 = nn.Conv2d(planes*2, planes*2, kernel_size=3, stride=stride,
                               padding=1, bias=False, groups=num_group)
        self.bn2 = nn.BatchNorm2d(planes*2)
        self.conv3 = nn.Conv2d(planes*2, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class ResNeXt(nn.Module):

    def __init__(self, block, layers, num_classes=1000, num_group=32):
        self.inplanes = 64
        super(ResNeXt, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0], num_group)
        self.layer2 = self._make_layer(block, 128, layers[1], num_group, stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], num_group, stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], num_group, stride=2)
        self.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, num_group, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample, num_group=num_group))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, num_group=num_group))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x


def resnext18(**kwargs):
    """Constructs a ResNeXt-18 model.
    """
    model = ResNeXt(BasicBlock, [2, 2, 2, 2], **kwargs)
    return model


def resnext34(**kwargs):
    """Constructs a ResNeXt-34 model.
    """
    model = ResNeXt(BasicBlock, [3, 4, 6, 3], **kwargs)
    return model


def resnext50(**kwargs):
    """Constructs a ResNeXt-50 model.
    """
    model = ResNeXt(Bottleneck, [3, 4, 6, 3], **kwargs)
    return model


def resnext101_32x4d(**kwargs):
    """Constructs a ResNeXt-101 model.
    """
    model = ResNeXt(Bottleneck, [3, 4, 23, 3], num_group=32, **kwargs)
    return model

def resnext101_64x4d(**kwargs):
    """Constructs a ResNeXt-101 model.
    """
    model = ResNeXt(Bottleneck, [3, 4, 23, 3], num_group=64, **kwargs)
    return model


def resnext152(**kwargs):
    """Constructs a ResNeXt-152 model.
    """
    model = ResNeXt(Bottleneck, [3, 8, 36, 3], **kwargs)
    return model

class resnext(_fasterRCNN):
  def __init__(self, classes, num_layers=101, pretrained=False, class_agnostic=False):
    #self.model_path = 'data/pretrained_model/resnext101_64x4d-e77a0586.pth'
    self.model_path = 'data/pretrained_model/resnext101_32x4d-29e315fa.pth'
    self.dout_base_model = 1024
    self.pretrained = pretrained
    self.class_agnostic = class_agnostic

    _fasterRCNN.__init__(self, classes, class_agnostic)

  def _init_modules(self):
    #resnext = resnext101_64x4d()   
    resnext = resnext101_32x4d()

    if self.pretrained == True:
      print("Loading pretrained weights from %s" %(self.model_path))
      #state_dict = torch.load(self.model_path)
      #resnext.load_state_dict({k:v for k,v in state_dict.items() if k in resnext.state_dict()})
      pretrained_dict = torch.load(self.model_path)
      new = list(pretrained_dict.items())
      my_model_kvpair = resnext.state_dict() 
      cnt = 0
      for key, value in my_model_kvpair.items():
        layer_name, weights = new[cnt]
        my_model_kvpair[key] = weights
        cnt += 1
      resnext.load_state_dict(my_model_kvpair)     

    # Build resnext.
    self.RCNN_base = nn.Sequential(resnext.conv1, resnext.bn1,resnext.relu,
      resnext.maxpool,resnext.layer1,resnext.layer2,resnext.layer3)

    self.RCNN_top = nn.Sequential(resnext.layer4)

    self.RCNN_cls_score = nn.Linear(2048, self.n_classes)
    if self.class_agnostic:
      self.RCNN_bbox_pred = nn.Linear(2048, 4)
    else:
      self.RCNN_bbox_pred = nn.Linear(2048, 4 * self.n_classes)

    # Fix blocks
    for p in self.RCNN_base[0].parameters(): p.requires_grad=False
    for p in self.RCNN_base[1].parameters(): p.requires_grad=False

    assert (0 <= cfg.RESNEXT.FIXED_BLOCKS < 4)
    if cfg.RESNEXT.FIXED_BLOCKS >= 3:
      for p in self.RCNN_base[6].parameters(): p.requires_grad=False
    if cfg.RESNEXT.FIXED_BLOCKS >= 2:
      for p in self.RCNN_base[5].parameters(): p.requires_grad=False
    if cfg.RESNEXT.FIXED_BLOCKS >= 1:
      for p in self.RCNN_base[4].parameters(): p.requires_grad=False

    def set_bn_fix(m):
      classname = m.__class__.__name__
      if classname.find('BatchNorm') != -1:
        for p in m.parameters(): p.requires_grad=False

    self.RCNN_base.apply(set_bn_fix)
    self.RCNN_top.apply(set_bn_fix)

  def train(self, mode=True):
    # Override train so that the training mode is set as we want
    nn.Module.train(self, mode)
    if mode:
      # Set fixed blocks to be in eval mode
      self.RCNN_base.eval()
      self.RCNN_base[4].train()
      self.RCNN_base[5].train()
      self.RCNN_base[6].train()

      def set_bn_eval(m):
        classname = m.__class__.__name__
        if classname.find('BatchNorm') != -1:
          m.eval()

      self.RCNN_base.apply(set_bn_eval)
      self.RCNN_top.apply(set_bn_eval)

  def _head_to_tail(self, pool5):
    fc7 = self.RCNN_top(pool5).mean(3).mean(2)
    return fc7