lib/pymafx/models/hr_module.py

import logging
import os

import torch
import torch._utils
import torch.nn as nn
import torch.nn.functional as F

# from core.cfgs import cfg
from .res_module import BasicBlock, Bottleneck

logger = logging.getLogger(__name__)

BN_MOMENTUM = 0.1


class HighResolutionModule(nn.Module):
    def __init__(
        self,
        num_branches,
        blocks,
        num_blocks,
        num_inchannels,
        num_channels,
        fuse_method,
        multi_scale_output=True
    ):
        super().__init__()
        self._check_branches(num_branches, blocks, num_blocks, num_inchannels, num_channels)

        self.num_inchannels = num_inchannels
        self.fuse_method = fuse_method
        self.num_branches = num_branches

        self.multi_scale_output = multi_scale_output

        self.branches = self._make_branches(num_branches, blocks, num_blocks, num_channels)
        self.fuse_layers = self._make_fuse_layers()
        self.relu = nn.ReLU(True)

    def _check_branches(self, num_branches, blocks, num_blocks, num_inchannels, num_channels):
        if num_branches != len(num_blocks):
            error_msg = 'NUM_BRANCHES({}) <> NUM_BLOCKS({})'.format(num_branches, len(num_blocks))
            logger.error(error_msg)
            raise ValueError(error_msg)

        if num_branches != len(num_channels):
            error_msg = 'NUM_BRANCHES({}) <> NUM_CHANNELS({})'.format(
                num_branches, len(num_channels)
            )
            logger.error(error_msg)
            raise ValueError(error_msg)

        if num_branches != len(num_inchannels):
            error_msg = 'NUM_BRANCHES({}) <> NUM_INCHANNELS({})'.format(
                num_branches, len(num_inchannels)
            )
            logger.error(error_msg)
            raise ValueError(error_msg)

    def _make_one_branch(self, branch_index, block, num_blocks, num_channels, stride=1):
        downsample = None
        if stride != 1 or \
           self.num_inchannels[branch_index] != num_channels[branch_index] * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(
                    self.num_inchannels[branch_index],
                    num_channels[branch_index] * block.expansion,
                    kernel_size=1,
                    stride=stride,
                    bias=False
                ),
                nn.BatchNorm2d(num_channels[branch_index] * block.expansion, momentum=BN_MOMENTUM),
            )

        layers = []
        layers.append(
            block(
                self.num_inchannels[branch_index], num_channels[branch_index], stride, downsample
            )
        )
        self.num_inchannels[branch_index] = \
            num_channels[branch_index] * block.expansion
        for i in range(1, num_blocks[branch_index]):
            layers.append(block(self.num_inchannels[branch_index], num_channels[branch_index]))

        return nn.Sequential(*layers)

    def _make_branches(self, num_branches, block, num_blocks, num_channels):
        branches = []

        for i in range(num_branches):
            branches.append(self._make_one_branch(i, block, num_blocks, num_channels))

        return nn.ModuleList(branches)

    def _make_fuse_layers(self):
        if self.num_branches == 1:
            return None

        num_branches = self.num_branches
        num_inchannels = self.num_inchannels
        fuse_layers = []
        for i in range(num_branches if self.multi_scale_output else 1):
            fuse_layer = []
            for j in range(num_branches):
                if j > i:
                    fuse_layer.append(
                        nn.Sequential(
                            nn.Conv2d(num_inchannels[j], num_inchannels[i], 1, 1, 0, bias=False),
                            nn.BatchNorm2d(num_inchannels[i]),
                            nn.Upsample(scale_factor=2**(j - i), mode='nearest')
                        )
                    )
                elif j == i:
                    fuse_layer.append(None)
                else:
                    conv3x3s = []
                    for k in range(i - j):
                        if k == i - j - 1:
                            num_outchannels_conv3x3 = num_inchannels[i]
                            conv3x3s.append(
                                nn.Sequential(
                                    nn.Conv2d(
                                        num_inchannels[j],
                                        num_outchannels_conv3x3,
                                        3,
                                        2,
                                        1,
                                        bias=False
                                    ), nn.BatchNorm2d(num_outchannels_conv3x3)
                                )
                            )
                        else:
                            num_outchannels_conv3x3 = num_inchannels[j]
                            conv3x3s.append(
                                nn.Sequential(
                                    nn.Conv2d(
                                        num_inchannels[j],
                                        num_outchannels_conv3x3,
                                        3,
                                        2,
                                        1,
                                        bias=False
                                    ), nn.BatchNorm2d(num_outchannels_conv3x3), nn.ReLU(True)
                                )
                            )
                    fuse_layer.append(nn.Sequential(*conv3x3s))
            fuse_layers.append(nn.ModuleList(fuse_layer))

        return nn.ModuleList(fuse_layers)

    def get_num_inchannels(self):
        return self.num_inchannels

    def forward(self, x):
        if self.num_branches == 1:
            return [self.branches[0](x[0])]

        for i in range(self.num_branches):
            x[i] = self.branches[i](x[i])

        x_fuse = []

        for i in range(len(self.fuse_layers)):
            y = x[0] if i == 0 else self.fuse_layers[i][0](x[0])
            for j in range(1, self.num_branches):
                if i == j:
                    y = y + x[j]
                else:
                    y = y + self.fuse_layers[i][j](x[j])
            x_fuse.append(self.relu(y))

        return x_fuse


blocks_dict = {'BASIC': BasicBlock, 'BOTTLENECK': Bottleneck}


class PoseHighResolutionNet(nn.Module):
    def __init__(self, cfg, pretrained=True, global_mode=False):
        self.inplanes = 64
        extra = cfg.HR_MODEL.EXTRA
        super().__init__()

        # stem net
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64, momentum=BN_MOMENTUM)
        self.conv2 = nn.Conv2d(64, 64, kernel_size=3, stride=2, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(64, momentum=BN_MOMENTUM)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self._make_layer(Bottleneck, self.inplanes, 64, 4)

        self.stage2_cfg = cfg['HR_MODEL']['EXTRA']['STAGE2']
        num_channels = self.stage2_cfg['NUM_CHANNELS']
        block = blocks_dict[self.stage2_cfg['BLOCK']]
        num_channels = [num_channels[i] * block.expansion for i in range(len(num_channels))]
        self.transition1 = self._make_transition_layer([256], num_channels)
        self.stage2, pre_stage_channels = self._make_stage(self.stage2_cfg, num_channels)

        self.stage3_cfg = cfg['HR_MODEL']['EXTRA']['STAGE3']
        num_channels = self.stage3_cfg['NUM_CHANNELS']
        block = blocks_dict[self.stage3_cfg['BLOCK']]
        num_channels = [num_channels[i] * block.expansion for i in range(len(num_channels))]
        self.transition2 = self._make_transition_layer(pre_stage_channels, num_channels)
        self.stage3, pre_stage_channels = self._make_stage(self.stage3_cfg, num_channels)

        self.stage4_cfg = cfg['HR_MODEL']['EXTRA']['STAGE4']
        num_channels = self.stage4_cfg['NUM_CHANNELS']
        block = blocks_dict[self.stage4_cfg['BLOCK']]
        num_channels = [num_channels[i] * block.expansion for i in range(len(num_channels))]
        self.transition3 = self._make_transition_layer(pre_stage_channels, num_channels)
        self.stage4, pre_stage_channels = self._make_stage(
            self.stage4_cfg, num_channels, multi_scale_output=True
        )

        # Classification Head
        self.global_mode = global_mode
        if self.global_mode:
            self.incre_modules, self.downsamp_modules, \
            self.final_layer = self._make_head(pre_stage_channels)

        self.pretrained_layers = cfg['HR_MODEL']['EXTRA']['PRETRAINED_LAYERS']

    def _make_head(self, pre_stage_channels):
        head_block = Bottleneck
        head_channels = [32, 64, 128, 256]

        # Increasing the #channels on each resolution
        # from C, 2C, 4C, 8C to 128, 256, 512, 1024
        incre_modules = []
        for i, channels in enumerate(pre_stage_channels):
            incre_module = self._make_layer(head_block, channels, head_channels[i], 1, stride=1)
            incre_modules.append(incre_module)
        incre_modules = nn.ModuleList(incre_modules)

        # downsampling modules
        downsamp_modules = []
        for i in range(len(pre_stage_channels) - 1):
            in_channels = head_channels[i] * head_block.expansion
            out_channels = head_channels[i + 1] * head_block.expansion

            downsamp_module = nn.Sequential(
                nn.Conv2d(
                    in_channels=in_channels,
                    out_channels=out_channels,
                    kernel_size=3,
                    stride=2,
                    padding=1
                ), nn.BatchNorm2d(out_channels, momentum=BN_MOMENTUM), nn.ReLU(inplace=True)
            )

            downsamp_modules.append(downsamp_module)
        downsamp_modules = nn.ModuleList(downsamp_modules)

        final_layer = nn.Sequential(
            nn.Conv2d(
                in_channels=head_channels[3] * head_block.expansion,
                out_channels=2048,
                kernel_size=1,
                stride=1,
                padding=0
            ), nn.BatchNorm2d(2048, momentum=BN_MOMENTUM), nn.ReLU(inplace=True)
        )

        return incre_modules, downsamp_modules, final_layer

    def _make_transition_layer(self, num_channels_pre_layer, num_channels_cur_layer):
        num_branches_cur = len(num_channels_cur_layer)
        num_branches_pre = len(num_channels_pre_layer)

        transition_layers = []
        for i in range(num_branches_cur):
            if i < num_branches_pre:
                if num_channels_cur_layer[i] != num_channels_pre_layer[i]:
                    transition_layers.append(
                        nn.Sequential(
                            nn.Conv2d(
                                num_channels_pre_layer[i],
                                num_channels_cur_layer[i],
                                3,
                                1,
                                1,
                                bias=False
                            ), nn.BatchNorm2d(num_channels_cur_layer[i]), nn.ReLU(inplace=True)
                        )
                    )
                else:
                    transition_layers.append(None)
            else:
                conv3x3s = []
                for j in range(i + 1 - num_branches_pre):
                    inchannels = num_channels_pre_layer[-1]
                    outchannels = num_channels_cur_layer[i] \
                        if j == i-num_branches_pre else inchannels
                    conv3x3s.append(
                        nn.Sequential(
                            nn.Conv2d(inchannels, outchannels, 3, 2, 1, bias=False),
                            nn.BatchNorm2d(outchannels), nn.ReLU(inplace=True)
                        )
                    )
                transition_layers.append(nn.Sequential(*conv3x3s))

        return nn.ModuleList(transition_layers)

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

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

        return nn.Sequential(*layers)

    def _make_stage(self, layer_config, num_inchannels, multi_scale_output=True):
        num_modules = layer_config['NUM_MODULES']
        num_branches = layer_config['NUM_BRANCHES']
        num_blocks = layer_config['NUM_BLOCKS']
        num_channels = layer_config['NUM_CHANNELS']
        block = blocks_dict[layer_config['BLOCK']]
        fuse_method = layer_config['FUSE_METHOD']

        modules = []
        for i in range(num_modules):
            # multi_scale_output is only used last module
            if not multi_scale_output and i == num_modules - 1:
                reset_multi_scale_output = False
            else:
                reset_multi_scale_output = True

            modules.append(
                HighResolutionModule(
                    num_branches, block, num_blocks, num_inchannels, num_channels, fuse_method,
                    reset_multi_scale_output
                )
            )
            num_inchannels = modules[-1].get_num_inchannels()

        return nn.Sequential(*modules), num_inchannels

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.conv2(x)
        x = self.bn2(x)
        x = self.relu(x)
        x = self.layer1(x)

        x_list = []
        for i in range(self.stage2_cfg['NUM_BRANCHES']):
            if self.transition1[i] is not None:
                x_list.append(self.transition1[i](x))
            else:
                x_list.append(x)
        y_list = self.stage2(x_list)

        s_feat_s2 = y_list[0]

        x_list = []
        for i in range(self.stage3_cfg['NUM_BRANCHES']):
            if self.transition2[i] is not None:
                x_list.append(self.transition2[i](y_list[-1]))
            else:
                x_list.append(y_list[i])
        y_list = self.stage3(x_list)

        s_feat_s3 = y_list[0]

        x_list = []
        for i in range(self.stage4_cfg['NUM_BRANCHES']):
            if self.transition3[i] is not None:
                x_list.append(self.transition3[i](y_list[-1]))
            else:
                x_list.append(y_list[i])
        y_list = self.stage4(x_list)

        s_feat = [y_list[-2], y_list[-3], y_list[-4]]

        # s_feat_s4 = y_list[0]

        # if cfg.MODEL.PyMAF.HR_FEAT_STAGE == 2:
        #     s_feat = s_feat_s2
        # elif cfg.MODEL.PyMAF.HR_FEAT_STAGE == 3:
        #     s_feat = s_feat_s3
        # elif cfg.MODEL.PyMAF.HR_FEAT_STAGE == 4:
        #     s_feat = s_feat_s4
        # else:
        #     raise ValueError('HR_FEAT_STAGE should be 2, 3, or 4.')

        # Classification Head
        if self.global_mode:
            y = self.incre_modules[0](y_list[0])
            for i in range(len(self.downsamp_modules)):
                y = self.incre_modules[i + 1](y_list[i + 1]) + \
                    self.downsamp_modules[i](y)

            y = self.final_layer(y)

            if torch._C._get_tracing_state():
                xf = y.flatten(start_dim=2).mean(dim=2)
            else:
                xf = F.avg_pool2d(y, kernel_size=y.size()[2:]).view(y.size(0), -1)
        else:
            xf = None

        return s_feat, xf

    def init_weights(self, pretrained=''):
        # logger.info('=> init weights from normal distribution')
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                nn.init.normal_(m.weight, std=0.001)
                for name, _ in m.named_parameters():
                    if name in ['bias']:
                        nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.ConvTranspose2d):
                nn.init.normal_(m.weight, std=0.001)
                for name, _ in m.named_parameters():
                    if name in ['bias']:
                        nn.init.constant_(m.bias, 0)

        if os.path.isfile(pretrained):
            pretrained_state_dict = torch.load(pretrained)
            # logger.info('=> loading pretrained HRnet model {}'.format(pretrained))

            need_init_state_dict = {}
            for name, m in pretrained_state_dict.items():
                if name.split('.')[0] in self.pretrained_layers \
                   or self.pretrained_layers[0] is '*':
                    need_init_state_dict[name] = m
            self.load_state_dict(need_init_state_dict, strict=False)
        elif pretrained:
            logger.error('=> please download pre-trained models first!')
            raise ValueError('{} is not exist!'.format(pretrained))


def get_hrnet_encoder(cfg, init_weight=True, global_mode=False, **kwargs):
    model = PoseHighResolutionNet(cfg, global_mode=global_mode)

    if init_weight:
        if cfg.HR_MODEL.PRETR_SET in ['imagenet']:
            model.init_weights(cfg.HR_MODEL.PRETRAINED_IM)
            logger.info('loaded HRNet imagenet pretrained model')
        elif cfg.HR_MODEL.PRETR_SET in ['coco']:
            model.init_weights(cfg.HR_MODEL.PRETRAINED_COCO)
            logger.info('loaded HRNet coco pretrained model')
        else:
            model.init_weights()

    return model