import os import torch import torch.nn as nn import torch._utils import torch.nn.functional as F # from core.cfgs import cfg from .res_module import BasicBlock, Bottleneck import logging 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