taohan10200 / IIM

PyTorch implementations of the paper: "Learning Independent Instance Maps for Crowd Localization"
MIT License
169 stars 41 forks source link

主页给的HRNet权重链接hrnetv2_w48_imagenet_pretrained.pth和Crowd_locator中模型结构不太一样 #34

Open xiong224 opened 1 year ago

xiong224 commented 1 year ago

RuntimeError: Error(s) in loading state_dict for Crowd_locator: Missing key(s) in state_dict: "Extractor.last_layer.0.weight", "Extractor.last_layer.0.bias", "Extractor.last_layer.1.weight", "Extractor.last_layer.1.bias", "Extractor.last_layer.1.running_mean", "Extractor.last_layer.1.running_var", "Extractor.last_layer.3.weight", "Extractor.last_layer.3.bias", "Extractor.last_layer.5.weight", "Extractor.last_layer.5.bias", "Binar.weight", "Binar.bias", "Binar.Threshold_Module.0.weight", "Binar.Threshold_Module.1.weight", "Binar.Threshold_Module.2.weight", "Binar.Threshold_Module.3.weight", "Binar.Threshold_Module.4.weight", "Binar.Threshold_Module.5.weight", "Binar.Threshold_Module.7.weight". Unexpected key(s) in state_dict: "Extractor.incre_modules.0.0.conv1.weight", "Extractor.incre_modules.0.0.bn1.weight", "Extractor.incre_modules.0.0.bn1.bias", "Extractor.incre_modules.0.0.bn1.running_mean", "Extractor.incre_modules.0.0.bn1.running_var", "Extractor.incre_modules.0.0.bn1.num_batches_tracked", "Extractor.incre_modules.0.0.conv2.weight", "Extractor.incre_modules.0.0.bn2.weight", "Extractor.incre_modules.0.0.bn2.bias", "Extractor.incre_modules.0.0.bn2.running_mean", "Extractor.incre_modules.0.0.bn2.running_var", "Extractor.incre_modules.0.0.bn2.num_batches_tracked", "Extractor.incre_modules.0.0.conv3.weight", "Extractor.incre_modules.0.0.bn3.weight", "Extractor.incre_modules.0.0.bn3.bias", "Extractor.incre_modules.0.0.bn3.running_mean", "Extractor.incre_modules.0.0.bn3.running_var", "Extractor.incre_modules.0.0.bn3.num_batches_tracked", "Extractor.incre_modules.0.0.downsample.0.weight", "Extractor.incre_modules.0.0.downsample.1.weight", "Extractor.incre_modules.0.0.downsample.1.bias", "Extractor.incre_modules.0.0.downsample.1.running_mean", "Extractor.incre_modules.0.0.downsample.1.running_var", "Extractor.incre_modules.0.0.downsample.1.num_batches_tracked", "Extractor.incre_modules.1.0.conv1.weight", "Extractor.incre_modules.1.0.bn1.weight", "Extractor.incre_modules.1.0.bn1.bias", "Extractor.incre_modules.1.0.bn1.running_mean", "Extractor.incre_modules.1.0.bn1.running_var", "Extractor.incre_modules.1.0.bn1.num_batches_tracked", "Extractor.incre_modules.1.0.conv2.weight", "Extractor.incre_modules.1.0.bn2.weight", "Extractor.incre_modules.1.0.bn2.bias", "Extractor.incre_modules.1.0.bn2.running_mean", "Extractor.incre_modules.1.0.bn2.running_var", "Extractor.incre_modules.1.0.bn2.num_batches_tracked", "Extractor.incre_modules.1.0.conv3.weight", "Extractor.incre_modules.1.0.bn3.weight", "Extractor.incre_modules.1.0.bn3.bias", "Extractor.incre_modules.1.0.bn3.running_mean", "Extractor.incre_modules.1.0.bn3.running_var", "Extractor.incre_modules.1.0.bn3.num_batches_tracked", "Extractor.incre_modules.1.0.downsample.0.weight", "Extractor.incre_modules.1.0.downsample.1.weight", "Extractor.incre_modules.1.0.downsample.1.bias", "Extractor.incre_modules.1.0.downsample.1.running_mean", "Extractor.incre_modules.1.0.downsample.1.running_var", "Extractor.incre_modules.1.0.downsample.1.num_batches_tracked", "Extractor.incre_modules.2.0.conv1.weight", "Extractor.incre_modules.2.0.bn1.weight", "Extractor.incre_modules.2.0.bn1.bias", "Extractor.incre_modules.2.0.bn1.running_mean", "Extractor.incre_modules.2.0.bn1.running_var", "Extractor.incre_modules.2.0.bn1.num_batches_tracked", "Extractor.incre_modules.2.0.conv2.weight", "Extractor.incre_modules.2.0.bn2.weight", "Extractor.incre_modules.2.0.bn2.bias", "Extractor.incre_modules.2.0.bn2.running_mean", "Extractor.incre_modules.2.0.bn2.running_var", "Extractor.incre_modules.2.0.bn2.num_batches_tracked", "Extractor.incre_modules.2.0.conv3.weight", "Extractor.incre_modules.2.0.bn3.weight", "Extractor.incre_modules.2.0.bn3.bias", "Extractor.incre_modules.2.0.bn3.running_mean", "Extractor.incre_modules.2.0.bn3.running_var", "Extractor.incre_modules.2.0.bn3.num_batches_tracked", "Extractor.incre_modules.2.0.downsample.0.weight", "Extractor.incre_modules.2.0.downsample.1.weight", "Extractor.incre_modules.2.0.downsample.1.bias", "Extractor.incre_modules.2.0.downsample.1.running_mean", "Extractor.incre_modules.2.0.downsample.1.running_var", "Extractor.incre_modules.2.0.downsample.1.num_batches_tracked", "Extractor.incre_modules.3.0.conv1.weight", "Extractor.incre_modules.3.0.bn1.weight", "Extractor.incre_modules.3.0.bn1.bias", "Extractor.incre_modules.3.0.bn1.running_mean", "Extractor.incre_modules.3.0.bn1.running_var", "Extractor.incre_modules.3.0.bn1.num_batches_tracked", "Extractor.incre_modules.3.0.conv2.weight", "Extractor.incre_modules.3.0.bn2.weight", "Extractor.incre_modules.3.0.bn2.bias", "Extractor.incre_modules.3.0.bn2.running_mean", "Extractor.incre_modules.3.0.bn2.running_var", "Extractor.incre_modules.3.0.bn2.num_batches_tracked", "Extractor.incre_modules.3.0.conv3.weight", "Extractor.incre_modules.3.0.bn3.weight", "Extractor.incre_modules.3.0.bn3.bias", "Extractor.incre_modules.3.0.bn3.running_mean", "Extractor.incre_modules.3.0.bn3.running_var", "Extractor.incre_modules.3.0.bn3.num_batches_tracked", "Extractor.incre_modules.3.0.downsample.0.weight", "Extractor.incre_modules.3.0.downsample.1.weight", "Extractor.incre_modules.3.0.downsample.1.bias", "Extractor.incre_modules.3.0.downsample.1.running_mean", "Extractor.incre_modules.3.0.downsample.1.running_var", "Extractor.incre_modules.3.0.downsample.1.num_batches_tracked", "Extractor.downsamp_modules.0.0.weight", "Extractor.downsamp_modules.0.0.bias", "Extractor.downsamp_modules.0.1.weight", "Extractor.downsamp_modules.0.1.bias", "Extractor.downsamp_modules.0.1.running_mean", "Extractor.downsamp_modules.0.1.running_var", "Extractor.downsamp_modules.0.1.num_batches_tracked", "Extractor.downsamp_modules.1.0.weight", "Extractor.downsamp_modules.1.0.bias", "Extractor.downsamp_modules.1.1.weight", "Extractor.downsamp_modules.1.1.bias", "Extractor.downsamp_modules.1.1.running_mean", "Extractor.downsamp_modules.1.1.running_var", "Extractor.downsamp_modules.1.1.num_batches_tracked", "Extractor.downsamp_modules.2.0.weight", "Extractor.downsamp_modules.2.0.bias", "Extractor.downsamp_modules.2.1.weight", "Extractor.downsamp_modules.2.1.bias", "Extractor.downsamp_modules.2.1.running_mean", "Extractor.downsamp_modules.2.1.running_var", "Extractor.downsamp_modules.2.1.num_batches_tracked", "Extractor.final_layer.0.weight", "Extractor.final_layer.0.bias", "Extractor.final_layer.1.weight", "Extractor.final_layer.1.bias", "Extractor.final_layer.1.running_mean", "Extractor.final_layer.1.running_var", "Extractor.final_layer.1.num_batches_tracked", "Extractor.classifier.weight", "Extractor.classifier.bias".

taohan10200 commented 1 year ago

HRNet is only the backbone. There are other modules in Extractor, so you cannot load the Pretrained HRNet to initialize the whole model.

JackComputer553 commented 4 days ago

Chinese:知道怎么详细解决这个问题了吗? English:Do you have tackled this problem?