load state dict error during traininig

[Xi CHEN]

I runned your training scripts of res-50 and res-34.
after automatically downloading gluonweight.pth and master.zip, an error comes

File "train.py", line 69, in [64/907] main()
File "train.py", line 16, in main
model_script.main(cfg)
File "models/sbd/r50_dh128.py", line 23, in main
model, model_cfg = init_model(cfg)
File "models/sbd/r50_dh128.py", line 46, in init_model
model.feature_extractor.load_pretrained_weights()
File "/home/xx/data/workspace/interactive_seg/click_base/fbrs_interactive_segmentation/isegm/model/modeling/deeplab_v3.py", line 53, in load_pretrained_weights
norm_layer=self.backbone_norm_layer, **self._kwargs)
File "/home/xx/data/workspace/interactive_seg/click_base/fbrs_interactive_segmentation/isegm/model/modeling/resnet.py", line 12, in init
pretrained = resnet50_v1s(pretrained=pretrained_base, dilated=dilated, **kwargs)
File "/home/xx/data/workspace/interactive_seg/click_base/fbrs_interactive_segmentation/isegm/model/modeling/resnetv1b.py", line 245, in resnet50_v1s
torch.hub.load(GLUON_RESNET_TORCH_HUB, 'gluon_resnet50_v1s', pretrained=True).state_dict(),
File "/home/xx/anaconda3/envs/py36/lib/python3.6/site-packages/torch/hub.py", line 369, in load
model = entry(*args, **kwargs)
File "/home/xx/.cache/torch/hub/rwightman_pytorch-pretrained-gluonresnet_master/gluon_resnet.py", line 608, in gluon_resnet50_v1s
load_state_dict_from_url(model_urls['gluon_resnet50_v1s']))
File "/home/xx/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 847, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for GluonResNet:
Missing key(s) in state_dict: "conv1.0.weight", "conv1.1.weight", "conv1.1.bias", "conv1.1.running_mean", "conv1.1.running_var", "conv1.3.weight", "conv1.4.weight", "conv1.4.bias", "conv1.4.running_mean", "conv1.4.running_var", "conv1.6.weight", "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "layer1.0.conv1.weight", "layer1.0.bn1.weight", "layer1.0.bn1.bias", "layer1.0.bn1.running_mean", "layer1.0.bn1.running_var", "layer1.0.conv2.weight", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.0.conv3.weight", "layer1.0.bn3.weight", "layer1.0.bn3.bias", "layer1.0.bn3.running_mean", "layer1.0.bn3.running_var", "layer1.0.downsample.0.weight", "layer1.0.downsample.1.weight", "layer1.0.downsample.1.bias", "layer1.0.downsample.1.running_mean", "layer1.0.downsample.1.running_var", "layer1.1.conv1.weight", "layer1.1.bn1.weight", "layer1.1.bn1.bias", "layer1.1.bn1.running_mean", "layer1.1.bn1.running_var", "layer1.1.conv2.weight", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.1.bn2.running_mean" .........

[Petrov Ilya]

Please clear pytorch downloaded cache and check that pytorch version is >= 1.4.0 . I have just tried running training for both r34 and r50 and all models were loaded successfully.