uber-research / UPSNet

UPSNet: A Unified Panoptic Segmentation Network
Other
648 stars 120 forks source link

Segmentation fault (core dumped) #136

Open AMzhanghan opened 4 years ago

AMzhanghan commented 4 years ago

when I train the UPSNet, used the config of "upsnet/experiments/upsnet_resnet50_coco_4gpu.yaml", I got the problem as:

upsnet/../upsnet/models/resnet.py:285: UserWarning: unexpected key "fc.weight" in state_dict warnings.warn('unexpected key "{}" in state_dict'.format(name)) upsnet/../upsnet/models/resnet.py:285: UserWarning: unexpected key "fc.bias" in state_dict warnings.warn('unexpected key "{}" in state_dict'.format(name)) upsnet/../upsnet/models/resnet.py:299: UserWarning: missing keys in state_dict: "{'resnet_backbone.res2.layers.0.downsample.1.num_batches_tracked', 'resnet_backbone.res4.layers.3.bn1.num_batches_tracked', 'resnet_backbone.conv1.bn1.num_batches_tracked' ..... ..... python3.6/site-packages/torch/nn/functional.py:1006: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead. warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.") Segmentation fault (core dumped)

How to solve this problem? Thanks!

AMzhanghan commented 4 years ago

use_horovod: false ; I was not used the horovod