The ResNext models trained with billion scale weakly-supervised data. Please refer to Exploring the Limits of Weakly Supervised Pretraining presented at ECCV 2018 for the details of model training. The Caffe models are converted from PyTorch.
A problem will be encountered when converting the largest model ResNeXt-101 32x48d. If you have enough space to make it work, welcome to contribute.
Transform Completed
[libprotobuf FATAL google/protobuf/wire_format.cc:752] CHECK failed: (output->ByteCount()) == (expected_endpoint): : Protocol message serialized to a size different from what was originally expected. Perhaps it was modified by another thread during serialization?terminate called after throwing an instance of 'google::protobuf::FatalException'
what(): CHECK failed: (output->ByteCount()) == (expected_endpoint): : Protocol message serialized to a size different from what was originally expected. Perhaps it was modified by another thread during serialization?Aborted (core dumped)