hzxie / RMNet

The official implementation of "Efficient Regional Memory Network for Video Object Segmentation". (Xie et al., CVPR 2021)

https://haozhexie.com/project/rmnet/

hzxie/RMNet Issues

Caught TypeError in DataLoader worker process 0 in DataLoader
Updated 3 months ago3
About training process
Closed 7 months ago1
Why does the runner.py of RMNet do not train TinyFlowNet?
Closed 7 months ago1
Does Table 5 consider the computing time of optical flow?
Closed 7 months ago1
RMNet26？
Closed 2 years ago1
About RegionalAttentionMapGenerator()
Closed 3 years ago1
"RuntimeError: Error compiling objects for extension" when compiling reg_att_map_generator
Closed 3 years ago3
reg_att_map_generator.cu(114): error: type name is not allowed
Closed 3 years ago4
Pretrained models for YouTube-VOS dataset
Closed 3 years ago1
Hyperparameters for static image pretraining
Closed 3 years ago1
How can I use .flo file instead of tflownet?!
Closed 3 years ago2
About batchsize
Closed 3 years ago1
Could you release your pre-computed results?
Updated 3 years ago
About training schedule
Closed 3 years ago6
Training protocols for youtube finetuning
Closed 3 years ago1
光流 .flo 文件
Closed 3 years ago1
have you implemented KMN?
Closed 3 years ago1
Problem with building "reg_att_map_generator" extension
Closed 3 years ago1
A typo in README.md
Closed 3 years ago1
About network training
Closed 3 years ago1
Where is the code for Global-to-Global matching? / Why not use pretrained model for TinyFlowNet?
Closed 3 years ago3
The problem of the precomputed optical flow
Closed 3 years ago9
ModuleNotFoundError: No module named 'flow_affine_transformation'
Closed 3 years ago1
import torch error
Closed 3 years ago6