alexanderuo

> import argparse > > from lib.config import config from lib.config import update_config_demo import lib.models.seg_hrnet as seg_models > > import torch import torch.nn as nn import torch.backends.cudnn as cudnn import...

> > > > 你对齐下就可以了，我粘贴过来就变这样了 好的，谢谢兄弟，被你发现我是个中国人了哈哈

me too here are the details： => init weights from normal distribution Traceback (most recent call last): File "tools/test.py", line 139, in main() File "tools/test.py", line 71, in main logger.info(get_model_summary(model.cuda(),...

me too.my config file is : `model: arch: fcn8s data: dataset: nyuv2 train_split: training val_split: val img_rows: 480 img_cols: 640 path: /users/guozibin/dukaiyang/2.9k/dataset/input sbd_path: /private/home/meetshah/datasets/VOC/benchmark_RELEASE/ training: train_iters: 100000 batch_size: 1 val_interval:...

I am also looking forward to it .good luck with CVPR!