DBNet.pytorch

DBNet.pytorch copied to clipboard

validation image is not resized by multiple of 32

8

I found that validation images are resized at `class ResizeShortSize`, `data_loader/modules/augment.py`. The short side is resized to 736px (multiple of 32) by config setting, but long side is not guaranteed...

nai-kon

训练时，反向传播错误

1

Traceback (most recent call last): File "train_eval_test/train.py", line 80, in main(config) File "train_eval_test/train.py", line 64, in main trainer.train() File "/share/yongqin/experimentplan/PDBNet/trainer/base_trainer.py", line 103, in train self.epoch_result = self._train_epoch(epoch) File "/share/yongqin/experimentplan/PDBNet/trainer/trainer.py", line...

TALQinYong

您好大佬，请问代码在单机三卡时无法运行如何处理 您的原代码直接运行报错： ValueError: Error initializing torch.distributed using env:// rendezvous: environment variable MASTER_ADDR expected, but not set 以下改动后：程序直接卡死，一直无反应 os.environ['MASTER_ADDR'] = 'localhost' os.environ['MASTER_PORT'] = '5668' 麻烦给点帮助，谢谢啦

lizhenye2017

请问这是什么原因呢？

2


YunF99

求预训练模型

1

跪求预训练模型

PanJinquan

如何关闭数据增强呢？

3

hellohahaw

请教大家，如何用此模型训练其他数据集

14

源码中只给出了训练IC2015的说明，请问如何训练totaltext、ctw1500、td500之类的数据集呢？求助大佬解答，感激不尽！

wangzhenyan001

源码当中只给出了probability map，但是threshold map没有给出如何保存，请问应该怎样修改源码使得threshold map能够保存呢？求助大佬，感激不尽！！

wangzhenyan001

IndexError: list index out of range

7

root@dsw-239190-b6866c49-vs5c8:/mnt/workspace/downloads/137084/DBNet.pytorch# CUDA_VISIBLE_DEVICES=0 python3 tools/train.py --config_file "config/icdar2015_resnet18_FPN_DBhead_polyLR.yaml" # 单GPU训练Traceback (most recent call last): File "tools/train.py", line 78, in main(config) File "tools/train.py", line 37, in main train_loader = get_dataloader(config['dataset']['train'], config['distributed']) File "/mnt/workspace/downloads/137084/DBNet.pytorch/data_loader/__init__.py",...

jihuodexiaoyang

train的batch_size和validate的batch_size有关系限制吗

1

请问, 比如train是24, val是8,不会有什么影响吧

rhizomeIndark