Open LKCN opened 3 years ago
I met the same problem. Did you fix it?
看起来像是dataloader有问题,请帖上更多代码或者自己查查看。
检查一下checkpoint和图片路径是否正确,把num_worker设置成0试试
同样的问题已经解决.
搜索的是docker引起的莫名其妙的错误. 可能是我用的集群分给给每个用户是docker虚拟出来的
解决方法:
https://github.com/whai362/PSENet/blob/4d95395658662f2223805c36dcd573d9e190ce26/train.py#L158
改为 num_workers=0
运行后出现另外一个新错误. UnicodeDecodeError: 'ascii' codec can't decode byte 0xef in position 0: ordinal not in range(128) 卸载旧版本mmcv,安装最新版本的mmcv即可 pip uninstall mmcv pip install mmcv
解决完后,就能正常运行了..然后把num_worker改为gpu_num整数倍也没问题了
Traceback (most recent call last): File "E:/WangJianFeng/2020/TextDetection/PSENet/train_ic15.py", line 285, in
main(args)
File "E:/WangJianFeng/2020/TextDetection/PSENet/train_ic15.py", line 253, in main
train_loss, train_te_acc, train_ke_acc, train_te_iou, train_ke_iou = train(train_loader, model, dice_loss, optimizer, epoch)
File "E:/WangJianFeng/2020/TextDetection/PSENet/train_ic15.py", line 112, in train
for batch_idx, (imgs, gt_texts, gt_kernels, training_masks) in enumerate(train_loader):
File "D:\Anaconda3\envs\pytorch_gpu\lib\site-packages\torch\utils\data\dataloader.py", line 345, in next
data = self._next_data()
File "D:\Anaconda3\envs\pytorch_gpu\lib\site-packages\torch\utils\data\dataloader.py", line 856, in _next_data
return self._process_data(data)
File "D:\Anaconda3\envs\pytorch_gpu\lib\site-packages\torch\utils\data\dataloader.py", line 881, in _process_data
data.reraise()
File "D:\Anaconda3\envs\pytorch_gpu\lib\site-packages\torch_utils.py", line 395, in reraise
raise self.exc_type(msg)
TypeError: function takes exactly 5 arguments (1 given)