ustczhouyu comments

Results 51 comments of


                                            ustczhouyu

fots-tensorflow

Unexpected key(s) in state_dict: "backbone.conv1.weight", "backbone.bn1.weight",

OHEM and ROIRate haven't completed?

求助： eval的时候报错：Unexpected key(s) in state_dict: "backbone.conv1.weight", "backbone.bn1.weight",

自己训练的，测试读取出错 | | zhou19920226 | | 邮箱：[email protected] | Signature is customized by Netease Mail Master 在2019年10月22日 10:38，zcunyi 写道：我的测试命令是这样，python eval.py -m ./model/model_best.pth.tar -i ./Challenge4/ch4_test_images -o ./output 为啥显示TypeError: invalid file: PosixPath('./model/model_best.pth.tar')...

fail to train the model

好的，大概是多久呢，我等了十分钟，然后想停止，停不了。发自我的iPhone------------------ Original ------------------From: ChChwang Date: 周五,12月 21,2018 12:39To: bgshih/aster Cc: ustczhouyu , Author Subject: Re: [bgshih/aster] fail to train the model (#25)我用的python2，restore时间会长点，但是不会卡主。 —You are receiving this because you authored the...

fail to train the model

谢谢，大神可不可以把你的整个文件夹，除了数据和训练好的模型之外打包发给我啊，真的感激不尽，谢谢。发自我的iPhone------------------ Original ------------------From: ChChwang Date: 周五,12月 21,2018 13:02To: bgshih/aster Cc: ustczhouyu , Author Subject: Re: [bgshih/aster] fail to train the model (#25)具体时间没有计算，可以看看计算资源使用率。 —You are receiving this because you authored the...

如何评估

请问你们能训练aster吗，我用python3 train.py训练的时候，初始化一下了15行代码，到从我下载的预训练模型中恢复数据的那一步的时候就卡住了，ctrl+c也关不掉了。如下所示， INFO:tensorflow:Scale of 0 disables regularizer. INFO:tensorflow:Scale of 0 disables regularizer. INFO:tensorflow:Scale of 0 disables regularizer. INFO:tensorflow:Scale of 0 disables regularizer. INFO:root:Number of classes is 94 INFO:root:UNK label is...

ustczhouyu

fots-tensorflow

OHEM and ROIRate haven't completed?

测试时读取模型说是无效文件

测试时读取模型说是无效文件

fail to train the model

fail to train the model

如何评估

能训练中文识别吗?

请问训练完成后如何进行detection

请问如何将DOTA数据的8点坐标转换成符合本代码运行规范的五点坐标呢？