Chen Ma
Chen Ma
> > > Mee too i do not know how to save .h5 who can tell me can you save as xxx.weights file?,i got many files like this xx.data-00001-of-00002 xx.index...
> Mee too i do not know how to save .h5 who can tell me you can use model.save(xxxxx.5h)
> 解决了,21号和22号的代码不一样。。。 楼主,请问你是怎么解决的?,我也是训练出来以后用不了模型?
> > 解决了,21号和22号的代码不一样。。。 > > Did you solve this issue? If not, kindly post your query in English, I can help you! HI i also met this problem can u...
> > > This indicates that you have a problem with train txt file > what format are using ? it should be Filepath x1,y1,x2,y2 no headers @llmpass @juanmanuelrq Train...
> > > 需要把生成路径那个函数用os.path.join替代一下,就可以了,我是这样做的 您好,您是怎么准备数据集的呀?我总是提示数据集格式不对?
是先把我自己训练好的CKPT文件路径放在config里的orginal weight里,然后convert成yolo demo weight?,那我怎么加载转换后的结果呀
好的谢谢博主啦,我试试看能不能行
博主,我稍微尝试了一下,发现一个问题,我训练的CKPT文件在经过freeze 的操作生成pb文件以后,权重参数为什么发生了变化呀
您好相机拍摄的图片是2048x2048的满足倍数要求,但是图片格式是raw图,单通道的灰度图像,暂时不知道怎么送入网络训练只用更改第一次卷积的通道数吗?