ydhong_hit
ydhong_hit
>  Pre-training model ：hrnet_ocr_cs_trainval_8227_torch11.pth Maybe because of a previous error：The file could not be found ：final_state.pth I changed the name of the hrnet_ocr_cs_trainval_8227_torch11.pth model to this one and...
我也遇到了这个问题，好像是融合不同stride的边界标签的问题，只使用单独stride的边界标签进行训练就没问题，不知道作者是什么处理的
> Hi, > great project. > Do you have any plans for adding DDRNet support to mmsegmentation? Hi, now I am not going to do that. I will try it...
> Dera Yuanduo > > Thanks very much for your perfect Network. I have a question about the structure of the DDRNet. > > In your program code, the layer...
> This model is extremely fast & accurate. I've tried so many methods to make a model run fast enough with the same accuracy, like lite backbone, shrink the PPM...
> 实际应用效果真的不错，又快又好，我们公司线上就用了这个 多谢认可
> I am using your model to do segmentation, and its performance is really amazing. However, the inference speed is not ideal. I noticed that you merged conv2d and batchnorm...
> Hello Yuanduo, > > I think your achievement is really awesome. I am looking into your code and your model to develop more on it. > > I was...
> Hello Yuanduo, > > I think your achievement is really awesome. I am looking into your code and your model to develop more on it. > > I was...
> I notice that for Beit, by training 320k iterations, the model can achieve 56+ mIoU. Training for longer time seems to be a potential cause. But this is not...