wangzhiyuan

Results 10 comments of wangzhiyuan

你好,如果使用partFc train 使用curricular loss计算会有问题,需要所有的logits值,请问你是怎么实现的呢,你是用distributed.all_gather么

以前想到过这个问题,刚看到,可使用distributed.all_gather,搜集所有的GPU卡上的 logis即可,然后再算target_logit值。

> 邮件已收到。 can you share with me? [email protected] Thanks

> 想了解数据预处理这部分是怎么做的?比如训练和测试的分辨率等等 还是训练的超参数具体是什么 我: 输入:512x512 ,其他与shanghaiT A 参数相同,如数据增强(如镜像,随机截取512x512)相同 测试:整张图输入 loss:相关的计算比例跟作者一样 性能:目前val mae=101.1(训练的不好) 其他设置参数可能需要调,如anchors的数量等

> 我的输入的crop是128_128,其他与你类似,目前最好的val mae也是100多一点,anchor改成3_3,也这样 可能是一些细节论文并未提到。

> 如题 越大 越近的 人头 是不是感受野太小,语义信息不强?

> I would say it's expected that similarity decreases with different conditions, but what are the similarity values across images, for comparison ? (in order to have an idea of...

> Sorry I mean what are the actual number values across the 3 images with different content ? The actual similarity of the three images should be above 0.98

> what is the actual value between the top-left image vs the bottom-left image in your grid ? also, can you describe what you mean by "the last 384 dimensions"...

> essentially what i'm trying to understand is if we are in the case where: > > * all images in a given row (with different lighting / shadows) have...