amitabhama
amitabhama
EpochID: 50 Iter: 140 stage1_pafs_loss: 109600.7609375 stage1_heatmaps_loss: 28056.8501953125 stage2_pafs_loss: 101297.615625 stage2_heatmaps_loss: 25829.1998046875 stage3_pafs_loss: 100676.89765625 stage3_heatmaps_loss: 25646.5669921875
我用的pytorch, 用您源码训练loss也很大, 2w以上
收到, 我这边继续调试下, 看看loss
> > 收到, 我这边继续调试下, 看看loss > > 你好,可以留个联系方式,交流下吗 wechat: mahongyun177, 我也不是特别懂的.....还得问问作者大佬
@murdockhou Iter: 130000 stage1_pafs_loss: 0.013112904597073793 stage1_heatmaps_loss: 0.00752411549910903 stage2_pafs_loss: 0.011273426562547683 stage2_heatmaps_loss: 0.00575953284278512 stage3_pafs_loss: 0.011314316745847463 stage3_heatmaps_loss: 0.005732348002493381 EpochID: 50 Iter: 140000 stage1_pafs_loss: 0.013068882934749126 stage1_heatmaps_loss: 0.007446729391813278 stage2_pafs_loss: 0.011319325864315033 stage2_heatmaps_loss: 0.005765374982729554 stage3_pafs_loss: 0.011329260561615229 stage3_heatmaps_loss:...
> @amitabhama loss具体数值不重要, 重要的是 > > 1. 你的loss计算方式是什么样子, loss大小应该有个大概的, 要确保的是这个loss大小数值符合你的loss计算公式 > 2. 随着模型训练, 整体loss是下降趋势并且模型测试的时候有结果出来 > > 具体loss是个什么数值不是很关键, 满足上面两点就可以 用的l2_loss, 想问你跑tf,跑了多少个epoch
@murdockhou INFO:tensorflow:Saving dict for global step 13125: global_step = 13125, heatmap = 0.11633993, loss = 1555.1757, paf = 0.11959251 请问下,用你的源码跑的训练, heatmap和paf这两个值是什么意思, 还有这个loss,什么区间是表现还可以的, thx
@murdockhou 那想请问下你, 你训练的时候loss大概多少, 这个方便透露吗?以下是我目前训练的结果 INFO:tensorflow:Finished evaluation at 2019-12-10-02:13:41 INFO:tensorflow:Saving dict for global step 15750: global_step = 15750, heatmap = 0.12529747, loss = 1782.9702, paf = 0.13560909 INFO:tensorflow:Saving 'checkpoint_path' summary for...
> @amitabhama heatmap paf 定义在这[link](https://github.com/murdockhou/lightweight_openpose/blob/master/train.py#L70) > loss肯定越小越好, 具体哪里会好不是很清楚了 谢谢, 这个清楚了