Tomhouxin

Ok, Thanks! How much data is required to use the ploy mode？

这些是训练日志，目测貌似不再收敛了，hmean-iou:hmean停留在了0.8，loss也不在下降了，但是检测结果来看是乱起八糟的。是否要调整学习率继续训练呢？ {"mode": "val", "epoch": 69, "iter": 80, "lr": 0.00482, "hmean-iou:recall": 0.76316, "hmean-iou:precision": 0.84466, "hmean-iou:hmean": 0.80184} {"mode": "train", "epoch": 70, "iter": 5, "lr": 0.00478, "memory": 6697, "data_time": 1.78142, "loss_prob": 0.8945, "loss_db":...

 但是学习率已经下降到很低了

  And detect result like this

Ok, Thank you！！！

@rishab-sharma 你训练通过了吗

@meitianjinbu 你转成功后，是ncnn加载param文件的时候不能加载吗？比如这样：ParamDict read array element failed

@GengCauWong ，最终升级了pytorch1.2，重新训练的

@Robot000 , I got this error: RuntimeError: ONNX export failed: Couldn't export operator aten::softmax [https://github.com/pytorch/pytorch/issues/20643](https://github.com/pytorch/pytorch/issues/20643)

@hackeritchy , Did you solve?