DotWang

> @DotWang We do not have a plan to make it support mixed-precision training. It will be great if you can achieve it. > Maybe there is an alternative way...

Thanks for your clear explaination. So the bottom row results in Figure 1 whether can be understood as for a certain input image, in every epoch, although a same cues...

OK, I see. thank you very much. (It's my fault, the "CAM" I just said is the probability map "fc8-SEC-Softmax" in the code)

@yinan-1 之前我记得勾选了Chinese-Simplified和英文及法语（因为好像出过法语题），现在我只勾选Chinese-Simplified，还是报相同的错，不知道为啥。。

> why the correct/total is only 14.4476% when Predicting with the previous stored model through infer.py? Because actually the ground truth doesn't cover all pixels. The infer.py is only used...

@FishMaster93 yes

@FishMaster93 The time is so long, I forget the details, you can see the code. But I'm sure that we don't conduct a preprocessing, all procedures are lying in the...

新建一个key就行了

> > 新建一个key就行了 > > 试过了，不行 好吧，我是前天搞的key，也没玩几下，昨天就不能用了说让充值，刚才新建了一个又好了

> > > > 新建一个key就行了 > > > > > > > > > 试过了，不行 > > > > > > 好吧，我是前天搞的key，也没玩几下，昨天就不能用了说让充值，刚才新建了一个又好了 > > 是新建key吗 是的