TVXQ20031226
Results
4
comments of
TVXQ20031226
> @yangxue0827 @f27ny105t5123 请问你是如何在VOC2012数据集上训练的，我尝试dataset_name改为person，增加标签几个为perpon为1，其余所有类为0，但总是出现 > InvalidArgumentError (see above for traceback): LossTensor is inf or nan : Tensor had NaN values > [[Node: train_op/CheckNumerics = CheckNumerics[T=DT_FLOAT, message="LossTensor is inf or nan",...
不是数据集的问题，我检查过数据集，没有超界的情况，但是我之前是用vgg16训练的，feature_maps_dict那段代码是我自己写的，估计是那里出了问题，我现在把模型换成resnet以后就成功了 @zhanhuanli
> I changed ANCHOR_SCALES from [1.] to [2**-2, 2**-1, 1.], now it works. > > However, the fast_rcnn_loc_loss is still always be 0.0 after 10k iterations of training. Does it...
楼主你解决这个问题了吗？！我也碰到这个问题了！！！！ @niuniu111