shenghsiaowong issues

Results 7 issues of


                                            shenghsiaowong

传奇你好，我用你的代码在训练的时候为什么没有用到GPU，可是已经检测出来了cudacudnn以及我显卡的型号了啊

传奇你好，我用你的代码在训练的时候为什么没有用到GPU，可是已经检测出来了cudacudnn以及我显卡的型号了啊

mobilenet

Hi，eric，do you have any plans to achieve the channel pruning(except the one you use),eg:this article" Learning Efficient Convolutional Networks through Network Slimming

大佬，有打算做这篇的Channel Pruning for Accelerating Very Deep Neural Networks的模型剪枝吗

你好，这个模型部署在海思3519上可以使用海思的npu加速吗

can you help me to solve it ?WARNING: non-finite loss, ending training tensor([ nan, 0.22070, 0.00000, nan], device='cuda:0')

WARNING: non-finite loss, ending training tensor([ nan, 0.22070, 0.00000, nan], device='cuda:0')

HI，when i train my own dataset i got Class always 0?can you tell me

AVG IOU 0.4056, Class 0.0000, Obj 0.3534, No obj 0.0001, .5R 0.4000, .75R 0.0000, Cur obj 5, All obj 6, Coord xy 0.1274, Coord wh 0.6270 2019-06-09 18:58:00,455:INFO:Head 1 AVG...