caffe

caffe copied to clipboard

在反馈函数中，似乎不是均值呢？而是不断在替换bottom里面的值，最终保留的是最后一次的结果吧？ 是不是可以考虑，先caffe_set(bottom[0]->count(), 0, bottom[0]->cpu_diff()); 后面再调用caffe_cpu_axpby的时候，改写为： caffe_cpu_axpby( channels, Dtype(1.0 / image_count_dtype[static_cast(top0_map_Dtype[i])]), top[0]->cpu_diff() + (i \* channels), Dtype(1.0), bout + (static_cast(top0_map_Dtype[i])*channels) ); 因为我看到您，已经写到要计算均值的，可是为什么又注释掉呢？求解~

tanghy2016

你好，我想问一下，我这训练是什么情况？

2

I0811 04:43:50.113242 6500 solver.cpp:214] Iteration 0, loss = 0 I0811 04:43:50.113284 6500 solver.cpp:229] Train net output #0: tripletloss = 0 (\* 1 = 0 loss) I0811 04:43:50.113313 6500 solver.cpp:486] Iteration...

louielu1027

Test the triplet-loss accuracy!

3

Hello! I see your cifar-10 using the triplet loss replacing the softmax. If we want to test the triplet the accuracy, what can I do?

getengqing

Existing in caffe general way should I do?? Or, Do you have a special way for metric learning(triplet loss)? thank you

peternara