Chris zhang
Chris zhang
@leolee96 Hi, I am a new guy to learn deep learning ,now, I want to use Caffe to train ShuffleNet on my own data ,but just with one .prototxt file...
I've already revised it,Thank you for reminding me :)
Sorry, I didn't train the network because of the limitation of equipment.
I met this problem one year ago , Firstly, you should figure out the difference between deploy.prototxt and train_val.prototxt，then, write a train_val.prototxt based on deploy.prototxt , define the path of...
正常的分类数据集都可以训练的，这个网络是用来训练ImageNet的，如果想训练小分辨率的网络可能需要根据需要自己更改一下网络的容量