MModerato

``` name: "KevinNet_CIFAR10" layers { layer { name: "data" type: "data" source: "cifar10_train_leveldb" meanfile: "../../data/ilsvrc12/imagenet_mean.binaryproto" batchsize: 32 cropsize: 227 mirror: true det_context_pad: 16 det_crop_mode: "warp" det_fg_threshold: 0.5 det_bg_threshold: 0.5 det_fg_fraction:...

Do you have an experiment on NUS-WIDE ? @kevinlin311tw

Uh.. Is it correct for me to use SigmoidCrossEntropyLoss on multi-label dataset? @kevinlin311tw

I forgot whether I had met the mistake. I'm using another version of Caffe, so I can run it properly after the prototxt changes

> When a client application closes before the server could send its response, the server crashes. > This is only the case with the async server. Server I'm using is...

Thank you very much！ To add, I use asynchronous operations: async_run and async_call. I have bound a function to process video to the server. When the client sends the video...

server: ``` #include "rpc/server.h" #include #include std::string test(){ int count = 0; while(count

My environment is : ``` gcc version 5.4.0 Ubuntu 16.04 cmake version 3.5.1 ``` ``` #include "rpc/server.h" #include #include std::string test(int max){ int count = 0; while(count

@qchateau I just tested it with your branch, and it's amazing that my server is working properly! Then I need to validate further on the server. Sincerely thank you for...

 I modified this function to display the specified categories in `label. txt`