DeepCompression-caffe
DeepCompression-caffe copied to clipboard
may0324
Caffe for Deep Compression
您好： 我在编译的时候发现cpp文件中有masks_参数的运用，但是头文件中没有定义一系列参数，是在其他地方定义的吗？ /home4/jiashuaihe/environment/caffe/src/caffe/layers/cmp_conv_layer.cu(63): error: class "caffe::CmpConvolutionLayer" has no member "masks_" detected during instantiation of "void caffe::CmpConvolutionLayer::Forward_gpu(const std::vector &, const std::vector &) [with Dtype=float]" (132): here
作者你好，我看到全连接和卷积分别有带前缀cmp的实现。 1. 这里的`mask_data`是该层被剪枝的权重在原矩阵中的位置嘛？ 2. 实现了K均值聚类后读取类中心嘛？下面代码中这一行`muweight[i] = cent_data[indice_data[i]];`是否是对应的实现？ ```cc template void CmpInnerProductLayer::Forward_cpu(const vector& bottom, const vector& top) { Dtype* muweight = this->blobs_[0]->mutable_cpu_data(); const int *mask_data = this->masks_.cpu_data(); int count = this->blobs_[0]->count();...
*** Aborted at 1531205735 (unix time) try "date -d @1531205735" if you are using GNU date *** PC: @ 0x7fae1722831b caffe::CmpConvolutionLayer::compute_output_shape() *** SIGFPE (@0x7fae1722831b) received by PID 5626 (TID 0x7fae17e3e740)...
您好， 感谢您的分享！@may0324 我想问您下 剪枝后的模型怎么存成size 小的caffemodel. 可以分享下有关这方面的代码吗，谢谢您！
when snapshot start, it crash. ```I0721 11:04:23.275279 17167 solver.cpp:228] Iteration 9, loss = 1.88784 I0721 11:04:23.275313 17167 solver.cpp:244] Train net output #0: acc = 0.428571 I0721 11:04:23.275321 17167 solver.cpp:244] Train...
Dear may0324: At first, **I must appreciate your time and effort on the tutorial**. This is very excellent. Actually, I need some tools to prune VGG-16 for my research. Thus,...
Hi, @may0324 Thanks for your cool work! After cloned this code, we have been trying to replicate Han's work in pruning conv-nets, especially the large one like caffenet, a variant...
Some of the weights become very large when I run the gpu version. There may be some problems in "quantize_weight_backward".
Specific questions are as follows,  Eager to get your help。Thank you~
