helloearth012
helloearth012
These are what are supported in layer_factory.cpp void register_layer_creators() { REGISTER_LAYER_CREATOR(Input, GetInputLayer); REGISTER_LAYER_CREATOR(Convolution, GetConvolutionLayer); REGISTER_LAYER_CREATOR(DepthwiseConvolution, GetDepthwiseConvolutionLayer); REGISTER_LAYER_CREATOR(BatchNorm, GetBatchNormLayer); REGISTER_LAYER_CREATOR(LRN, GetLRNLayer); REGISTER_LAYER_CREATOR(Concat, GetConcatLayer); REGISTER_LAYER_CREATOR(Dropout, GetDropoutLayer); REGISTER_LAYER_CREATOR(ReLU, GetReluLayer); REGISTER_LAYER_CREATOR(PReLU, GetPReluLayer); REGISTER_LAYER_CREATOR(Scale, GetScaleLayer);...
Below two lines are in feather/test_txt.cpp size_t input_size = 224 * 2224 * 3 ; float *input = new float[input_size * 20]; 1. typo 2224->224? 2. why do you allocate...
很多平台,2个线程会略微好一些,更多线程反而引入一些cpu对线程管理的问题,最后反而速度更慢。(使用openmp) 但是看您的数据,多线程下,加速非常明显,请问是如何实现的?
和平台相关吗,还是总是其中一个更快? ZQ_GEMM和BLAS_GEMM在计算的时候,区别是什么?谢谢
ZQ_CNN_Layer.h:465:47: error: ‘_strcmpi’ was not declared in this scope if (_strcmpi("SAME", paras[n][1].c_str()) == 0) ZQ_CNN_Layer.h:1022:47: error: ‘_strcmpi’ was not declared in this scope if (_strcmpi("SAME", paras[n][1].c_str()) == 0) ZQ_CNN_Layer.h:2887:47: error:...
现在不知道哪些是需要配合使用,比如Pnet, Rnet, Onet, 哪些单独使用。不清楚每个model对应的意思,比如多少点的检测,更快,更慢,精度比之前提高了,还是下降了。非常感谢。