yangyangv8
Results
2
issues of
yangyangv8
对转换工具编译时只生成了feather_convert_caffe这个文件,通过这个文件也能将caffe模型转换成feathermodel,这样转化的featherCNN模型正确吗,另外编译时需要安装protobuf吗? 还有一个问题我的caffe网络有44层(Convolution,Eltwise,ReLU三种类型),调用Forward(float *input)执行网络时layers.size的值为33,ReLU层有11层,这样解析的layers.size正确吗?
### Problem Description In the rccl file prims_simple.h,I have added a section of printf in this kernel function, such as : > __device__ __forceinline__ void genericOp( > intptr_t srcIx, intptr_t...
Under Investigation
AMD Radeon RX 7900 XTX
ROCm 5.7.0