007
007
I draw the net structure from your torch model, but i am not sure correctness. Can share your net structure? [net structure](https://github.com/camel007/binary-face-alignment/blob/master/binary_face_alignment.png) NOTE: I didn't add binary layer
Hey, nelson! Can you list some paper you reference? Thank you!
您好,论文中做ternary之前,先对weight进行归一化,即除以最大的abs(w)归一化到[-1, 1]。 根据论文中设定threshold的方法  weight已经归一化,最大的max(abs(w))是1,因此delta就是t,也就是文中的0.05。 请问是这样吗?谢谢
gcc: 9.4 boost 1.75.0 ubuntu 14.04 改了几个地方: 1. CMakeLists.txt 中target_link_libraries(plugin_app ${Boost_LIBRARIES}) 改为 target_link_libraries(plugin_app ${Boost_LIBRARIES} dl) 不然会出现dlopen系列为定义 2. rest_rpc中 ./include/rest_rpc/rpc_client.hpp 207行 ./include/rest_rpc/client_utls.hpp 3行 ./include/rest_rpc/use_asio.hpp 34行 __cplusplus > 201402L 改为__cplusplus > 201703L...
I have cloned the 'face' branch, but still get this error? INFO:root:Namespace(batch_size=384, data_dir='./', gpus='0', kv_store='local', list_dir='/data/celeba_dababase/moon_mxnet/im2rec/', lr=0.05, model_load_epoch=0, model_load_prefix='../model/lightened_moon/lightened_moon', model_save_prefix='../model/lightened_moon/lightened_moon_fuse', num_examples=159923, retrain=False) Traceback (most recent call last): File "lightened_moon.py", line...