taylorlu / facenet-caffe Goto Github PK

Hello, I 'm new into caffe, I clone the project and installed requirement to run , get error result.
F0513 13:12:47.509194 8257 net.cpp:757] Cannot copy param 0 weights from layer 'Bottleneck/BatchNorm'; shape mismatch. Source param shape is 512 (512); target param shape is 128 (128). To learn this layer's parameters from scratch rather than copying from a saved net, rename the layer.
*** Check failure stack trace: ***
Aborted (core dumped)

please help , thank you in advance.

F0411 11:10:11.883401 6173 cudnn_relu_layer.cpp:13] Check failed: status == CUDNN_STATUS_SUCCESS (1 vs. 0) CUDNN_STATUS_NOT_INITIALIZED
*** Check failure stack trace: ***

Thanks for this useful tool for converting facenet-tensorflow to facenet-caffe!

About the models, an important factor may have been ignored when do inference.
20170512-110547: per_image_standardization (the prewhiten function in your codes)
20180402-114759: fixed_standardization

With the correct standardization used, the 2018 model shall perform better than the 2017 model.

I also put this notice at the original FaceNet issue pool: davidsandberg/facenet#948 (comment)