Yong

@TimoSaemann I want to know the setting bn_mode="LEARN“ is the customized by yourself? I mean, could I use the bn_mode="LEARN" in the official CAFFE?@ @ thanks

Mac compile cython error with mesh_core_cython

3

"Using deprecated NumPy API, disable it by " "#defining NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-W#warnings] #warning "Using deprecated NumPy API, disable it by " \ ^ mesh_core_cython.cpp:583:10: fatal error: 'ios' file not found...

How to understand for the "center_map" in the prototxt? What's the meaning for the networks?

3

layer { name: "image" type: "Slice" bottom: "data" top: "image" top: "center_map" slice_param { slice_point: 3 axis: 1 } } layer { name: "silence2" type: "Silence" bottom: "center_map" } @dragonfly90...

Why the BN layer of your deploy.prototxt does not set "use_global_stats: true"

1

Why the BN layer of your deploy.prototxt does not set "use_global_stats: true" Thanks @farmingyard

how to do definition the dist(distination)? like, when I have the keypoint position of the person pose of one image? would you mind sharing some real example

there are some different expression between the paper and the model

2

At first , I read the paper and the original prototxt code of the train_cls.prototxt and its solver.prototxt. I found that in the train_cls.prototxt there was no loss_weight for the...

pre-trained model or train log or code

1

good work! would you mind sharing your pre-trained model. I would like to test the result, my model not work well as you metioned

@ I want to know the setting bn_mode="LEARN“ is the customized by yourself? I mean, could I use the bn_mode="LEARN" in the official CAFFE? thanks

one docker image with openpose repo or with other pose estimation repo like centernet?

2

will you have some interests in building one docker image with this excellent repo. I know your repo from OpenMMD, Thanks. Looking forward to your any replies

Excellent work。The caffemodel in your paper will be share? Anther question is the customized caffe is needed to change the caffe.proto or add some special layer param setting? I mean,...