ZuckXu
ZuckXu
No, I am using the latest caffe
yes, that's what I would expect, I am trying on some other machine , wired error
thanks, the problem is solved after checking the path of caffe that is somehow not my caffe even though the path is set in bashrc
to make it running on mobile, you need to think about model compression, quantization or use another backbone like mobilenet instead of vgg19, PAF is necessary in this bottom up...
@1adrianb thanks for your quick response, another unrelated question : are you planning to work on the bnn model for multi-person pose estimation, I am more interested to see how...
Gonna to test it
1. this is nota a fully end-2-end training process, basically , you need to manually save the tx, ty, t from the highest response value of conv5_4 and you use...
@zhangjian0826 I did not have the code now, but the idea is that for each image, you do the inference and save the output of the conv5_4 and then you...
@RTMDFG you are probably right, I did not have time to develop further, currently the APN pretrained net is not finished yet, so please contribute @abhimahesh , not just asking...
same question , seems there is no such sum_axis >>> dir(mxnet.symbol) ['Activation', 'AttrScope', 'BatchNorm', 'BlockGrad', 'Concat', 'Context', 'Convolution', 'Deconvolution', 'Dropout', 'ElementWiseSum', 'Embedding', 'Executor', 'ExecutorHandle', 'Flatten', 'FullyConnected', 'Group', 'IdentityAttachKLSparseReg', 'LRN', 'LeakyReLU',...