yang502
yang502
## I am using python2.7 branch. And has 2 leech get file from seeder. They can download succeed,but after a period of time(may be half hour ), I found one...
I am using the branch on Python2.7 when I download the file from seeder , the network of leecher was unexpect lost .But I didin't now , and the btdownloadheaderless.py...
I try to compted En as a weight in batch data, but loss quickly change to NAN. I always try to compute in whole dataset, img_per_class =[900000,700000,60000], because img_num is...
I am try to reproduce the results on market1501. But the triplet loss is very small, nearly to zero. So after iter=35000+, the network did not update(loss=0). I can't reproduce...
In your paper, the parameters of FCN and W (sparse coefficient matrix) seems are alternate update. I want to where is the corresponding optimization process implemented? @lingxiao-he
where is your model define file?
My input dataset has converted as numpy matrices by np.asmatrix() and it's dim is 1024; I use the python API