search

linhdvu14 / vggvox-speaker-identification

Speaker identification with VGGVox network
82 stars 34 forks source link

about the conv_bn_dynamic_apool #2

Open hktxt opened 5 years ago

hktxt commented 5 years ago

I read your code and found that the 9*1 is a conv layer in conv_bn_dynamic_apool() function. The paper says "replaced by two -layers-a fully connected layers of 9*1 and an average layer with 1/*8..." I stuck on this for a long time. Maybe you are right, that is a conv layer, which make sense.

hktxt commented 5 years ago

another question is why K.l2_normalize ?

hktxt commented 5 years ago

The wavreader function produce different result against with matlab.

zhengqun commented 5 years ago

FileNotFoundError: File b'cfg/enroll_list.csv' does not exist ? can you help me ?

linhdvu14 commented 5 years ago

Pretty sure I got the layer structure by following the Matlab model. Will check/update when I got more time.