search

backstopmedia / tensorflowbook

457 stars 296 forks source link

the first dimension of the kernel variable #18

Open ruoyu0088 opened 7 years ago

ruoyu0088 commented 7 years ago

I don't understand the following sentence in 05_object_recognition_and_classification:

In the example code, there is a single kernel which is the first dimension of the kernel variable.

Acorrding to the document the shape of kernel is [filter_height, filter_width, in_channels, out_channels], the first dimension of the kernel is filter_height.