About transform_param

[ryusaeba]

Hi there,
I would like to do detection. If I use your caffemodel as initial weight as my base network.
It is better to add your transform parameters (as below shows) in my .prototxt, right?
| # transform_param {
| # scale: 0.017
| # mean_value: [103.94,116.78,123.68]
So your input data range is changed from [0-255] to [0-4.335]. My understanding is correct?

[shicai]

yes, use these tranform parameters.
the input range is changed from [0, 255] to [-2.x, 2.x], because you subtract the mean values of BGR.

[ryusaeba]

Thanks for the kindly reply :)