What is the relationship between lambda and batchsize?

[double-vane]

How do you determine the lambda？

[goodluckcwl]

Good question. Actually, the batch size I used is nothing special. I think the best lambda should be determined by experiment.

[double-vane]

@goodluckcwl Thank you very much.
Does the lambda remain the same?
layer {
name: "fc6"
type: "MarginInnerProduct"
bottom: "fc5"
bottom: "label"
top: "fc6"
top: "lambda"
param {
lr_mult: 1
decay_mult: 1
}
margin_inner_product_param {
num_output: 10575
type: QUADRUPLE
weight_filler {
type: "xavier"
}
base: 3.6
gamma: 0.12
power: 1
lambda_min: 3.6
iteration: 0
}
}

[goodluckcwl]

Note that this prototxt is used for fine-tune only. Besides, I don't known whether a larger batch size makes sense or not. You can have a try. For example, set batch_size=256.