maga33 / transfernet Goto Github PK

Hello,

I trained TransferNet on my dataset with novel categories. During the inference in Matlab there is classificationet. prototxt and classificationnet.caffemodel adopted. As these files differs from the attentionnet.prototxt and attentionnet.caffemodel, it is imposible to infer on my dataset. How should I modify my trained attentionnet.caffemodel to classificationet.caffemodel ?

Sincerely

Michal

Hello,

I am testing Transfernet to modify it to my data. I still face troubles to understand attention module as it is described differently in your equations in paper, your diagram (same paper) and in deploy.prototxt . I tried to visualize the network deploy.prototxt in Netscope - http://ethereon.github.io/netscope/#/editor but it gives me errors. Can you describe me where is the soft_att blob located as there are two contradictory definitions in prototxt, namely:

layer {
name: "soft-att"
type: "Scale"
bottom: "conv5_3"
scale_param { scale_factor: 0.004 } # no scaling
top: "conv5_3_scaled"
}

and

layer {
name: "soft-att"
type: "LinearSum"
bottom: "conv5_3_scaled"
bottom: "att"
top: "soft-att"
}

The Netscope refuse to visualize it (also attention.prototxt) and I am not able to figure out, what is the exact structure of attention module.

Thank you for clarification

Michal