How do I to prevent backward computation in specific layers in caffe - machine-learning

Question

I want to disable the backward computations in certain convolution layers in caffe, how do I do this?
I have used propagate_down setting，however find out it works for fc layer but not convolution layer.
Please help~
first update: I set propagate_down:false in test/pool_proj layer. I don't want it to backward(but other layer backward). But from the log file, it says that the layer still needs backward.
second update: Let's denote a deep learning model, there are two path from input layer to output layer, p1: A->B->C->D, p2: A->B->C1->D, A is the input layer and D is fc layer, others are conv layer. When gradient backward from D to previous layers, p1 has no different from the normal gradient-backward procedure, but for p2, it stop at C1(but the weight of C1 layer still update, it just doesn't backward its error to previous layers).
prototxt
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 224
mean_value: 104
mean_value: 117
mean_value: 123
}
data_param {
source: "/media/eric/main/data/ImageNet/ilsvrc12_train_lmdb"
batch_size: 32
backend: LMDB
}
}
layer {
name: "data"
type: "Data"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mirror: false
crop_size: 224
mean_value: 104
mean_value: 117
mean_value: 123
}
data_param {
source: "/media/eric/main/data/ImageNet/ilsvrc12_val_lmdb"
batch_size: 50
backend: LMDB
}
}
layer {
name: "conv1/7x7_s2"
type: "Convolution"
bottom: "data"
top: "conv1/7x7_s2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 3
kernel_size: 7
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "conv1/relu_7x7"
type: "ReLU"
bottom: "conv1/7x7_s2"
top: "conv1/7x7_s2"
}
layer {
name: "pool1/3x3_s2"
type: "Pooling"
bottom: "conv1/7x7_s2"
top: "pool1/3x3_s2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "pool1/norm1"
type: "LRN"
bottom: "pool1/3x3_s2"
top: "pool1/norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv2/3x3_reduce"
type: "Convolution"
bottom: "pool1/norm1"
top: "conv2/3x3_reduce"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "conv2/relu_3x3_reduce"
type: "ReLU"
bottom: "conv2/3x3_reduce"
top: "conv2/3x3_reduce"
}
layer {
name: "conv2/3x3"
type: "Convolution"
bottom: "conv2/3x3_reduce"
top: "conv2/3x3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 192
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "conv2/relu_3x3"
type: "ReLU"
bottom: "conv2/3x3"
top: "conv2/3x3"
}
layer {
name: "conv2/norm2"
type: "LRN"
bottom: "conv2/3x3"
top: "conv2/norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool2/3x3_s2"
type: "Pooling"
bottom: "conv2/norm2"
top: "pool2/3x3_s2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "test/5x5_reduce"
type: "Convolution"
bottom: "pool2/3x3_s2"
top: "test/5x5_reduce"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 16
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "test/relu_5x5_reduce"
type: "ReLU"
bottom: "test/5x5_reduce"
top: "test/5x5_reduce"
}
layer {
name: "test/5x5"
type: "Convolution"
bottom: "test/5x5_reduce"
top: "test/5x5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 32
pad: 2
kernel_size: 5
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "test/relu_5x5"
type: "ReLU"
bottom: "test/5x5"
top: "test/5x5"
}
layer {
name: "test/pool"
type: "Pooling"
bottom: "pool2/3x3_s2"
top: "test/pool"
pooling_param {
pool: MAX
kernel_size: 3
stride: 1
pad: 1
}
}
layer {
name: "test/pool_proj"
type: "Convolution"
bottom: "test/pool"
top: "test/pool_proj"
propagate_down:false
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
layer {
name: "test/relu_pool_proj"
type: "ReLU"
bottom: "test/pool_proj"
top: "test/pool_proj"
}
layer {
name: "test/output"
type: "Concat"
bottom: "test/5x5"
bottom: "test/pool_proj"
top: "test/output"
}
layer{
name: "test_output/pool"
type: "Pooling"
bottom: "test/output"
top: "test/output"
pooling_param{
pool: MAX
kernel_size: 28
}
}
layer {
name: "classifier"
type: "InnerProduct"
bottom: "test/output"
top: "classifier"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1000
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "loss3"
type: "SoftmaxWithLoss"
bottom: "classifier"
bottom: "label"
top: "loss3"
loss_weight: 1
}
layer {
name: "top-1"
type: "Accuracy"
bottom: "classifier"
bottom: "label"
top: "top-1"
include {
phase: TEST
}
}
layer {
name: "top-5"
type: "Accuracy"
bottom: "classifier"
bottom: "label"
top: "top-5"
include {
phase: TEST
}
accuracy_param {
top_k: 5
}
}
log
I1116 15:44:04.405261 19358 net.cpp:226] loss3 needs backward computation.
I1116 15:44:04.405283 19358 net.cpp:226] classifier needs backward computation.
I1116 15:44:04.405302 19358 net.cpp:226] test_output/pool needs backward computation.
I1116 15:44:04.405320 19358 net.cpp:226] test/output needs backward computation.
I1116 15:44:04.405339 19358 net.cpp:226] test/relu_pool_proj needs backward computation.
I1116 15:44:04.405357 19358 net.cpp:226] test/pool_proj needs backward computation.
I1116 15:44:04.405375 19358 net.cpp:228] test/pool does not need backward computation.
I1116 15:44:04.405395 19358 net.cpp:226] test/relu_5x5 needs backward computation.
I1116 15:44:04.405412 19358 net.cpp:226] test/5x5 needs backward computation.
I1116 15:44:04.405431 19358 net.cpp:226] test/relu_5x5_reduce needs backward computation.
I1116 15:44:04.405448 19358 net.cpp:226] test/5x5_reduce needs backward computation.
I1116 15:44:04.405468 19358 net.cpp:226] pool2/3x3_s2_pool2/3x3_s2_0_split needs backward computation.
I1116 15:44:04.405485 19358 net.cpp:226] pool2/3x3_s2 needs backward computation.
I1116 15:44:04.405505 19358 net.cpp:226] conv2/norm2 needs backward computation.
I1116 15:44:04.405522 19358 net.cpp:226] conv2/relu_3x3 needs backward computation.
I1116 15:44:04.405542 19358 net.cpp:226] conv2/3x3 needs backward computation.
I1116 15:44:04.405560 19358 net.cpp:226] conv2/relu_3x3_reduce needs backward computation.
I1116 15:44:04.405578 19358 net.cpp:226] conv2/3x3_reduce needs backward computation.
I1116 15:44:04.405596 19358 net.cpp:226] pool1/norm1 needs backward computation.
I1116 15:44:04.405616 19358 net.cpp:226] pool1/3x3_s2 needs backward computation.
I1116 15:44:04.405632 19358 net.cpp:226] conv1/relu_7x7 needs backward computation.
I1116 15:44:04.405652 19358 net.cpp:226] conv1/7x7_s2 needs backward computation.
I1116 15:44:04.405670 19358 net.cpp:228] data does not need backward computation.
I1116 15:44:04.405705 19358 net.cpp:270] This network produces output loss3
I1116 15:44:04.405745 19358 net.cpp:283] Network initialization done.

Answer 1

From Evan Shelhamer (https://groups.google.com/forum/#!topic/caffe-users/54Z-B-CXmLE):
propagate_down is intended to switch off backprop along certain paths
from the loss while not entirely turning off layers earlier in the
graph. If gradients propagate to a layer by another path, or
regularization such as weight decay is not disabled, the parameters of
these layers will still be updated. I suspect decay is still on for
these layers, so you could set decay_mult: 0 for the weights and
biases.
Setting lr_mult: 0 on the other hand fixes parameters and skips
backprop where it is unnecessary.
You have decay_mult: 1 in some of the early layers, so the gradients are still calculated. Set lr_mult: 0 in all of the layers that you don't want the weights updated.
For example, change the following:
layer {
name: "conv1/7x7_s2"
type: "Convolution"
bottom: "data"
top: "conv1/7x7_s2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 3
kernel_size: 7
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
to
layer {
name: "conv1/7x7_s2"
type: "Convolution"
bottom: "data"
top: "conv1/7x7_s2"
param {
lr_mult: 0
decay_mult: 1
}
param {
lr_mult: 0
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 3
kernel_size: 7
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0.2
}
}
}
Also for reference:
https://github.com/BVLC/caffe/issues/4984