Caffe-Python-自定义网络 原
这里我们用一个例子先来体验一下
- 首先定义一下我们的环境变量 $PYTHONPATH，我这儿是Windows开发环境，至于Windows Caffe怎么编译由读者自己下去搞定
我使用的控制台是 Windows PowerShell
添加环境变量
$env:PATHPATH="F:\caffe-python\python\;F:\caffe-windows\windows\install\python"这里F:\caffe-python\python 是我的新Layer的路径F:\caffe-windows\windows\install\python 是我的Caffe编译以后install的路径
编写自己的TestLayer
import caffe
import numpy as np
class TestLayer(caffe.Layer):
def setup(self, bottom, top):
if len(bottom) != 1:
raise Exception("Need two inputs to compute distance.")
def reshape(self, bottom, top):
print("-----------------1---------------------")
top[0].reshape(1)
def forward(self, bottom, top):
top[0].data[...] = bottom[0].data
print("-----------------2---------------------")
def backward(self, top, propagate_down, bottom):
bottom[...].data=top[0].data
pass- 官方给出的一个例子
import caffe
import numpy as np
class EuclideanLossLayer(caffe.Layer):
def setup(self, bottom, top):
# 输入检查
if len(bottom) != 2:
raise Exception("Need two inputs to compute distance.")
def reshape(self, bottom, top):
# 输入检查
if bottom[0].count != bottom[1].count:
raise Exception("Inputs must have the same dimension.")
# 初始化梯度差分zeros_like函数的意义是创建一个与参数等大小的全0矩阵
self.diff = np.zeros_like(bottom[0].data, dtype=np.float32)
# loss 输出(loss是一个标量)
top[0].reshape(1)
#前向传播(计算loss bottom[0].data是第一个输入 bottom[1].data是第二个输入)
#注意：前向传播是输出top
def forward(self, bottom, top):
self.diff[...] = bottom[0].data - bottom[1].data
top[0].data[...] = np.sum(self.diff**2) / bottom[0].num / 2.
#后向传播
#注意：前向传播是输出到bottom
def backward(self, top, propagate_down, bottom):
for i in range(2):
if not propagate_down[i]:
continue
if i == 0:
sign = 1
else:
sign = -1
#误差向后扩散
bottom[i].diff[...] = sign * self.diff / bottom[i].num编写完我们的ayers以后写出网络结构
name: "TEST"
layer {
name: "cifar"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mean_file: "examples/cifar10/Release/cifar10/mean.binaryproto"
}
data_param {
source: "examples/cifar10/Release/cifar10/cifar10_train_lmdb"
batch_size: 100
backend: LMDB
}
}
layer {
name: "cifar"
type: "Data"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mean_file: "examples/cifar10/Release/cifar10/mean.binaryproto"
}
data_param {
source: "examples/cifar10/Release/cifar10/cifar10_test_lmdb"
batch_size: 100
backend: LMDB
}
}
layer {
name: "test1"
type: "Python"
bottom: "data"
top: "test1"
python_param {
module: "test_layer"
layer: "Test_Layer"
}
}可视化我们的网络结构以后如图
编写solver
net: "F:/caffe-python/python/test_layer.prototxt"
base_lr: 0.001
lr_policy: "fixed"
max_iter: 10
solver_mode: CPU接下来在powershell里面去启动caffe 先cd到caffe所在的目录 我的目录是这样的
cd F:\Smart_Classroom\3rdparty\ALLPLATHFORM\caffe-windows\windows\examples\cifar10\Release然后执行caffe
./caffe.exe train --solver=F:/caffe-python/python/test_python_layer_solver.prototxt如下图:
在后向和前向传播的过程中我们成功的调用了两个print 至此，编写自己的Caffe层就成功了
PS: 编写的时候严格注意路径否则会出现以下报错
本文参与 腾讯云自媒体分享计划，分享自作者个人站点/博客。
原始发表：2018/12/16 ，如有侵权请联系 cloudcommunity@tencent.com 删除
评论
登录后参与评论
推荐阅读
目录