caffe是賈揚清大神開發的一套系統，caffe2是重構後的版本。其基本結構為：
import numpy as np
import time
from caffe2.python import core, workspace
from caffe2.proto import caffe2_pb2
x = np.random.randn(2, 3).astype(np.float32)
print("generated x from numpy:\n{}".format(x))
workspace.feedblob("x", x)
print(workspace.blobs())
print(workspace.fetchblob('x'))
fetchblob獲得具體的資料
op = core.createoperator(
"relu", # the type of operator that we want to run
["x"], # a list of input blobs by their names
["y"], # a list of output blobs by their names
'active1'
)workspace.runoperatoronce(op)
workspace.fetchblobs('y')
op2 = core.createoperator(
"gaussianfill",
, # gaussianfill does not need any parameters.
["w"],
shape=[100, 100], # shape argument as a list of ints.
mean=1.0, # mean as a single float
std=1.0, # std as a single float
)workspace.runoperatoronce(op2)
temp = workspace.fetchblob("z")
net = core.net("linear_net")
x = net.gaussianfill(, ["x"], mean=0.0, std=1.0, shape=[2, 3], run_once=0)
w = net.gaussianfill(, ["w"], mean=0.0, std=1.0, shape=[5, 3], run_once=0)
b = net.constantfill(, ["b"], shape=[5,], value=1.0, run_once=0)
y = net.fc([x,w,b],['y'])
print(net.proto())
workspace.runnetonce(net)
for name in workspace.blobs():
print("{}:\n{}".format(name, workspace.fetchblob(name)))
方法1:使用workspace.runnetonce,初始化網路，執行網路，然後銷毀網路。
方法2:先使用workspace.createnet初始化網路，然後使用workspace.runnet來執行網路。
可以用下面的**來畫圖：
caffe2為了更方便呼叫和管理，可以通過匯入brew這個包來呼叫幫助函式。像fc層的實現就可以使用：
from caffe2.python import brew
brew.fc(model, blob_in, blob_out, ...)
from caffe2.python import brew
def addlenetmodel(model, data):
conv1 = brew.conv(model, data, 'conv1', 1, 20, 5)
pool1 = brew.max_pool(model, conv1, 'pool1', kernel=2, stride=2)
conv2 = brew.conv(model, pool1, 'conv2', 20, 50, 5)
pool2 = brew.max_pool(model, conv2, 'pool2', kernel=2, stride=2)
fc3 = brew.fc(model, pool2, 'fc3', 50 * 4 * 4, 500)
fc3 = brew.relu(model, fc3, fc3)
pred = brew.fc(model, fc3, 'pred', 500, 10)
softmax = brew.softmax(model, pred, 'softmax')
Caffe深度學習計算框架
1 caffe set mode caffe gpu 1 name dummy net 2 3 layers 45 layers 67 layers 8 layers 1 name conv1 2 type convolution 3 bottom data 4 top conv1 5 convol...
唐宇迪深度學習框架Caffe系列 10
繪製loss曲線 安裝matplotlib庫 這個庫需要安裝python tk sudo apt get install python tksudo pip install matplotlib import numpy as np import matplotlib.pyplot as plt i...
深度學習框架caffe訓練過程
1.資料準備 2.生成訓練資料和測試資料的label，生成 3.生成訓練資料和測試資料對應的lmdb build tools convert imageset shuffle true backend lmdb data cigarettetrain20170413 data cigarettetr...