Caffe 实例笔记 3 Brewing Logistic Regression then Going Deeper_logistic regression improve accuracy-CSDN博客

本文链接：https://blog.csdn.net/bea_tree/article/details/51648486

From now on, I will try to write some blogs in English to improve my English writing skills. If there is anything wrong in the blogs ,please let me know. Thanks.
In this example, we will
1. use caffe as a generic SGD optimizer to train logistic regression ,
2. and then we will add layers to improve accuracy.

1 classify with sklearn

shutil - Utility functions for copying and archiving files and directory trees.

Note the following function when generate a binary classification:

sklearn.datasets.make_classification(...)
sklearn.cross_validation.train_test_split(X,y)
ind=np.random.permutation(X.shape[0])[:1000]
df=pd.DataFrame(X[ind])
_=pd.scatter_matrix(df,figsize=(9,9),diagonal='kde',marker='o',s=40,alpha=0.4,c=y[ind])#alpha=transparency
clf = sklearn.linear_model.SGDClassifier(...)
clf.fit(X, y)
yt_pred = clf.predict(Xt)
print('Accuracy: {:.3f}'.format(sklearn.metrics.accuracy_score(yt, yt_pred)))

we can get the result like this:
accuracy:0.772
accuracy:0.772
accuracy:0.772
accuracy:0.772
1 loops, best of 3: 443 ms per loop

2 use caffe

2.1 save dataset to HDF5

?

dirname=os.path.abspath('/home/beatree/caffe-rc3/examples/hdf5_classification/data')
if not os.path.exists(dirname):
    os.makedirs(dirname)
train_filename=os.path.join(dirname,'train.h5')
test_filename=os.path.join(dirname,'test.h5')
with h5py.File(train_filename,'w')as f:
    f['data']=X
    f['label']=y.astype(np.float32)
with open(os.path.join(dirname,'train.txt'),'w') as f:
    f.write(train_filename+'\n')#why list the same data file twice???
    f.write(train_filename+'\n')
comp_kwargs={'compression':'gzip','compression_opts':1}
with h5py.File(test_filename,'w')as f: 
    f.create_dataset('data',data=Xt,**comp_kwargs)
    f.create_dataset('label',data=yt.astype(np.float32),**comp_kwargs)
with open (os.path.join(dirname,'test.txt'),'w')as f:
    f.write(test_filename+'\n')

2.2 prottobuf model(shallow)

from caffe import layers as L
from caffe import params as P
def logreg(hdf5,batch_size):
    n=caffe.NetSpec()
    n.data,n.label=L.HDF5Data(batch_size=batch_size,source=hdf5,ntop=2)
    n.ip1=L.InnerProduct(n.data,num_output=2,weight_filler=dict(type='xavier'))
    n.accuracy=L.Accuracy(n.ip1,n.label)
    n.loss=L.SoftmaxWithLoss(n.ip1,n.label)
    return n.to_proto()
train_net_path='/home/beatree/caffe-rc3/examples/hdf5_classification/logreg_auto_train.prototxt'
test_net_path='/home/beatree/caffe-rc3/examples/hdf5_classification/logreg_auto_test.prototxt'
with open(train_net_path,'w')as f:
    f.write(str(logreg('/home/beatree/caffe-rc3/examples/hdf5_classification/data/train.txt',10)))
with open(test_net_path,'w')as f:
    f.write(str(logreg('/home/beatree/caffe-rc3/examples/hdf5_classification/data/test.txt',10)))

solver.prototxt

from caffe.proto import caffe_pb2
def solver(train_net_path,test_net_path):
    s= caffe_pb2.SolverParameter()
    s.train_net= train_net_path
    s.test_net.append(test_net_path)
    s.test_interval=1000
    s.test_iter.append(250)
    s.max_iter=10000
    s.base_lr=0.01
    s.lr_policy='step'
    s.gamma=0.1
    s.stepsize=5000
    s.momentum=0.9
    s.weight_decay=5e-4
    s.display=1000
    s.snapshot=10000
    s.snapshot_prefix='/home/beatree/caffe-rc3/examples/hdf5_classification/data/train'
    s.solver_mode=caffe_pb2.SolverParameter.CPU
    return s
solver_path='/home/beatree/caffe-rc3/examples/hdf5_classification/logreg_solver.protxt'
with open (solver_path,'w') as f:
    f.write(str(solver(train_net_path,test_net_path)))

%%timeit
caffe.set_mode_cpu()
solver=caffe.get_solver(solver_path)
solver.solve()
accuracy=0
batch_size=solver.test_nets[0].blobs['data'].num
test_iters=int(len(Xt)/batch_size)
for i in range (test_iters):
    solver.test_nets[0].forward()
    accuracy+=solver.test_nets[0].blobs['accuracy'].data
accuracy/=test_iters
print ('accuracy:{:.3}'.format(accuracy))

accuracy:0.771
accuracy:0.771
10 loops, best of 3: 156 ms per loop

2.3 deeper model

from caffe import layers as L
from caffe import params as P
def nonlinear_net(hdf5,batch_size):
    n=caffe.NetSpec()
    n.data,n.label=L.HDF5Data(batch_size=batch_size,source=hdf5,ntop=2)
    n.ip1=L.InnerProduct(n.data,num_output=40,weight_filler=dict(type='xavier'))
    n.relu1=L.ReLU(n.ip1,in_place=True)
    n.ip2=L.InnerProduct(n.relu1,num_output=2,weight_filler=dict(type='xavier'))
    n.accuracy=L.Accuracy(n.ip2,n.label)
    n.loss=L.SoftmaxWithLoss(n.ip2,n.label)
    return n.to_proto()
train_net_path='/home/beatree/caffe-rc3/examples/hdf5_classification/nonlinear_auto_train.prototxt'
test_net_path='/home/beatree/caffe-rc3/examples/hdf5_classification/nonlinear_auto_test.prototxt'
with open(train_net_path,'w')as f:
    f.write(str(nonlinear_net('/home/beatree/caffe-rc3/examples/hdf5_classification/data/train.txt',10)))
with open(test_net_path,'w')as f:
    f.write(str(nonlinear_net('/home/beatree/caffe-rc3/examples/hdf5_classification/data/test.txt',10)))
solver_path='/home/beatree/caffe-rc3/examples/hdf5_classification/nonliear_logreg_solver.prototxt'
with open (solver_path,'w') as f:
    f.write(str(solver(train_net_path,test_net_path)))

%%timeit
caffe.set_mode_cpu()
solver=caffe.get_solver(solver_path)
solver.solve()
accuracy=0
batch_size=solver.test_nets[0].blobs['data'].num
test_iters=int(len(Xt)/batch_size)
for i in range (test_iters):
    solver.test_nets[0].forward()
    accuracy+=solver.test_nets[0].blobs['accuracy'].data
accuracy/=test_iters
print ('acc:{:.3}'.format(accuracy))