本文整理汇总了Python中util.Util.load_from_npz方法的典型用法代码示例。如果您正苦于以下问题：Python Util.load_from_npz方法的具体用法？Python Util.load_from_npz怎么用？Python Util.load_from_npz使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类util.Util的用法示例。
在下文中一共展示了Util.load_from_npz方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: train
# 需要导入模块: from util import Util [as 别名]
# 或者: from util.Util import load_from_npz [as 别名]
def train(nn_name = '12-net',rootdir = 'F:\\'):
"""
Fucntion for traning 12-net with testing on part of data
using cross validation
"""
is_calib = nn_name.find('calib') > 0
X_name = 'train_data_'+('icalib_' if is_calib else '' )+ nn_name[:2] + '.npz'
y_name = 'labels_'+('icalib_' if is_calib else '' )+ nn_name[:2] + '.npz'
is_calib = nn_name.find('calib') > 0
rates = sp.hstack((0.05 * sp.ones(333,dtype=sp.float32),0.005*sp.ones(333,dtype=sp.float32),0.0005*sp.ones(333,dtype=sp.float32),
0.00005*sp.ones(5,dtype=sp.float32)))
rates12 = rates
rates24 = rates
rates48 = rates
rates12_c = rates12[333:666]
rates48_c = rates12_c
rates24_c = rates12_c
if nn_name == '24-net':
if is_calib:
nn = Cnnl(nn_name = nn_name,l_rates=rates24_c)
else:
nn = Cnnl(nn_name = nn_name,l_rates=rates24)
elif nn_name == '48-net':
if is_calib:
nn = Cnnl(nn_name = nn_name,l_rates=rates48_c)
else:
nn = Cnnl(nn_name = nn_name,l_rates=rates48)
else:
if is_calib:
nn = Cnnl(nn_name = nn_name,l_rates=rates12_c)
else:
nn = Cnnl(nn_name = nn_name,l_rates = rates12)
if is_calib:
X = util.load_from_npz(X_name)
y = util.load_from_npz(y_name)
nn.fit(X,y)
else:
rpath = os.path.join(rootdir,'traindata',nn.nn_name)
nn.train_on_hdd(rootdir = rpath)
nn.__save_model_old__(nn_name + '_lasagne_.pickle')示例2: train_on_hdd
# 需要导入模块: from util import Util [as 别名]
# 或者: from util.Util import load_from_npz [as 别名]
def train_on_hdd(self,rootdir = '12-net/'):
print(self.nn_name,'training start...','data folder',rootdir)
mean_acc = 0
total_time = 0
bpaths = util.get_files(rootdir = rootdir,fexpr = '*.npz')
m = len(bpaths)
r = len(util.load_from_npz(bpaths [-1]))
total_len = m * len(util.load_from_npz(bpaths [0]))
print('data input size is around',total_len)
for epoch in range(self.max_epochs):
self.eta.set_value(self.l_rates[epoch])
t_loss = 0
start = time()
for bpath in bpaths:
batch = util.load_from_npz(bpath)
items,labels = batch[:,0],batch[:,1]
items = sp.array([e.astype(sp.float32) for e in items])
labels = labels.astype(sp.int32)
X_train, X_val, y_train, y_val = train_test_split(items,labels,test_size = 0.25)
t_loss += self.__train_fn__ (X_train,y_train)
val_acc = 0
val_batches = 0
for xval,yval in self.iterate_minibatches(X_val,y_val,16):
err, acc = self.__val_fn__(xval, yval)
val_acc += acc
val_batches += 1
if self.verbose:
dur = time() - start
a0 = 100*(val_acc/val_batches)
mean_acc += a0
total_time += dur
print("epoch %d out of %d \t loss %g \t acсuracy %g \t time %d s \t" % (epoch + 1,self.max_epochs, t_loss / (total_len),a0,dur))
m = (total_time)//60
s = total_time - 60 * m
h = m//60
m = m - 60 * h
mean_acc = mean_acc / self.max_epochs
print('Training end with total time %d h %d m %d s and mean accouracy over epochs %g' % (h,m,s,mean_acc))示例3: cv
# 需要导入模块: from util import Util [as 别名]
# 或者: from util.Util import load_from_npz [as 别名]
def cv(nn_name,d_num = 10000,k_fold = 7,score_metrics = 'accuracy',verbose = 0):
suff = str(nn_name[:2])
if nn_name.find('calib') > 0:
X_data_name = 'train_data_icalib_'+ suff + '.npz'
y_data_name = 'labels_icalib_'+ suff + '.npz'
else:
X_data_name = 'train_data_'+ suff + '.npz'
y_data_name = 'labels_'+ suff + '.npz'
X,y = util.load_from_npz(X_data_name),util.load_from_npz(y_data_name)
d_num = min(len(X),d_num)
X = X[:d_num]
y = y[:d_num]
rates12 = sp.hstack((0.001 * sp.ones(70,dtype=sp.float32),0.0001*sp.ones(20,dtype=sp.float32),0.00001*sp.ones(5,dtype=sp.float32)))
rates24 = sp.hstack((0.01 * sp.ones(25,dtype=sp.float32),0.0001*sp.ones(15,dtype=sp.float32)))
rates48 = sp.hstack ([0.05 * sp.ones(15,dtype=sp.float32),0.005*sp.ones(10,dtype=sp.float32) ])
if nn_name == '48-net':
X12 = util.load_from_npz('train_data_12.npz')[:d_num]
X24 = util.load_from_npz('train_data_24.npz')[:d_num]
elif nn_name == '24-net':
X12 = util.load_from_npz('train_data_12.npz')[:d_num]
if score_metrics == 'accuracy':
score_fn = accuracy_score
elif score_metrics == 'f1':
score_fn = f1_score
elif score_metrics == 'recall':
score_fn = recall_score
scores = []
iteration = 0
for t_indx,v_indx in util.kfold(X,y,k_fold=k_fold):
nn = None
X_train,X_test,y_train,y_test = X[t_indx], X[v_indx], y[t_indx], y[v_indx]
#print('\t \t',str(iteration+1),'fold out of ',str(k_fold),'\t \t' )
if nn_name == '24-net':
nn = Cnnl(nn_name = nn_name,l_rates=rates24,verbose=verbose,subnet=Cnnl(nn_name = '12-net',l_rates=rates12,verbose=verbose).load_model(
'12-net_lasagne_.pickle'))
nn.fit(X = X_train,y = y_train,X12 = X12[t_indx])
elif nn_name == '48-net':
nn = Cnnl(nn_name = nn_name,l_rates=rates48,subnet=Cnnl(nn_name = '24-net',l_rates=rates24,subnet=Cnnl(nn_name = '12-net',l_rates=rates12).load_model(
'12-net_lasagne_.pickle')).load_model('24-net_lasagne_.pickle'))
nn.fit(X = X_train,y = y_train,X12 = X12[t_indx],X24 = X24[t_indx])
else:
nn = Cnnl(nn_name = nn_name,l_rates=rates12,verbose=0)
nn.fit(X = X_train,y = y_train)
if nn_name == '24-net':
y_pred = nn.predict(X_test,X12=X12[v_indx])
elif nn_name == '48-net':
y_pred = nn.predict(X_test,X12=X12[v_indx],X24=X24[v_indx])
else:
y_pred = nn.predict(X_test)
score = score_fn(y_test,y_pred)
#print(iteration,'fold score',score)
scores.append(score)
iteration += 1
score_mean = sp.array(scores).mean()
print(d_num,'mean score',score)
return score_mean