numpy.savez的使用方法

参考文档：https://docs.scipy.org/doc/numpy-1.12.0/reference/generated/numpy.load.html

 

>>> a=np.array([[1, 2, 3], [4, 5, 6]])
>>> b=np.array([1, 2])
>>> np.savez('/tmp/123.npz', a=a, b=b)
>>> data = np.load('/tmp/123.npz')
>>> data['a']
array([[1, 2, 3],
       [4, 5, 6]])
>>> data['b']
array([1, 2])
>>> data.close()

 

我的示例：

train_Resnet50 = extract_Resnet50(paths_to_tensor(train_files)) ###x, 1, 1, 2048
valid_Resnet50 = extract_Resnet50(paths_to_tensor(valid_files)) ###x, 1, 1, 2048

test_Resnet50  = extract_Resnet50(paths_to_tensor(test_files))  ###x, 1, 1, 2048

np.savez('bottleneck_features/DogResnet50Data.npz',train=train_Resnet50,valid=valid_Resnet50,test=test_Resnet50)

 

bottleneck_features = np.load('bottleneck_features/DogResnet50Data.npz')
train_Resnet502 = bottleneck_features['train']
valid_Resnet502 = bottleneck_features['valid']
test_Resnet502 = bottleneck_features['test']