我试图从包含digitStruct.mat文件的tar.gz文件中提取数据,我使用了以下代码片段。
train_dataset = h5py.File('./train/digitStruct.mat')
我想从这个对象本身访问bbox和名称的细节,例如:
train_dataset[0]
应该输出这样的内容:
{'boxes': [{'height': 219.0,
'label': 1.0,
'left': 246.0,
'top': 77.0,
'width': 81.0},
{'height': 219.0, 'label': 9.0, 'left': 323.0, 'top': 81.0, 'width': 96.0}],
'filename': '1.png'}
我搜索了一下,在这个链接上找到了一些帮助。
但是上面的链接涉及到创建单独的函数get_box_data(index, hdf5_data)和get_name(index, hdf5_data)来获取相应索引的值,但是我想直接从变量名train_dataset[index]中访问它。
好吧,我想我找到了我在上面的评论中提到的东西。 它将SVHN HDF5文件的.mat v7.3格式转换为更简单的工作。文件名被输入为 dsFileName=
. (我只有6个测试文件要转换,所以没有添加输入机制。)它需要一个名为: yourfilename.mat
的文件并转换为 yourfilename.h5
. 第二个文件更容易处理(更小更快!)。新的.h5文件有一个名为的数据集。digitStruct
每行有以下记录。
1.png
) 注意:这调用了github上共享的代码。URL和署名包含在下面的源代码中。
import h5py
import numpy as np
import os
import digitStruct
## Note digitStruct.py source found at:
## https://github.com/prijip/Py-Gsvhn-DigitStruct-Reader/blob/master/digitStruct.py
# Main
if __name__ == "__main__":
dsFileName = 'Stanford/extra/digitStruct.mat'
print ('Working on',os.path.split(dsFileName))
print ('Create .h5 called',os.path.splitext(dsFileName)[0]+'.h5')
h5f = h5py.File(os.path.splitext(dsFileName)[0]+'.h5', 'w')
print ('Created',os.path.split(h5f.filename))
# Count number of images in digitStruct.mat file [/name] dataset
mat_f = h5py.File(dsFileName)
num_img = mat_f['/digitStruct/name'].size
mat_f.close()
ds_dtype = np.dtype ( [('name','S16'), ('label','S10'), ('left','f8'),
('top','f8'), ('width','f8'), ('height','f8')] )
ds_recarray = np.recarray ( (10,) , dtype=ds_dtype )
ds_table = h5f.create_dataset('digitStruct', (2*num_img,), dtype=ds_dtype, maxshape=(None,) )
idx_dtype = np.dtype ( [('name','S16'), ('first','i4'), ('length','i4')] )
## idx_recarray = np.recarray ( (1,) , dtype=idx_dtype )
idx_table = h5f.create_dataset('idx_digitStruct', (num_img,), dtype=idx_dtype, maxshape=(None,) )
imgCounter = 0
lblCounter = 0
for dsObj in digitStruct.yieldNextDigitStruct(dsFileName):
if (imgCounter % 1000 == 0) :
print(dsObj.name)
if (idx_table.shape[0] < imgCounter ) : # resize idx_table as needed
idx_table.resize(idx_table.shape[0]+1000, axis=0)
idx_table[imgCounter,'name'] = dsObj.name
idx_table[imgCounter,'first'] = lblCounter
idx_table[imgCounter,'length'] = len(dsObj.bboxList)
raCounter = 0
for bbox in dsObj.bboxList:
ds_recarray[raCounter]['name'] = dsObj.name
ds_recarray[raCounter]['label'] = bbox.label
ds_recarray[raCounter]['left'] = bbox.left
ds_recarray[raCounter]['top'] = bbox.top
ds_recarray[raCounter]['width'] = bbox.width
ds_recarray[raCounter]['height'] = bbox.height
raCounter += 1
lblCounter += 1
if (ds_table.shape[0] < lblCounter ) : # resize ds_table as needed
ds_table.resize(ds_table.shape[0]+1000, axis=0)
ds_table[lblCounter-raCounter:lblCounter] = ds_recarray[0:raCounter]
imgCounter += 1
## if imgCounter >= 2000:
## break
print ('Total images processed:', imgCounter )
print ('Total labels processed:', lblCounter )
ds_table.resize(lblCounter, axis=0)
idx_table.resize(imgCounter, axis=0)
h5f.close()