python代码

Question

我正在尝试使用Python中的火炬制作我自己的数据集。但是，每个文件打开时内存使用都会泄漏。

在以下for循环期间发生内存泄漏

for subj, _file in enumerate(filelist):

我在代码中删除了不必要的内容，例如import

parser.add_argument('--stddev', dest='stddev', default='subject', type=str, help="How to calculate ")
args = parser.parse_args()

# Options
if args.sess_num == 0:
  label_set = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

base_dir = './kriss_proto'
ori_base_dir = '{}/original'.format(base_dir)
filelist = os.listdir(ori_base_dir) # ['BD001.mat', ...]
filenum = len(filelist)

# Saving data
eeg_data = {}
eeg_data['dataset'] = {}
split_data = {}
split_data['splits'] = []
split_data['splits'].append({})

_meanstd = []
for i in range(32):
  _meanstd.append([])
  if args.stddev == 'subject':
    for j in range(filenum):
      _meanstd[i].append([])

idx = 0

for subj, _file in enumerate(filelist):
  filepath = os.path.join(ori_base_dir, _file)
  with h5py.File(filepath, 'r') as mat:

    ## Step by step (with object searching)
    bd_eeg = mat.get('BD_EEG')
    vst = bd_eeg.get('VST')

    for run in vst.keys():
      print("Processing {} - {}".format(_file, run))
      run_data = vst.get(run)
      eeg = run_data['data3D']
      eeg = th.Tensor(eeg)
      eeg = eeg.permute(2, 1, 0)

      label = run_data['class_labels']
      label = th.Tensor(label)
      label = th.squeeze(label)

      # DATA COPY
      for i in range(int(label.shape[0])):
        if (label[i] in label_set) and (int(eeg[i].shape[0]) > 400):
          eeg_data['dataset'][idx] = {}
          eeg_data['dataset'][idx]['eeg'] = eeg[i, :, :32]
          eeg_data['dataset'][idx]['label'] = label[i] - label_set[0] # label should start from 0
          if args.stddev == 'whole':
            for j in range(32):
              for k in range(int(eeg[i].shape[0])):
                _meanstd[j].append(eeg[i][k, j])
          elif args.stddev == 'subject':
            for j in range(32):
              for k in range(int(eeg[i].shape[0])):
                _meanstd[j][subj].append(eeg[i][k, j])     

          idx += 1