摘要：使用示例 x = x[:,:,torch.arange(x.size(2))%8!=0] 剪切掉第三个维度的8的整数行 维度上不仅支持用：进行多行选择，也可以用bool组成的tensor判断是否保存这一行。

摘要：问题报错 RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [544, 768]], whi

摘要：train.py import torch import numpy as np import os import math import sys import argparse import psutil import torch import torch.optim as optim impor

摘要：#run.py import argparse parser = argparse.ArgumentParser() parser.add_argument('--device', type=str, default='cpu:0',help='use which device') parser.a

摘要：实现模版 class our_dataset(Dataset): def __init__(self,···): super(our_dataset, self).__init__() #初始化，可以自定义添加参数 def __getitem__(self,index): ··· return im

摘要：import os import psutil info = psutil.virtual_memory() print(u'cpu个数：',psutil.cpu_count()) print(u'电脑总内存：%.4f GB' % (info.total / 1024 / 1024 / 1024))