PyTorch中的拷贝与就地操作详解

import torch # import main library
import torch.nn as nn # import modules like nn.ReLU()
import torch.nn.functional as F # import torch functions like F.relu() and F.relu_()

def get_memory_allocated(device, inplace = False):
 '''
 Function measures allocated memory before and after the ReLU function call.
 INPUT:
 - device: gpu device to run the operation
 - inplace: True - to run ReLU in-place, False - for normal ReLU call
 '''
 
 # Create a large tensor
 t = torch.randn(10000, 10000, device=device)
 
 # Measure allocated memory
 torch.cuda.synchronize()
 start_max_memory = torch.cuda.max_memory_allocated() / 1024**2
 start_memory = torch.cuda.memory_allocated() / 1024**2
 
 # Call in-place or normal ReLU
 if inplace:
 F.relu_(t)
 else:
 output = F.relu(t)
 
 # Measure allocated memory after the call
 torch.cuda.synchronize()
 end_max_memory = torch.cuda.max_memory_allocated() / 1024**2
 end_memory = torch.cuda.memory_allocated() / 1024**2
 
 # Return amount of memory allocated for ReLU call
 return end_memory - start_memory, end_max_memory - start_max_memory
 # setup the device
device = torch.device('cuda:0' if torch.cuda.is_available() else "cpu")
#开始测试
# Call the function to measure the allocated memory for the out-of-place ReLU
memory_allocated, max_memory_allocated = get_memory_allocated(device, inplace = False)
print('Allocated memory: {}'.format(memory_allocated))
print('Allocated max memory: {}'.format(max_memory_allocated))
'''
Allocated memory: 382.0
Allocated max memory: 382.0
'''
#Then call the in-place ReLU as follows:
memory_allocated_inplace, max_memory_allocated_inplace = get_memory_allocated(device, inplace = True)
print('Allocated memory: {}'.format(memory_allocated_inplace))
print('Allocated max memory: {}'.format(max_memory_allocated_inplace))
'''
Allocated memory: 0.0
Allocated max memory: 0.0
'''

import torch as t
import numpy as np
a = np.ones(4)
b = t.from_numpy(a) # Numpy->Tensor
print(a)
print(b)
'''输出：
[1. 1. 1. 1.]
tensor([1., 1., 1., 1.], dtype=torch.float64)
'''
b.add_(1)# add_会修改b自身
print(a)
print(b)
'''输出：
[2. 2. 2. 2.]
tensor([2., 2., 2., 2.], dtype=torch.float64)
b进行add操作后, a,b同步发生了变化
'''

x = torch.tensor([1, 2])
y = torch.tensor([3, 4])
id_0 = id(y)
y = y + x
print(id(y) == id_0) 
# False 

x = torch.tensor([1, 2])
y = torch.tensor([3, 4])
id_0 = id(y)
y[:] = y + x
print(id(y) == id_0) 
# True

x = torch.tensor([1, 2])
y = torch.tensor([3, 4])
id_0 = id(y)
torch.add(x, y, out=y) 
# y += x, y.add_(x)
print(id(y) == id_0) 
# True

import torch

a = torch.tensor(1.0, requires_grad=True)
b = a.clone()
c = a.detach()
a.data *= 3
b += 1

print(a) # tensor(3., requires_grad=True)
print(b)
print(c)

'''
输出结果：
tensor(3., requires_grad=True)
tensor(2., grad_fn=<AddBackward0>)
tensor(3.)  # detach()后的值随着a的变化出现变化
'''

import torch as t
a = t.tensor([1.0,2.0], requires_grad=True)
b = a.detach()
#c[:] = a.detach()
print(id(a))
print(id(b))
#140568935450520
140570337203616

import torch
a = torch.tensor(1.0, requires_grad=True)
a_ = a.clone()
y = a**2
z = a ** 2+a_ * 3
y.backward()
print(a.grad) # 2
z.backward()
print(a_.grad)　　　# None. 中间variable，无grad
print(a.grad) 
'''
输出：
tensor(2.) 
None
tensor(7.) # 2*2+3=7
'''

import torch
torch.manual_seed(0)

x= torch.tensor([1., 2.], requires_grad=True)
clone_x = x.clone() 
detach_x = x.detach()
clone_detach_x = x.clone().detach() 

f = torch.nn.Linear(2, 1)
y = f(x)
y.backward()

print(x.grad)
print(clone_x.requires_grad)
print(clone_x.grad)
print(detach_x.requires_grad)
print(clone_detach_x.requires_grad)
'''
输出结果如下：
tensor([-0.0053, 0.3793])
True
None
False
False
'''

import torch
a = torch.tensor(1.0)
a_ = a.clone()
a_.requires_grad_() #require_grad=True
y = a_ ** 2
y.backward()
print(a.grad) # None
print(a_.grad) 
'''
输出：
None
tensor(2.)
'''