pytorch的显存释放机制torch.cuda.empty_cache()
参考：
https://cloud.tencent.com/developer/article/1626387
据说在pytorch中使用torch.cuda.empty_cache()可以释放缓存空间，于是做了些尝试：
上代码：
import torch import time import os #os.environ["CUDA_VISIBLE_DEVICES"] = "3" device='cuda:2' dummy_tensor_4 = torch.randn(120, 3, 512, 512).float().to(device) # 120*3*512*512*4/1024/1024 = 360.0M memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第一阶段：") print("变量类型：", dummy_tensor_4.dtype) print("变量实际占用内存空间：", 120*3*512*512*4/1024/1024, "M") print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") torch.cuda.empty_cache() time.sleep(15) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第二阶段：") print("释放缓存后:", "."*100) print("变量实际占用内存空间：", 120*3*512*512*4/1024/1024, "M") print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") del dummy_tensor_4 torch.cuda.empty_cache() time.sleep(15) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第三阶段：") print("删除变量后释放缓存后:", "."*100) print("变量实际占用内存空间：", 0, "M") print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") time.sleep(60)
运行结果：
第一阶段：
第二阶段：
第三阶段：
===================================================
可以看到在pytorch中显存创建360M的变量其实总占有了1321M空间，其中变量自身占了360M空间，缓存也占了360M空间，中间多出了那1321-360*2=601M空间却无法解释，十分诡异。
总的来说 torch.cuda.empty_cache() 操作有一定用处，但是用处不太大。
===================================================
更改代码：
import torch import time import os #os.environ["CUDA_VISIBLE_DEVICES"] = "3" device='cuda:2' dummy_tensor_4 = torch.randn(120, 3, 512, 512).float().to(device) # 120*3*512*512*4/1024/1024 = 360.0M dummy_tensor_5 = torch.randn(120, 3, 512, 512).float().to(device) # 120*3*512*512*4/1024/1024 = 360.0M memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第一阶段：") print("变量类型：", dummy_tensor_4.dtype) print("变量实际占用内存空间：", 2*120*3*512*512*4/1024/1024, "M") print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") torch.cuda.empty_cache() time.sleep(15) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第二阶段：") print("释放缓存后:", "."*100) print("变量实际占用内存空间：", 2*120*3*512*512*4/1024/1024, "M") print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") del dummy_tensor_4 del dummy_tensor_5 torch.cuda.empty_cache() time.sleep(15) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第三阶段：") print("删除变量后释放缓存后:", "."*100) print("变量实际占用内存空间：", 0, "M") print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") time.sleep(60)
第一阶段：
第二阶段：
第三阶段：
发现依然有显存空间无法解释。
=============================================
上面的操作都是在24G显存的titan上进行的，最后决定用1060显卡试验下，6G显存比较好尝试。
代码：
import torch import time import os import functools #os.environ["CUDA_VISIBLE_DEVICES"] = "3" device='cuda:0' shape_ = (4, 1024, 512, 512) # 4GB # dummy_tensor_4 = torch.randn(120, 3, 512, 512).float().to(device) # 120*3*512*512*4/1024/1024 = 360.0M # dummy_tensor_5 = torch.randn(10, 120, 3, 512, 512).float().to(device) # 120*3*512*512*4/1024/1024 = 360.0M dummy_tensor_6 = torch.randn(*shape_).float().to(device) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第一阶段：") print("变量类型：", dummy_tensor_6.dtype) print("变量实际占用内存空间：", functools.reduce(lambda x, y: x*y, shape_)*4/1024/1024, "M") print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") torch.cuda.empty_cache() time.sleep(15) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第二阶段：") print("释放缓存后:", "."*100) print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") del dummy_tensor_6 torch.cuda.empty_cache() time.sleep(15) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第三阶段：") print("删除变量后释放缓存后:", "."*100) print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") time.sleep(60)
输出结果：
第一阶段:
第二阶段:
第三阶段:
由于显卡总共6G显存，所以
memory_allocated
memory_reserved
这两部分应该是指的相同显存空间，因为这两个部分都是显示4G空间，总共6G空间。
可以看到单独执行：torch.cuda.empty_cache()
并没有释放显存，还是4775MB，但是执行：
del dummy_tensor_6
torch.cuda.empty_cache()
显存就进行了释放，为679MB。
更改代码：
import torch import time import os import functools #os.environ["CUDA_VISIBLE_DEVICES"] = "3" device='cuda:0' shape_ = (4, 1024, 512, 512) # 4GB # dummy_tensor_4 = torch.randn(120, 3, 512, 512).float().to(device) # 120*3*512*512*4/1024/1024 = 360.0M # dummy_tensor_5 = torch.randn(10, 120, 3, 512, 512).float().to(device) # 120*3*512*512*4/1024/1024 = 360.0M dummy_tensor_6 = torch.randn(*shape_).float().to(device) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第一阶段：") print("生成变量后:", "."*100) print("变量类型：", dummy_tensor_6.dtype) print("变量实际占用内存空间：", functools.reduce(lambda x, y: x*y, shape_)*4/1024/1024, "M") print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") torch.cuda.empty_cache() time.sleep(15) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第二阶段：") print("释放缓存后:", "."*100) print("变量类型：", dummy_tensor_6.dtype) print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") # for _ in range(10000): # dummy_tensor_6 += 0.001 # print(torch.sum(dummy_tensor_6)) del dummy_tensor_6 time.sleep(15) memory_allocated = torch.cuda.memory_allocated(device)/1024/1024 memory_reserved = torch.cuda.memory_reserved(device)/1024/1024 print("第三阶段：") print("删除变量后释放缓存后:", "."*100) print("GPU实际分配给的可用内存", memory_allocated, "M") print("GPU实际分配给的缓存", memory_reserved, "M") time.sleep(60)
运行结果：
NVIDIA显存显示第一，二，，三阶段均为：
如果没有执行torch.cuda.empty_cache()，即使删除GPU上的变量显存空间也不会被释放，该部分显存还为缓存空间所占。
================================================
torch.cuda.memory_reserved() - torch.cuda.memory_allocated
表示进程中空闲的显存空间（不是GPU空闲显存空间，而是进程已获得的显存中未被使用的空间）
================================================