支持CUDA11.1吗

[MachineVision123]

我使用 from warp_ctc import CTCLoss 之后，报错：
ImportError: ....... warp-ctc-pytorch_bindings/pytorch_binding/warpctc_pytorch/_warp_ctc.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN3c1011CPUTensorIdEv
我之前是能用的。然后我用nvidia-smi查看cuda版本为11.1 ，请问是否不支持cuda11.1？期待解答，不胜感激！

[Rhythmblue]

I add some lines in CMakeLists for RTX3090+CUDA11.1+pytorch1.7.1.

warp-ctc/CMakeLists.txt

Lines 50 to 57 in e2609d8

	IF (CUDA_VERSION GREATER 8.9)
	set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_70,code=sm_70")
	ENDIF()
	if (NOT APPLE)
	set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} --std=c++14")
	set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}")
	ENDIF()

IF (CUDA_VERSION GREATER 8.9)   
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_70,code=sm_70")
ENDIF()

IF (CUDA_VERSION GREATER 9.9)
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_75,code=sm_75")
ENDIF() 

IF (CUDA_VERSION GREATER 10.9) 
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_80,code=sm_80")
ENDIF()                                                                          

if (NOT APPLE)    
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} --std=c++14") 
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}")
ENDIF() 

It works for the following testing codes,

import torch        
import warpctc_pytorch as warp_ctc

def test_simple():      
    probs = torch.FloatTensor([[[0.1, 0.6, 0.1, 0.1, 0.1], [0.1, 0.1, 0.6, 0.1, 0.1]]]).transpose(0, 1).contiguous()
    grads = torch.zeros(probs.size())                                                                               
    labels = torch.IntTensor([1, 2])                                                                                
    label_sizes = torch.IntTensor([2])   
    sizes = torch.IntTensor(probs.size(1)).fill_(probs.size(0)) 
    minibatch_size = probs.size(1)                                                                                  
    costs = torch.zeros(minibatch_size)                                                                             
    warp_ctc.cpu_ctc(probs,                                                                                         
                     grads,                                                                                         
                     labels,                                                                                        
                     label_sizes,                                                                                   
                     sizes,                                                                                         
                     minibatch_size,                                                                                
                     costs,                                                                                         
                     0)                                                                                             
    print('CPU_cost: %f' % costs.sum())                                                                             
    probs = probs.clone().cuda()                                                                                    
    grads = torch.zeros(probs.size()).cuda()                                                                        
    costs = torch.zeros(minibatch_size)                                                                             
    warp_ctc.gpu_ctc(probs,                                                                                         
                     grads,                                                                                         
                     labels,                                                                                        
                     label_sizes,                                                                                   
                     sizes,                                                                                         
                     minibatch_size,                                                                                
                     costs,                                                                                         
                     0)                                                                                             
    print('GPU_cost: %f' % costs.sum())                                                                             
    print(grads.view(grads.size(0) * grads.size(1), grads.size(2)))

if __name__ == '__main__':
    test_simple()

Output:

CPU_cost: 2.462858        
GPU_cost: 2.462858    
tensor([[ 0.1770, -0.7081,  0.1770,  0.1770,  0.1770],    
        [ 0.1770,  0.1770, -0.7081,  0.1770,  0.1770]], device='cuda:0')

[Luna-yu]

I add some lines in CMakeLists for RTX3090+CUDA11.1+pytorch1.7.1.

warp-ctc/CMakeLists.txt

Lines 50 to 57 in e2609d8

	IF (CUDA_VERSION GREATER 8.9)
	set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_70,code=sm_70")
	ENDIF()
	if (NOT APPLE)
	set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} --std=c++14")
	set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}")
	ENDIF()

IF (CUDA_VERSION GREATER 8.9)   
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_70,code=sm_70")
ENDIF()

IF (CUDA_VERSION GREATER 9.9)
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_75,code=sm_75")
ENDIF() 

IF (CUDA_VERSION GREATER 10.9) 
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -gencode arch=compute_80,code=sm_80")
ENDIF()                                                                          

if (NOT APPLE)    
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} --std=c++14") 
    set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}")
ENDIF() 

It works for the following testing codes,

import torch        
import warpctc_pytorch as warp_ctc

def test_simple():      
    probs = torch.FloatTensor([[[0.1, 0.6, 0.1, 0.1, 0.1], [0.1, 0.1, 0.6, 0.1, 0.1]]]).transpose(0, 1).contiguous()
    grads = torch.zeros(probs.size())                                                                               
    labels = torch.IntTensor([1, 2])                                                                                
    label_sizes = torch.IntTensor([2])   
    sizes = torch.IntTensor(probs.size(1)).fill_(probs.size(0)) 
    minibatch_size = probs.size(1)                                                                                  
    costs = torch.zeros(minibatch_size)                                                                             
    warp_ctc.cpu_ctc(probs,                                                                                         
                     grads,                                                                                         
                     labels,                                                                                        
                     label_sizes,                                                                                   
                     sizes,                                                                                         
                     minibatch_size,                                                                                
                     costs,                                                                                         
                     0)                                                                                             
    print('CPU_cost: %f' % costs.sum())                                                                             
    probs = probs.clone().cuda()                                                                                    
    grads = torch.zeros(probs.size()).cuda()                                                                        
    costs = torch.zeros(minibatch_size)                                                                             
    warp_ctc.gpu_ctc(probs,                                                                                         
                     grads,                                                                                         
                     labels,                                                                                        
                     label_sizes,                                                                                   
                     sizes,                                                                                         
                     minibatch_size,                                                                                
                     costs,                                                                                         
                     0)                                                                                             
    print('GPU_cost: %f' % costs.sum())                                                                             
    print(grads.view(grads.size(0) * grads.size(1), grads.size(2)))

if __name__ == '__main__':
    test_simple()

Output:

CPU_cost: 2.462858        
GPU_cost: 2.462858    
tensor([[ 0.1770, -0.7081,  0.1770,  0.1770,  0.1770],    
        [ 0.1770,  0.1770, -0.7081,  0.1770,  0.1770]], device='cuda:0')

(yu_tf_py) root@gao-PowerEdge-T640:/yu_ex/warp-ctc3333/pytorch_binding# python setup.py install
Traceback (most recent call last):
File "setup.py", line 6, in
from torch.utils.cpp_extension import BuildExtension, CppExtension
ModuleNotFoundError: No module named 'torch.utils'
(yu_tf_py) root@gao-PowerEdge-T640:/yu_ex/warp-ctc3333/pytorch_binding# pip install torch.utils
Requirement already satisfied: torch.utils in /root/ana3/envs/yu_tf_py/lib/python3.6/site-packages (0.1.2)
Requirement already satisfied: torch in /root/ana3/envs/yu_tf_py/lib/python3.6/site-packages (from torch.utils) (1.7.1+cu110)
Requirement already satisfied: numpy in /root/ana3/envs/yu_tf_py/lib/python3.6/site-packages (from torch->torch.utils) (1.19.2)
Requirement already satisfied: dataclasses in /root/ana3/envs/yu_tf_py/lib/python3.6/site-packages (from torch->torch.utils) (0.8)
Requirement already satisfied: typing-extensions in /root/ana3/envs/yu_tf_py/lib/python3.6/site-packages (from torch->torch.utils) (3.7.4.3)
I encountered such a problem when running install. Would you like to ask me if you have encountered any?
cuda11.1 torch 1.7.1