NanCheng2001
commented
1 year ago More details are as follows:
Pre-trained model restored from C:/Users/PC2080ti/Desktop/Mulit-View/jishunping/1/REDNet-master/MODEL_FOLDER/model.ckpt-150000
2022-12-18 18:58:03.486554: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:704] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order.
2022-12-18 18:58:03.493902: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:704] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order.
2022-12-18 19:21:23.300856: E tensorflow/stream_executor/cuda/cuda_blas.cc:698] failed to run cuBLAS routine cublasGemmBatchedEx: CUBLAS_STATUS_EXECUTION_FAILED
2022-12-18 19:21:23.301035: E tensorflow/stream_executor/cuda/cuda_blas.cc:2620] Internal: failed BLAS call, see log for details
Traceback (most recent call last):
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\client\session.py", line 1334, in _do_call
return fn(*args)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\client\session.py", line 1319, in _run_fn
options, feed_dict, fetch_list, target_list, run_metadata)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\client\session.py", line 1407, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InternalError: Blas xGEMMBatched launch failed : a.shape=[8,3,3], b.shape=[8,3,3], m=3, n=3, k=3, batch_size=8
[[{{node get_homographies/MatMul_2}}]]
[[{{node while/RefExit}}]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:/Users/PC2080ti/Desktop/Mulit-View/jishunping/1/REDNet-master/predict.py", line 264, in <module>
tf.app.run()
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "C:/Users/PC2080ti/Desktop/Mulit-View/jishunping/1/REDNet-master/predict.py", line 259, in main
rednet_pipeline(mvs_list)
File "C:/Users/PC2080ti/Desktop/Mulit-View/jishunping/1/REDNet-master/predict.py", line 206, in rednet_pipeline
[init_depth_map, prob_map, croped_images, scaled_cams, croped_cams, locations])
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\client\session.py", line 929, in run
run_metadata_ptr)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\client\session.py", line 1152, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\client\session.py", line 1328, in _do_run
run_metadata)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\client\session.py", line 1348, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: Blas xGEMMBatched launch failed : a.shape=[8,3,3], b.shape=[8,3,3], m=3, n=3, k=3, batch_size=8
[[node get_homographies/MatMul_2 (defined at C:\Users\PC2080ti\Desktop\Mulit-View\jishunping\1\REDNet-master\homography_warping.py:45) ]]
[[node while/RefExit (defined at C:\Users\PC2080ti\Desktop\Mulit-View\jishunping\1\REDNet-master\model.py:294) ]]
Caused by op 'get_homographies/MatMul_2', defined at:
File "C:/Users/PC2080ti/Desktop/Mulit-View/jishunping/1/REDNet-master/predict.py", line 264, in <module>
tf.app.run()
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "C:/Users/PC2080ti/Desktop/Mulit-View/jishunping/1/REDNet-master/predict.py", line 259, in main
rednet_pipeline(mvs_list)
File "C:/Users/PC2080ti/Desktop/Mulit-View/jishunping/1/REDNet-master/predict.py", line 173, in rednet_pipeline
depth_num, depth_start, depth_end)
File "C:\Users\PC2080ti\Desktop\Mulit-View\jishunping\1\REDNet-master\model.py", line 163, in inference_winner_take_all
depth_start=depth_start, depth_interval=depth_interval)
File "C:\Users\PC2080ti\Desktop\Mulit-View\jishunping\1\REDNet-master\homography_warping.py", line 45, in get_homographies_Twc
middle_mat2 = tf.matmul(middle_mat0, middle_mat1)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\ops\math_ops.py", line 2417, in matmul
a, b, adj_x=adjoint_a, adj_y=adjoint_b, name=name)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 1483, in batch_mat_mul
"BatchMatMul", x=x, y=y, adj_x=adj_x, adj_y=adj_y, name=name)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\framework\ops.py", line 3300, in create_op
op_def=op_def)
File "C:\Users\PC2080ti\anaconda3\envs\pyxj37\lib\site-packages\tensorflow\python\framework\ops.py", line 1801, in __init__
self._traceback = tf_stack.extract_stack()
InternalError (see above for traceback): Blas xGEMMBatched launch failed : a.shape=[8,3,3], b.shape=[8,3,3], m=3, n=3, k=3, batch_size=8
[[node get_homographies/MatMul_2 (defined at C:\Users\PC2080ti\Desktop\Mulit-View\jishunping\1\REDNet-master\homography_warping.py:45) ]]
[[node while/RefExit (defined at C:\Users\PC2080ti\Desktop\Mulit-View\jishunping\1\REDNet-master\model.py:294) ]]
Hello, I used viewselection.py to correctly generate viewpair.txt. Other configurations are the same as yours. I also used the Tensorflow1.13.1 version, and the cuda version is correct However, the following errors occurred when the prediction.py program was run. The errors occurred when the pre training weights were imported