https://github.com/tkuanlun350/Tensorflow-SegNet
Have changed in the main camvid data set inside three TXT file data path, but an error
The model is set to Training
Max training Iteration: 20000
Initial lr: 0.001000
CamVid Image dir:/home/jiang/lane/SegNet CamVid/train. TXT
CamVid Val dir:/home/jiang/lane/SegNet CamVid/Val. TXT
Batch Size: 1
Log dir:/tmp3/first350/TensorFlow/Logs
Filling the queue with 146 CamVid images before starting to "train". This will take what you can.
Filling the queue with 146 CamVid images before starting to "train". This will take what you can.
The 2017-11-06 23:39:54. 802996: I tensorflow/core/platform/cpu_feature_guard. Cc: 137] Your CPU supports instructions that this tensorflow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
Traceback (the most recent call last) :
The File "/home/jiang/lane/Tensorflow - SegNet - master/main. Py", line 52, in & lt; module>
Tf. The app. The run ()
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/platform/app. Py", 48, the line in the run
_sys. Exit (main (_sys argv [1] + flags_passthrough))
The File "/home/jiang/lane/Tensorflow - SegNet - master/main. Py", 49, line in the main
Model. Training (FLAGS, is_finetune=False)
The File "/home/jiang/lane/Tensorflow - SegNet - master/model. Py", line 389, training in
Sess. Run (init)
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/client/session. Py", line 889, in the run
Run_metadata_ptr)
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/client/session. Py", line 1120, in _run
Feed_dict_tensor, options, run_metadata)
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/client/session. Py", line 1317, in _do_run
The options, run_metadata)
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/client/session. Py", line 1336, in _do_call
Raise the type (e) (node_def, op, message)
Tensorflow. Python. Framework. Errors_impl. InvalidArgumentError: No OpKernel was registered to support the Op 'MaxPoolWithArgmax with these attrs. Registered devices: (CPU), registered kernels:
[[Node: pool1=MaxPoolWithArgmax [T=DT_FLOAT, Targmax=DT_INT64, ksize=[1, 2, 2, 1], the padding="SAME", strides=[1, 2, 2, 1]] (conv1/Relu)]]
Under Caused by op u 'pool1', defined at:
The File "/home/jiang/lane/Tensorflow - SegNet - master/main. Py", line 52, in & lt; module>
Tf. The app. The run ()
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/platform/app. Py", 48, the line in the run
_sys. Exit (main (_sys argv [1] + flags_passthrough))
The File "/home/jiang/lane/Tensorflow - SegNet - master/main. Py", 49, line in the main
Model. Training (FLAGS, is_finetune=False)
The File "/home/jiang/lane/Tensorflow - SegNet - master/model. Py", line 372, training in
Loss, eval_prediction=inference (train_data_node train_labels_node, batch_size, phase_train)
The File "/home/jiang/lane/Tensorflow - SegNet - master/model. Py", line 182, inference in
Padding='SAME, name=' pool1 ')
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/ops/gen_nn_ops py", line 3525, in max_pool_with_argmax
Padding=padding, Targmax=Targmax, name=name)
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/framework/op_def_library py", line 787, in _apply_op_helper
Op_def=op_def)
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/framework/ops. Py", line 2956, in create_op
Op_def=op_def)
The File "/usr/local/lib/python2.7/dist - packages/tensorflow/python/framework/ops. Py", line 1470, in __init__
Self. _traceback=self. _graph. _extract_stack () # pylint: disable=protected - access
InvalidArgumentError (see above for traceback) : No OpKernel was registered to support the Op 'MaxPoolWithArgmax with these attrs. Registered devices: (CPU), registered kernels:
[[Node: pool1=MaxPoolWithArgmax [T=DT_FLOAT, Targmax=DT_INT64, ksize=[1, 2, 2, 1], the padding="SAME", strides=[1, 2, 2, 1]] (conv1/Relu)]]
Don't know how to return a responsibility to check the along while also didn't found out
CodePudding user response:
Ask the great spirit guideCodePudding user response:
CodePudding user response:
MaxPoolWithArgmax this using theano realize I don't know what is it you that tf implementation, I use keras, background with theano adjustable success but the effect is not much, you can talk aboutCodePudding user response:
You will now? .CodePudding user response:
A few days before has been to solve this problem:Create a new environment, python tensorflow version is specified as 1.11=3.6 installation,
Pay attention to Util. Py file CPU or gpu
CodePudding user response:
Runfile (' C:/Users/dell/Desktop/Tensorflow SegNet - master/main p y ', wdir='C:/Users/dell/Desktop/Tensorflow SegNet - master')The model is set to Training
Max training Iteration: 20000
Initial lr: 0.001000
CamVid Image dir: C:/Users/dell/Desktop/Tensorflow - SegNet - master/CamVid/train. TXT
nullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnullnull