Open ProgramItUp opened 7 years ago
Hmm interesting... could you run the following script and see if it returns any errors?
https://raw.githubusercontent.com/tflearn/tflearn/master/examples/images/convnet_mnist.py
Yep. Same problem. I wonder if something went wrong during my installation or upgrade of Tensorflow?
~/tensorflow_models/models/im2txt$ python covenet_mnist.py
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcurand.so locally
Downloading MNIST...
Succesfully downloaded train-images-idx3-ubyte.gz 9912422 bytes.
Extracting mnist/train-images-idx3-ubyte.gz
Downloading MNIST...
Succesfully downloaded train-labels-idx1-ubyte.gz 28881 bytes.
Extracting mnist/train-labels-idx1-ubyte.gz
Downloading MNIST...
Succesfully downloaded t10k-images-idx3-ubyte.gz 1648877 bytes.
Extracting mnist/t10k-images-idx3-ubyte.gz
Downloading MNIST...
Succesfully downloaded t10k-labels-idx1-ubyte.gz 4542 bytes.
Extracting mnist/t10k-labels-idx1-ubyte.gz
Traceback (most recent call last):
File "covenet_mnist.py", line 31, in <module>
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
File "/usr/local/lib/python2.7/dist-packages/tflearn/layers/conv.py", line 72, in conv_2d
with tf.variable_scope(scope, name, values=[incoming], reuse=reuse) as scope:
File "/usr/lib/python2.7/contextlib.py", line 84, in helper
return GeneratorContextManager(func(*args, **kwds))
TypeError: variable_scope() got an unexpected keyword argument 'values'
From the looks of it your installation of tensorflow/cuda went wrong somewhere, or you lack a dependency
I have followed the installation instructions but am having a problem during training.
When I run
python ./train.py
the linenetwork = conv_2d(network, 8, [5, 3], activation='relu')
throws the errorTypeError: variable_scope() got an unexpected keyword argument 'values'
Any thoughts what the problem could be? Thanks,