What does the tf_exported_symbols.lds do
I'm learning bazel and tensorflow, and when I check the tensorflow code I find this file:
So what does this file actually do?
See also questions close to this topic
How to implement elements comparsion in tensor by Tensorflow?
In my custom loss function, I want to implement this specific computation:
tensor A: placeholder([None, 1]) tensor B: placeholder([None, 1])
And A, B has the same shape.
tensor res: placeholder([None, 1]).
tensor A: [0, 0, 1, 2, 2, 2, 3,...] tensor B: [4, 9, 2, 3, 5, 9, 4,...] tensor res: [4, 4, 2, 3, 3, 3, 4,...]
At first, res = B, if A[i] == A[i-1], then res[i] = res[i-1]; else, res[i] = B[i]. So we get res=[4, 4, 2, 3, 3, 3, 4,...].
I'm really troubled in the question, and I'm not expected in tensorflow.Hope to answer, thx.
Does Tensorflow JAVA API support CNN training?
I want to train my CNN model with JAVA api. I already know that 1. simple operations are supported(ex. matmul) 2. Tensorflow ver 1.3 doesn't support CNN operation with JAVA api.
BUT Tensorflow updated gradually. So, I want to know whether training CNN model is possible with JAVA Tensorflow API. If possible, how can I do? If you know the tutorial or source of github, please let me know
Run MNIST on AlexNet and got ValueError: None values not supported
This is my 1st time running the MNIST dataset on AlexNet and I got this error.
Traceback (most recent call last): File "alexnet_mnist.py", line 161, in <module> pred = alexnet(x, weights,biases,keep_prob) # Feedforward predicted value File "alexnet_mnist.py", line 112, in alexnet _fc1_drop = tf.nn.dropout(_fc1, _keep_pro) # Dropout is applied for the preventtion of overfitting File "/home/joshua/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py", line 1894, in dropout x = ops.convert_to_tensor(x, name="x") File "/home/joshua/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 676, in convert_to_tensor as_ref=False) File "/home/joshua/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 741, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "/home/joshua/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 113, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name) File "/home/joshua/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 102, in constant tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape)) File "/home/joshua/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 364, in make_tensor_proto raise ValueError("None values not supported.") ValueError: None values not supported.
What does it mean? And how to solve this?