Following is my code using tensorflow, and I have been trying to debug this error for two days...
changed_result = y_conv.eval(feed_dict={x: pixelNew, keep_prob: 1.0})
and:
changed_result = tf.Variable([0.0],tf.float32)
I have tried making changed_result a tensor or just not declaring it. Both won't work.
Below is the whole error description:
Traceback (most recent call last): File "deepMnist.py", line 235, in tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
File "/Users/ximinlin/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 43, in run sys.exit(main(sys.argv[:1] + flags_passthrough))
File "deepMnist.py", line 162, in main changed_result = y_conv.eval(feed_dict={x: pixelNew, keep_prob: 1.0}) File "/Users/ximinlin/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 575, in eval return _eval_using_default_session(self, feed_dict, self.graph, session)
File "/Users/ximinlin/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3633, in _eval_using_default_session return session.run(tensors, feed_dict)
File "/Users/ximinlin/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 766, in run run_metadata_ptr)
File "/Users/ximinlin/anaconda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 921, in _run + e.args[0]) TypeError: Cannot interpret feed_dict key as Tensor: Can not convert a int into a Tensor.
Following is definition of x and keep_pro:
x = tf.placeholder(tf.float32, [None, 784])
keep_prob = 0
keep_prob, and x are actually code from tensorflow tutorial, and I just copy them to my code
